CN111784030B - Distributed photovoltaic power prediction method and device based on spatial correlation - Google Patents
Distributed photovoltaic power prediction method and device based on spatial correlation Download PDFInfo
- Publication number
- CN111784030B CN111784030B CN202010534498.5A CN202010534498A CN111784030B CN 111784030 B CN111784030 B CN 111784030B CN 202010534498 A CN202010534498 A CN 202010534498A CN 111784030 B CN111784030 B CN 111784030B
- Authority
- CN
- China
- Prior art keywords
- historical
- distributed photovoltaic
- power
- photovoltaic
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 80
- 238000010248 power generation Methods 0.000 claims abstract description 123
- 230000008439 repair process Effects 0.000 claims abstract description 37
- 230000002159 abnormal effect Effects 0.000 claims abstract description 30
- 238000012937 correction Methods 0.000 claims description 36
- 238000004458 analytical method Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 19
- 238000012417 linear regression Methods 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 14
- 238000012545 processing Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000007795 chemical reaction product Substances 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Photovoltaic Devices (AREA)
Abstract
The application provides a distributed photovoltaic power prediction method and device based on spatial correlation, comprising the following steps: performing abnormal repair on the obtained historical power generation data of the distributed photovoltaic and the centralized photovoltaic within a preset range; acquiring a historical generating capacity sequence of the distributed photovoltaic and a historical generating capacity sequence of the centralized photovoltaic from the repaired historical generating capacity data; determining a reference power station of the distributed photovoltaic from all the centralized photovoltaic according to the historical power generation amount sequence of the distributed photovoltaic and the historical power generation amount sequence of the centralized photovoltaic; and predicting the power of the distributed photovoltaic according to the relation between the historical power generation data of the reference power station and the historical power generation data of the distributed photovoltaic. The application realizes the distributed photovoltaic practical power prediction by utilizing the existing daily power generation amount data under the condition of no need of configuring a power prediction system.
Description
Technical Field
The application belongs to the technical field of distributed photovoltaic power generation, and particularly relates to a distributed photovoltaic power prediction method and device based on spatial correlation.
Background
Photovoltaic power generation is gradually developing from a high-voltage-class centralized photovoltaic power station to a low-voltage-class large-scale distributed photovoltaic grid-connected as a main renewable energy source accessed in a high proportion. By the end of 2019, the distributed photovoltaic accessed by 10kV and below in the Jibei area is over 1500MW, wherein the distributed photovoltaic of the users accessed by 220/380V at low voltage accounts for about 60%. With the rapid increase of the distributed photovoltaic access capacity, the conventional daily load prediction and the operation and control of the power grid are brought with serious challenges to the regional dispatching department. For the distributed photovoltaic with 220/380V grade single point access, the power information is not uploaded to the dispatching system, and only the daily electricity quantity data is uploaded to the electricity consumption information acquisition system of the power grid company. Therefore, how to utilize the existing data to develop the distributed photovoltaic prediction has important significance for power grid dispatching control and power grid operation.
Theoretically, distributed photovoltaic power prediction can be divided into direct prediction and indirect prediction methods. The direct prediction method is essentially a data statistics prediction method, and a photovoltaic prediction model is established according to historical data of photovoltaic output, and mainly comprises a time sequence prediction method, a gray theory prediction method, a multiple linear regression prediction method and the like. The indirect prediction method is to directly predict according to weather forecast data without providing historical data of photovoltaic output, and mainly comprises numerical weather forecast (NWP) and a base cloud picture. The power prediction method is mainly suitable for a photovoltaic power station provided with a meteorological information acquisition system and a power prediction system, the single-point access distributed photovoltaic capacity is small, and the investment cost of independently configuring the power prediction system is too high to popularize.
Disclosure of Invention
The application provides a distributed photovoltaic power prediction method and device based on spatial correlation, which at least solve the problem that the power of a distributed photovoltaic is difficult to accurately predict in the prior art.
According to one aspect of the present application, there is provided a distributed photovoltaic power prediction method based on spatial correlation, including:
performing abnormal repair on the obtained historical power generation data of the distributed photovoltaic and the centralized photovoltaic within a preset range;
acquiring a historical generating capacity sequence of the distributed photovoltaic and a historical generating capacity sequence of the centralized photovoltaic from the repaired historical generating capacity data;
determining a reference power station of the distributed photovoltaic from all the centralized photovoltaic according to the historical power generation amount sequence of the distributed photovoltaic and the historical power generation amount sequence of the centralized photovoltaic;
predicting the power of the distributed photovoltaic according to the relation between the historical power generation data of the reference power station and the historical power generation data of the distributed photovoltaic;
and carrying out error analysis on the predicted distributed photovoltaic power, and carrying out error correction according to the error analysis result.
In an embodiment, performing anomaly repair on the obtained historical power generation data of the distributed photovoltaic and all the centralized photovoltaic within a preset range includes:
Searching for vacant data in the historical generating capacity data and judging the type of the vacant data;
if the type of the vacant data is point missing, repairing by adopting an adjacent data spline interpolation method;
if the type of the vacant data is continuous missing, a similar daily linear regression method is adopted for repairing.
In an embodiment, the performing anomaly repair on the obtained historical power generation data of the distributed photovoltaic and the centralized photovoltaic within a preset range further includes:
and repairing the out-of-range abnormal data and the abnormal fluctuation data in the historical power generation data by adopting an adjacent data spline interpolation method.
In one embodiment, predicting the power of the distributed photovoltaic from a relationship of historical power generation data of a reference power plant to historical power generation data of the distributed photovoltaic comprises:
obtaining an on-load capacity ratio according to the historical power generation amount of the distributed photovoltaic and the historical power generation amount of the reference power station;
obtaining historical on-stream capacity of the distributed photovoltaic according to the historical on-stream capacity and the on-stream capacity ratio of the reference power station;
establishing a proportional relation between a power prediction sequence and a historical operating capacity;
and obtaining the power prediction sequence of the distributed photovoltaic according to the proportional relation between the power prediction sequence and the historical on-operation capacity, the power prediction sequence of the reference power station and the on-operation capacity ratio.
In one embodiment, error analysis of predicted power of a distributed photovoltaic includes:
determining an error source of power of the distributed photovoltaic according to a capacity calculation coefficient of the distributed photovoltaic, a unit on-operation capacity prediction error of a reference power station and a unit on-operation capacity power generation power difference value of the distributed photovoltaic and the reference power station, wherein the error source comprises: performance errors, capacity errors, and external errors.
In one embodiment, performing error correction according to the result of the error analysis includes:
and correcting the performance error and the capacity error.
According to another aspect of the present application, there is also provided a distributed photovoltaic power prediction apparatus based on spatial correlation, including:
the abnormal repair unit is used for carrying out abnormal repair on the acquired historical power generation amount data of the distributed photovoltaic and the centralized photovoltaic within a preset range;
the historical generating capacity sequence obtaining unit is used for obtaining a historical generating capacity sequence of the distributed photovoltaic and a historical generating capacity sequence of the centralized photovoltaic from the repaired historical generating capacity data;
the reference power station determining unit is used for determining a reference power station of the distributed photovoltaic from all the concentrated photovoltaic according to the historical power generation amount sequence of the distributed photovoltaic and the historical power generation amount sequence of the concentrated photovoltaic;
The photovoltaic power station power prediction unit is used for predicting the power of the distributed photovoltaic according to the relation between the historical power generation amount data of the reference power station and the historical power generation amount data of the distributed photovoltaic;
and the error correction unit is used for carrying out error analysis on the predicted distributed photovoltaic power and carrying out error correction according to the error analysis result.
In one embodiment, the anomaly repair unit includes:
the vacancy type judging module is used for searching vacancy data in the historical generating capacity data and judging the type of the vacancy data;
the spline interpolation method repair module is used for repairing by adopting an adjacent data spline interpolation method if the type of the vacant data is point missing;
and the linear regression method repair module is used for repairing by adopting a similar daily linear regression method if the type of the vacant data is continuous missing.
In an embodiment, the anomaly repair unit further includes:
and the abnormal data repair module is used for repairing the out-of-range abnormal data and the abnormal fluctuation data in the historical power generation data by adopting an adjacent data spline interpolation method.
In an embodiment, a photovoltaic power plant power prediction unit comprises:
the on-line capacity ratio acquisition module is used for acquiring an on-line capacity ratio according to the historical power generation amount of the distributed photovoltaic and the historical power generation amount of the reference power station;
The historical on-line capacity acquisition module is used for acquiring the historical on-line capacity of the distributed photovoltaic according to the historical on-line capacity and the on-line capacity ratio of the reference power station;
the relation establishing module is used for establishing a proportional relation between the power prediction sequence and the historical operating capacity;
and the power prediction sequence acquisition module is used for acquiring the power prediction sequence of the distributed photovoltaic according to the proportional relation between the power prediction sequence and the historical on-operation capacity, the power prediction sequence of the reference power station and the on-operation capacity ratio.
In one embodiment, the error correction unit includes: the analysis module is used for determining error sources of power of the distributed photovoltaic according to the capacity calculation coefficient of the distributed photovoltaic, the unit on-operation capacity prediction error of the reference power station and the unit on-operation capacity power generation power difference value of the distributed photovoltaic and the reference power station, and the error sources comprise: performance errors, capacity errors, and external errors.
In an embodiment, the error correction unit further comprises: and the correction module is used for correcting the performance error and the capacity error.
In a certain geographical range, the distributed photovoltaic and the adjacent concentrated photovoltaic output data have space-time correlation, the application utilizes the characteristic that the mapping relation between the distributed photovoltaic and the reference power station is established through the daily power generation amount data of the distributed photovoltaic and the daily power generation amount data of the reference power station, so as to calculate the power prediction curve of the distributed photovoltaic by referring to the power prediction system curve of the power station, quantitatively deduce the error source of the prediction method and correct the error source. The power prediction system has the advantage that the function of predicting the power of the distributed photovoltaic by utilizing the existing solar energy generation amount data is realized under the condition that a power prediction system is not required to be configured.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a distributed photovoltaic power prediction method based on spatial correlation.
FIG. 2 is a flowchart of performing anomaly repair on historical power generation data in an embodiment of the application.
Fig. 3 is a flowchart of a specific calculation method for predicting the distributed photovoltaic power in the present application.
Fig. 4 is a flowchart of error analysis and error correction for a predicted result of distributed photovoltaic power according to an embodiment of the present application.
Fig. 5 is a block diagram of a distributed photovoltaic power prediction apparatus based on spatial correlation.
FIG. 6 is a block diagram illustrating an anomaly repair unit according to an embodiment of the present application.
Fig. 7 is a block diagram of a photovoltaic power plant power prediction unit according to an embodiment of the present application.
Fig. 8 is a schematic diagram of a photovoltaic distribution geographic location in an embodiment of the present application.
FIG. 9 is a graph showing the comparison of the predicted curve and the actual power value in an embodiment of the present application.
Fig. 10 illustrates a comparison curve of the power average of distributed photovoltaic time-sharing within statistical date before and after correction in an embodiment of the present application.
Fig. 11 is a specific implementation of an electronic device according to an embodiment of the present application.
Fig. 12 is a differentiated correction chart based on a time-sharing power ratio, which is used for performing performance error correction on a distributed power prediction result.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the prior art, the method for predicting the distributed photovoltaic power is mainly suitable for a photovoltaic power station provided with a meteorological information acquisition system and a power prediction system, and the single-point access distributed photovoltaic has small capacity, so that the early cost of independently configuring the power prediction system is too high, and in order to solve the problem of predicting the single-point access distributed photovoltaic, the application provides a method for predicting the distributed photovoltaic power based on spatial correlation, which is shown in a figure 1 and comprises the following steps:
S101: and carrying out abnormal repair on the obtained historical power generation data of the distributed photovoltaic and the centralized photovoltaic within a preset range.
In a specific embodiment, firstly, aiming at a target distributed photovoltaic, historical power generation data of the target distributed photovoltaic and historical power generation data of a plurality of centralized photovoltaic power stations within a certain distance range are obtained, and then, the obtained historical power generation data are subjected to data cleaning. After the cleaning is finished, checking whether abnormal data or missing data exist in the historical generating capacity data, and repairing.
S102: and acquiring a historical generating capacity sequence of the distributed photovoltaic and a historical generating capacity sequence of the centralized photovoltaic from the repaired historical generating capacity data.
In a specific embodiment, the daily power generation amount of the distributed photovoltaic and the daily power generation amount of the adjacent centralized photovoltaic power station are obtained from the repaired historical power generation amount data, and a historical power generation amount sequence Q of the distributed photovoltaic is formed DG ＝{Q DG,1 ,Q DG,2 ,…,Q DG,n-1 Historical power generation sequence Q of adjacent centralized photovoltaic power station PV ＝{Q PV,1 ,Q PV ,2,…,Q PV,n-1 }。
S103: and determining a reference power station of the distributed photovoltaic from all the concentrated photovoltaic according to the historical power generation amount sequence of the distributed photovoltaic and the historical power generation amount sequence of the concentrated photovoltaic.
In one embodiment, it is assumed that the historical power generation sequence of the distributed photovoltaic is Q DG ＝{Q DG,1 ,Q DG ,2,…,Q DG,n-1 The historical power generation sequence of the adjacent centralized photovoltaic power station is Q PV ＝{Q PV,1 ,Q PV,2 ,…,Q PV,n-1 }, then Q DG And Q PV The pearson correlation coefficient of (c) is:
and selecting the centralized power station with the largest coefficient of the pearson correlation with the distributed photovoltaic power generation amount as a reference power station for power prediction.
S104: and predicting the power of the distributed photovoltaic according to the relation between the historical power generation data of the reference power station and the historical power generation data of the distributed photovoltaic.
In a specific embodiment, the reference power station selected in step S103 is the power station closest to the target distributed photovoltaic, a power generation mapping relationship is established by using the historical power generation data of the reference power station and the historical power generation data of the (target) distributed photovoltaic, and then the power of the distributed photovoltaic is primarily predicted according to the power generation mapping relationship.
S105: and correcting the performance error and the capacity error according to error sources deduced by the formula to obtain a final power prediction result.
The execution main body of the method shown in fig. 1 can be a PC, a terminal, etc., and the function of accurately predicting distributed photovoltaic power is realized through the data of the distributed photovoltaic solar energy generation capacity and the adjacent concentrated photovoltaic solar energy generation capacity.
In an embodiment, performing anomaly repair on the obtained historical power generation data of the distributed photovoltaic and all centralized photovoltaic within a preset range, as shown in fig. 2, includes:
s201: and searching for the vacant data in the historical generating capacity data and judging the type of the vacant data.
S202: if the type of the vacant data is point missing, repairing by adopting an adjacent data spline interpolation method.
S203: if the type of the vacant data is continuous missing, a similar daily linear regression method is adopted for repairing.
In a specific embodiment, the method searches for vacant data in the historical generated energy data after data cleaning, wherein the vacant data has two types, one is point missing and the other is continuous missing, the point missing data is usually caused by data transmission problems, an adjacent data spline interpolation method is adopted for individual missing points, and a similar day linear regression method is adopted for data patching for the continuous missing data.
In an embodiment, the performing anomaly repair on the obtained historical power generation data of the distributed photovoltaic and the centralized photovoltaic within a preset range further includes:
and repairing the out-of-range abnormal data and the abnormal fluctuation data in the historical power generation data by adopting an adjacent data spline interpolation method.
In a specific embodiment, because the transmission error or the historical generating capacity data of which the stored abnormal photovoltaic power data exceeds the capacity range or is negative is the out-of-range abnormal data, the data is judged by setting upper and lower limits, and then is repaired by using a spline interpolation method; and aiming at abnormal fluctuation data in the historical power generation data, filling by adopting an adjacent data spline interpolation method.
In one embodiment, predicting the power of the distributed photovoltaic from a relationship of historical power generation data of the reference power plant and the historical power generation data of the distributed photovoltaic, as shown in fig. 3, comprises:
s301: and obtaining the on-load capacity ratio according to the historical power generation amount of the distributed photovoltaic and the historical power generation amount of the reference power station.
In one embodiment, the photovoltaic power generation amount Q is distributed according to the i-1 th day DG,i-1 And referring to the power generation amount Q of the power station PV,i-1 Calculating the ratio k of the i-1 th day distributed photovoltaic power station to the reference power station in the running capacity i-1 The following formula:
k i-1 ＝Q PV,i-1 /Q DG,i-1 (2)
s302: and obtaining the historical on-stream capacity of the distributed photovoltaic according to the historical on-stream capacity and the on-stream capacity ratio of the reference power station.
In one embodiment, the operating capacity M is known to be on day i-1 of the reference plant PV,i-1 Calculate the running capacity M of the distributed light Fu Di i-1 day DG,i-1 The following formula:
M DG,i-1 ＝M PV,i-1 /k i-1 ＝M PV,i-1 Q DG,i-1 /Q PV,i-1 (3)
s303: and establishing a proportional relation between the power prediction sequence and the historical operating capacity.
In a specific embodiment, if the interference of different equipment models and operation modes on the photovoltaic output performance is not considered, the same output predicted value is corresponding to the same on-operating capacity of the distributed photovoltaic and the reference power station, and the following formula is adopted:
in the middle ofPower prediction sequences for the i-1 day distributed photovoltaic and reference power stations, respectively.
S304: and obtaining the power prediction sequence of the distributed photovoltaic according to the proportional relation between the power prediction sequence and the historical on-operation capacity, the power prediction sequence of the reference power station and the on-operation capacity ratio.
In one embodiment, the estimated power prediction sequence of Fu Di i days for distributed light can be initially calculated from the formula (3) and the formula (4)
The power prediction result obtained according to the above formula usually has a large error, and the main reason is that the output characteristics of the distributed photovoltaic and the reference power station are different in actual engineering, so that error correction is required to be performed on the prediction result.
As shown in fig. 4, the error analysis on the predicted result of the distributed photovoltaic power specifically includes the following steps:
s401: a source of prediction error is determined. The following parameters are defined:
1) Distributed photovoltaic capacity conversion coefficient m DG,i-1 Its value is the estimated value M of the running capacity DG,i-1 And rated capacity M DG,N Ratio of;
2) Prediction error delta P of current operation capacity of reference power station unit i，1 Reflecting errors existing in a power prediction system of the reference power station;
3) Power difference delta P between distributed photovoltaic and reference power station unit in-operation capacity i,2 Reflecting the difference in power generation performance of the distributed photovoltaic and reference power stations.
By mathematical derivation, the distributed photovoltaic prediction error delta P can be obtained i The following relation is satisfied:
ΔP i ＝m DG,i-1 M DG,N (ΔP i,1 +ΔP i,2 ) (6)
from the above equation, it can be seen that there are mainly three parts of the prediction error sources. First, reference is made to the power prediction error (Δp) of the plant itself i,1 ) The external error is not optimized; secondly, the reference power station and the distributed photovoltaic power generation performance difference (delta P) i,2 ) Known as performance error; third, the capacity conversion coefficient m DG,i-1 Referred to as capacity error, and ΔP i,2 、m DG,i-1 There is a fixed mathematical relationship, for distributed photovoltaics, external errors are objectively unchangeable, but performance errors and capacity errors can be corrected, and the power prediction accuracy of the distributed photovoltaics can be improved.
S402: and correcting the prediction error. Error correction is required by adopting different modes according to the source of the error, and the following is discussed in case:
When the error source is performance error, the difference based on time-sharing electric quantity ratio is adoptedAnd (3) a chemical correction strategy, namely distributing the daily electric quantity errors caused by the power generation performance difference according to the time-sharing electric quantity proportion and considering the electric quantity fluctuation of adjacent intervals, wherein the area surrounded by the power curve and the time axis is the daily electric quantity, the solid line is the power without considering the performance errors, and the dotted line is the power after correcting the performance errors, as shown in fig. 12. Taking the example that the power generation performance of the reference power station is better than that of the distributed photovoltaic, the time-sharing power generation amount of the reference power station is set as S PV ＝{s 1 ,s 2 ,…,s 96 Time-sharing generating capacity obtained by converting power generation performance of distributed photovoltaic is S DG ＝{n 1 s 1 ,n 2 s 2 ,…,n 96 s 96 Then the solar energy difference delta Q of the reference power station is converted PV Can be approximated as:
to calculate the coefficient n t Value, consider the power fluctuation of adjacent 3 time periods, Δq PV The allocation is made according to the following formula:
the formula is that alpha is a fluctuation following factor, and is an error adjustment parameter (fluctuation following factor) set by engineering practice in consideration of that the power generation performance difference is larger at high power and smaller at low power, and the calculation formula is as follows:
when the error source is a capacity error, the following discussion is needed:
1) When m is DG,i-1 When the temperature is less than or equal to 1, the converted distributed photovoltaic operation capacity M DG,i Not exceeding the rated capacity M DG,N The power predictive value does not exceed the rated capacity.
2) When m is DG,i-1 At > 1, the converted distributed photovoltaic operating capacity M DG,i Will exceed its rated capacity M DG,N . During peak power periods of the reference power station, the predicted power value converted to the distributed photovoltaic exceeds the rated capacity, and the predicted power error can be corrected.
According to the classification, correcting the error according to the following error function:
where n= {1,2,3, …,96}. I.e. when m DG,i-1 > 1 and predicted powerGreater than rated capacity M DG,N When considering capacity limitation, m will be DG,i-1 Taking 1, the power predicted value converted to the distributed photovoltaic side at this time is the rated capacity value, and the prediction error is the same as the above under other conditions.
The execution main body of the method shown in fig. 4 can be a PC, a terminal, etc., the application performs quantitative error analysis on the power prediction method, derives a relation between the power prediction error and 3 kinds of error sources, the relation is suitable for analyzing other distributed photovoltaic power prediction errors by adopting the proposed method, and the function of further reducing the error is realized by setting an error function in the output peak period.
Based on the same inventive concept, the embodiments of the present application also provide a distributed photovoltaic power prediction apparatus based on spatial correlation, which can be used to implement the method described in the above embodiments, as described in the following embodiments. Because the principle of solving the problem of the distributed photovoltaic power prediction device based on the spatial correlation is similar to that of the distributed photovoltaic power prediction method based on the spatial correlation, the implementation of the distributed photovoltaic power prediction device based on the spatial correlation can be referred to the implementation of the distributed photovoltaic power prediction method based on the spatial correlation, and the repetition is omitted. As used below, the term "unit" or "module" may be a combination of software and/or hardware that implements the intended function. While the system described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
The application provides a distributed photovoltaic power prediction device based on spatial correlation, as shown in fig. 5, comprising:
an anomaly repair unit 501, configured to perform anomaly repair on the obtained historical power generation amount data of the distributed photovoltaic and the centralized photovoltaic within a preset range;
a historical power generation amount sequence obtaining unit 502, configured to obtain a historical power generation amount sequence of the distributed photovoltaic and a historical power generation amount sequence of the centralized photovoltaic from the repaired historical power generation amount data;
a reference power station determining unit 503 for determining a reference power station of the distributed photovoltaic from all the concentrated photovoltaic according to the historical power generation amount sequence of the distributed photovoltaic and the historical power generation amount sequence of the concentrated photovoltaic;
the photovoltaic power station power prediction unit 504 is configured to predict the power of the distributed photovoltaic according to the relation between the historical power generation amount data of the reference power station and the historical power generation amount data of the distributed photovoltaic.
The error correction unit 505 is configured to perform error analysis on the predicted power of the distributed photovoltaic, and perform error correction according to the result of the error analysis.
In one embodiment, as shown in fig. 6, the anomaly repair unit 501 includes:
the vacancy type judging module 601 is configured to find vacancy data in the historical power generation amount data and judge the type of the vacancy data;
The spline interpolation method repair module 602 is configured to repair by adopting an adjacent data spline interpolation method if the type of the blank data is a point missing;
the linear regression method repair module 603 is configured to repair if the type of the missing data is continuous missing, by using a similar daily linear regression method.
In an embodiment, the anomaly repair unit further includes:
and the abnormal data repair module is used for repairing the out-of-range abnormal data and the abnormal fluctuation data in the historical power generation data by adopting an adjacent data spline interpolation method.
In one embodiment, as shown in fig. 7, the photovoltaic power plant power prediction unit 504 includes:
the on-line capacity ratio acquisition module 701 is used for acquiring an on-line capacity ratio according to the historical power generation amount of the distributed photovoltaic and the historical power generation amount of the reference power station;
the historical on-stream capacity acquisition module 702 is configured to obtain a historical on-stream capacity of the distributed photovoltaic according to the historical on-stream capacity and the on-stream capacity ratio of the reference power station;
a relationship establishing module 703, configured to establish a proportional relationship between the power prediction sequence and the historical operating capacity;
and the power prediction sequence acquisition module 704 is used for acquiring the power prediction sequence of the distributed photovoltaic according to the proportional relation between the power prediction sequence and the historical on-operation capacity, the power prediction sequence of the reference power station and the on-operation capacity ratio.
In one embodiment, the error correction unit 505 includes: the analysis module is used for determining error sources of power of the distributed photovoltaic according to the capacity calculation coefficient of the distributed photovoltaic, the unit on-operation capacity prediction error of the reference power station and the unit on-operation capacity power generation power difference value of the distributed photovoltaic and the reference power station, and the error sources comprise: performance errors, capacity errors, and external errors.
In an embodiment, the error correction unit 505 further includes: and the correction module is used for correcting the performance error and the capacity error.
In order to support the distributed photovoltaic power prediction method provided by the application, the following describes the practical use case of the distributed photovoltaic power prediction method provided by the application:
four distributed photovoltaics of #1 (20.5 kW), #2 (113.4 kW), #3 (135 kW) and #4 (108 kW) in Shangyi county of Zhangkou are selected, and 96-point power true values of the distributed photovoltaics are recorded by installing a power metering device of a certain company. And comparing the predicted value of the practical prediction method with the actual value.
The distributed photovoltaic periphery has 3 centralized photovoltaic power stations with unequal distances, namely an A station (28 MW), a B station (8 WM) and a C station (20 WM). The geographic locations of the four distributed photovoltaics and the three centralized photovoltaics are shown in fig. 8.
The following indicators are analyzed for the distributed photovoltaic power prediction method, briefly described below.
(1) Relative power error delta j
(2) Maximum positive power errorMaximum negative error->
(3) Power daily average absolute error epsilon P
(4) Root mean square error gamma of power P
In the formulas (16) to (20),for the j-th data point power in distributed photovoltaic 1 dayPredictive value->For the j-th data point power actual value, N is the number of data points, P N Is a distributed photovoltaic rated capacity.
The measurement time is 161 days in total from 1 month 1 day in 2019 to 6 months 10 days in 2019, and comprises 15 minutes of instantaneous power measurement value and electric quantity data. Based on the method, after abnormal data processing in the measurement time, the average value of the correlation coefficients of the distributed photovoltaic power station and the centralized photovoltaic power station is shown in the following table.
TABLE 1 average correlation coefficient
It can be seen from the table that the correlation coefficient between the distributed photovoltaic and the a photovoltaic power station is the highest, so the a photovoltaic power station is selected as the reference power station.
Taking #4 distributed photovoltaic as an example, a typical day prediction curve of 2019 month 3 was selected for comparison with the actual power values, as shown in fig. 9.
It can be seen that for a typical day, the power prediction curve is highly fitted to the actual power curve, and the power prediction value is higher than the actual value during peak output time, but the prediction deviation during peak output time after correction is reduced.
In the statistical days, the power prediction error indexes of the distributed photovoltaic are shown in table 2, and all indexes are average values of formulas (11) to (14).
Table 2 power prediction error index for power station with a as reference
It can be seen that the average absolute daily error of 4 distributed photovoltaic modules before correction is between 7.20% and 7.21%, and after correction is between 5.53% and 6.07%, wherein the average daily absolute error of the #2 distributed modules after correction is 5.53%, which is very close to that of a reference power station; the root error of the day square before the correction of the distributed photovoltaic is 12.45-13.37 percent, and the root error after the correction is 9.67-10.80 percent, and both indexes are improved.
Taking #4 distributed photovoltaic as an example, the distributed photovoltaic time-sharing power average comparison curve in the statistics of the statistics before and after the correction obtained by the formula (12) is shown in fig. 10. As can be seen from fig. 10, the time-sharing power prediction average before correction is overall larger, and the prediction error increases with the increase of the output, and the time-sharing power prediction average after correction is still higher than the actual value, but the error significantly decreases. At the peak time, the time-sharing power average value before correction is 84.6kW, the actual time-sharing power average value is 69.4kW, and the maximum error is about 14.1%; the corrected time-sharing power average value is 77.6kW, and the maximum error is reduced to 7.6%.
According to the application, the map of the centralized photovoltaic power station and the distributed photovoltaic is established through the daily power generation amount data, the power prediction value of the reference power station is utilized to calculate the distributed power prediction value, a power prediction system is not required to be arranged, and the power prediction of the distributed photovoltaic can be realized, so that the method has economical efficiency and practicability. The application also deduces the error source adopting the power prediction method, and further reduces the prediction error by correcting the error in the output peak period.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principles and embodiments of the present invention have been described in detail with reference to specific examples, which are provided to facilitate understanding of the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
The embodiment of the present application further provides a specific implementation manner of an electronic device capable of implementing all the steps in the method in the foregoing embodiment, and referring to fig. 11, the electronic device specifically includes the following:
a processor 1001, a memory 1002, a communication interface (Communications Interface) 1003, a bus 1004, and a nonvolatile memory 1005;
wherein, the processor 1001, the memory 1002, and the communication interface 1003 complete communication with each other through the bus 1004;
the processor 1001 is configured to invoke the computer program in the memory 1002 and the nonvolatile memory 1005, where the processor executes the computer program to implement all the steps in the method in the foregoing embodiment, for example, the processor executes the computer program to implement the following steps:
s101: and carrying out abnormal repair on the obtained historical power generation data of the distributed photovoltaic and the centralized photovoltaic within a preset range.
S102: and acquiring a historical generating capacity sequence of the distributed photovoltaic and a historical generating capacity sequence of the centralized photovoltaic from the repaired historical generating capacity data.
S103: and determining a reference power station of the distributed photovoltaic from all the concentrated photovoltaic according to the historical power generation amount sequence of the distributed photovoltaic and the historical power generation amount sequence of the concentrated photovoltaic.
S104: and predicting the power of the distributed photovoltaic according to the relation between the historical power generation data of the reference power station and the historical power generation data of the distributed photovoltaic.
S105: and correcting the performance error and the capacity error according to error sources deduced by the formula to obtain a final power prediction result.
An embodiment of the present application also provides a computer-readable storage medium capable of implementing all the steps of the method in the above embodiment, the computer-readable storage medium storing thereon a computer program that, when executed by a processor, implements all the steps of the method in the above embodiment, for example, the processor implements the following steps when executing the computer program:
s101: and carrying out abnormal repair on the obtained historical power generation data of the distributed photovoltaic and the centralized photovoltaic within a preset range.
S102: and acquiring a historical generating capacity sequence of the distributed photovoltaic and a historical generating capacity sequence of the centralized photovoltaic from the repaired historical generating capacity data.
S103: and determining a reference power station of the distributed photovoltaic from all the concentrated photovoltaic according to the historical power generation amount sequence of the distributed photovoltaic and the historical power generation amount sequence of the concentrated photovoltaic.
S104: and predicting the power of the distributed photovoltaic according to the relation between the historical power generation data of the reference power station and the historical power generation data of the distributed photovoltaic.
S105: and correcting the performance error and the capacity error according to error sources deduced by the formula to obtain a final power prediction result.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for a hardware+program class embodiment, the description is relatively simple, as it is substantially similar to the method embodiment, as relevant see the partial description of the method embodiment. Although the present description provides method operational steps as described in the examples or flowcharts, more or fewer operational steps may be included based on conventional or non-inventive means. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution. When implemented in an actual device or end product, the instructions may be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment, or even in a distributed data processing environment) as illustrated by the embodiments or by the figures. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, it is not excluded that additional identical or equivalent elements may be present in a process, method, article, or apparatus that comprises a described element. For convenience of description, the above devices are described as being functionally divided into various modules, respectively. Of course, when implementing the embodiments of the present disclosure, the functions of each module may be implemented in the same or multiple pieces of software and/or hardware, or a module that implements the same function may be implemented by multiple sub-modules or a combination of sub-units, or the like. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form. The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be appreciated by those skilled in the art that embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the present specification embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present description embodiments may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein. In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction. The foregoing is merely an example of an embodiment of the present disclosure and is not intended to limit the embodiment of the present disclosure. Various modifications and variations of the illustrative embodiments will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, or the like, which is within the spirit and principles of the embodiments of the present specification, should be included in the scope of the claims of the embodiments of the present specification.
Claims (14)
1. A distributed photovoltaic power prediction method based on spatial correlation, comprising:
performing abnormal repair on the obtained historical power generation data of the distributed photovoltaic and the centralized photovoltaic within a preset range; the concentrated photovoltaic in the preset range is a concentrated photovoltaic adjacent to the distributed photovoltaic;
acquiring a historical generating capacity sequence of the distributed photovoltaic and a historical generating capacity sequence of the centralized photovoltaic from the repaired historical generating capacity data;
determining a reference power station of the distributed photovoltaic from all the concentrated photovoltaic according to the historical power generation amount sequence of the distributed photovoltaic and the historical power generation amount sequence of the concentrated photovoltaic;
predicting the power of the distributed photovoltaic according to the relation between the historical power generation amount data of the reference power station and the historical power generation amount data of the distributed photovoltaic;
performing error analysis on the predicted distributed photovoltaic power, and performing error correction according to the error analysis result;
the determining the reference power station of the distributed photovoltaic from all the concentrated photovoltaic according to the historical power generation amount sequence of the distributed photovoltaic and the historical power generation amount sequence of the concentrated photovoltaic comprises the following steps:
Calculating a pearson correlation coefficient according to the historical power generation amount sequence of the distributed photovoltaic and the historical power generation amount sequence of the centralized photovoltaic;
and selecting the concentrated photovoltaic with the largest correlation coefficient with the distributed light Fu Pier as a reference power station.
2. The method for predicting distributed photovoltaic power according to claim 1, wherein the performing anomaly repair on the obtained historical power generation data of the distributed photovoltaic and all the centralized photovoltaic within a preset range comprises:
searching for vacant data in the historical generating capacity data and judging the type of the vacant data;
if the type of the vacant data is point missing, repairing by adopting an adjacent data spline interpolation method;
if the type of the vacancy data is continuous missing, a similar daily linear regression method is adopted for repairing.
3. The method for predicting distributed photovoltaic power according to claim 2, wherein the performing anomaly repair on the obtained historical power generation data of the distributed photovoltaic and the centralized photovoltaic within a preset range further comprises:
and repairing the out-of-range abnormal data and the abnormal fluctuation data in the historical power generation data by adopting an adjacent data spline interpolation method.
4. A method of predicting distributed photovoltaic power according to claim 1, wherein predicting the power of the distributed photovoltaic from a relationship of historical power generation data of the reference power plant and historical power generation data of the distributed photovoltaic comprises:
obtaining an on-load capacity ratio according to the historical power generation amount of the distributed photovoltaic and the historical power generation amount of the reference power station;
obtaining historical on-stream capacity of the distributed photovoltaic according to the historical on-stream capacity of the reference power station and the on-stream capacity ratio;
establishing a proportional relation between a power prediction sequence and the historical operating capacity;
and obtaining a power prediction sequence of the distributed photovoltaic according to the proportional relation between the power prediction sequence and the historical on-line capacity, the power prediction sequence of the reference power station and the on-line capacity ratio.
5. The method of claim 1, wherein said error analyzing the predicted power of the distributed photovoltaic comprises:
determining an error source of power of the distributed photovoltaic according to a capacity calculation coefficient of the distributed photovoltaic, a unit on-operation capacity prediction error of the reference power station and a unit on-operation capacity power generation power difference value of the distributed photovoltaic and the reference power station, wherein the error source comprises: performance errors, capacity errors, and external errors.
6. The method of claim 5, wherein the performing error correction based on the result of the error analysis comprises:
and correcting the performance error and the capacity error.
7. A distributed photovoltaic power prediction apparatus based on spatial correlation, comprising:
the abnormal repair unit is used for carrying out abnormal repair on the acquired historical power generation amount data of the distributed photovoltaic and the centralized photovoltaic within a preset range; the concentrated photovoltaic in the preset range is a concentrated photovoltaic adjacent to the distributed photovoltaic;
the historical generating capacity sequence obtaining unit is used for obtaining a historical generating capacity sequence of the distributed photovoltaic and a historical generating capacity sequence of the centralized photovoltaic from the repaired historical generating capacity data;
a reference power station determining unit configured to determine a reference power station of the distributed photovoltaic from all the concentrated photovoltaic according to the historical power generation amount sequence of the distributed photovoltaic and the historical power generation amount sequence of the concentrated photovoltaic;
the photovoltaic power station power prediction unit is used for predicting the power of the distributed photovoltaic according to the relation between the historical power generation amount data of the reference power station and the historical power generation amount data of the distributed photovoltaic;
The error correction unit is used for carrying out error analysis on the predicted distributed photovoltaic power and carrying out error correction according to the error analysis result;
the reference power station determining unit is specifically configured to:
calculating a pearson correlation coefficient according to the historical power generation amount sequence of the distributed photovoltaic and the historical power generation amount sequence of the centralized photovoltaic;
and selecting the concentrated photovoltaic with the largest correlation coefficient with the distributed light Fu Pier as a reference power station.
8. The distributed photovoltaic power prediction apparatus according to claim 7, wherein the anomaly repair unit includes:
the vacancy type judging module is used for searching vacancy data in the historical generating capacity data and judging the type of the vacancy data;
the spline interpolation method repair module is used for repairing by adopting an adjacent data spline interpolation method if the type of the vacant data is point missing;
and the linear regression method repair module is used for repairing by adopting a similar daily linear regression method if the type of the vacancy data is continuous missing.
9. The distributed photovoltaic power prediction apparatus according to claim 8, wherein the anomaly repair unit further comprises:
And the abnormal data repair module is used for repairing the out-of-range abnormal data and the abnormal fluctuation data in the historical power generation data by adopting an adjacent data spline interpolation method.
10. The distributed photovoltaic power prediction apparatus according to claim 7, wherein the photovoltaic power plant power prediction unit comprises:
the on-line capacity ratio acquisition module is used for acquiring an on-line capacity ratio according to the historical power generation amount of the distributed photovoltaic and the historical power generation amount of the reference power station;
the historical on-line capacity acquisition module is used for acquiring the historical on-line capacity of the distributed photovoltaic according to the historical on-line capacity of the reference power station and the on-line capacity ratio;
the relation establishing module is used for establishing a proportional relation between the power prediction sequence and the historical operating capacity;
and the power prediction sequence acquisition module is used for acquiring a power prediction sequence of the distributed photovoltaic according to the proportional relation between the power prediction sequence and the historical on-load capacity, the power prediction sequence of the reference power station and the on-load capacity ratio.
11. The distributed photovoltaic power prediction apparatus according to claim 7, wherein the error correction unit includes:
the analysis module is used for determining error sources of the power of the distributed photovoltaic according to the capacity calculation coefficient of the distributed photovoltaic, the unit on-operation capacity prediction error of the reference power station and the unit on-operation capacity power generation power difference value of the distributed photovoltaic and the reference power station, and the error sources comprise: performance errors, capacity errors, and external errors.
12. The distributed photovoltaic power prediction apparatus according to claim 11, wherein the error correction unit further comprises:
and the correction module is used for correcting the performance error and the capacity error.
13. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the spatial correlation-based distributed photovoltaic power prediction method of any of claims 1 to 6 when the program is executed by the processor.
14. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the spatial correlation based distributed photovoltaic power prediction method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010534498.5A CN111784030B (en) | 2020-06-12 | 2020-06-12 | Distributed photovoltaic power prediction method and device based on spatial correlation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010534498.5A CN111784030B (en) | 2020-06-12 | 2020-06-12 | Distributed photovoltaic power prediction method and device based on spatial correlation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111784030A CN111784030A (en) | 2020-10-16 |
| CN111784030B true CN111784030B (en) | 2023-10-24 |
Family
ID=72756463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010534498.5A Active CN111784030B (en) | 2020-06-12 | 2020-06-12 | Distributed photovoltaic power prediction method and device based on spatial correlation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111784030B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580862A (en) * | 2020-12-08 | 2021-03-30 | 国家电网有限公司 | Method and device for predicting short-term real-time power generation power of distributed photovoltaic system |
| CN113487100B (en) * | 2021-07-19 | 2023-08-15 | 国网浙江省电力有限公司电力科学研究院 | Global accurate prediction method and system for photovoltaic power generation output |
| CN114255136A (en) * | 2021-11-09 | 2022-03-29 | 许继集团有限公司 | Method and system for predicting ultrashort-term power generation power of distributed photovoltaic power station |
| CN116777305B (en) * | 2023-08-18 | 2023-11-10 | 河北思极科技有限公司 | Power data quality improving method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108960526A (en) * | 2018-07-24 | 2018-12-07 | 国网山东省电力公司电力科学研究院 | A kind of distributed photovoltaic based on region equivalent goes out force prediction method and system |
| CN109919353A (en) * | 2019-01-11 | 2019-06-21 | 杭州电子科技大学 | A kind of distributed photovoltaic prediction technique of the ARIMA model based on spatial coherence |
| CN109960885A (en) * | 2019-03-29 | 2019-07-02 | 国网天津市电力公司电力科学研究院 | A kind of distributed photovoltaic power generation power forecasting method |
| CN109978242A (en) * | 2019-03-12 | 2019-07-05 | 国网冀北电力有限公司 | The photovoltaic power generation cluster power forecasting method and device of scale are risen based on statistics |
| CN110008982A (en) * | 2019-01-11 | 2019-07-12 | 国网浙江省电力有限公司 | A kind of weather monitoring point selection method based on photovoltaic power generation power output cluster |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9825580B2 (en) * | 2014-09-26 | 2017-11-21 | State Grid Corporation Of China | Method for constructing real-time solar irradiation metering network of gigawatts level photovoltaic power generation base |
-
2020
- 2020-06-12 CN CN202010534498.5A patent/CN111784030B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108960526A (en) * | 2018-07-24 | 2018-12-07 | 国网山东省电力公司电力科学研究院 | A kind of distributed photovoltaic based on region equivalent goes out force prediction method and system |
| CN109919353A (en) * | 2019-01-11 | 2019-06-21 | 杭州电子科技大学 | A kind of distributed photovoltaic prediction technique of the ARIMA model based on spatial coherence |
| CN110008982A (en) * | 2019-01-11 | 2019-07-12 | 国网浙江省电力有限公司 | A kind of weather monitoring point selection method based on photovoltaic power generation power output cluster |
| CN109978242A (en) * | 2019-03-12 | 2019-07-05 | 国网冀北电力有限公司 | The photovoltaic power generation cluster power forecasting method and device of scale are risen based on statistics |
| CN109960885A (en) * | 2019-03-29 | 2019-07-02 | 国网天津市电力公司电力科学研究院 | A kind of distributed photovoltaic power generation power forecasting method |
Non-Patent Citations (3)
| Title |
|---|
| 基于空间相关性的分布式光伏出力预测;张家安;王琨玥;陈建;郭凌旭;黄潇潇;范瑞卿;李志军;;电力建设(第03期);全文 * |
| 基于空间相关性的分布式光伏超短期预测技术研究;张柏林;拜润卿;智勇;申振;张彦凯;常康;梁福波;;陕西电力(05);全文 * |
| 考虑空间相关性的分布式光伏发电出力预测及误差评价指标研究;严华江;章坚民;胡瑛俊;张力行;焦田利;闻安;;浙江电力(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111784030A (en) | 2020-10-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111784030B (en) | Distributed photovoltaic power prediction method and device based on spatial correlation | |
| Schram et al. | On the trade-off between environmental and economic objectives in community energy storage operational optimization | |
| Pascual et al. | Energy management strategy for a renewable-based residential microgrid with generation and demand forecasting | |
| Dallinger et al. | Integration of intermittent renewable power supply using grid-connected vehicles–A 2030 case study for California and Germany | |
| Pina et al. | Modeling hourly electricity dynamics for policy making in long-term scenarios | |
| Atwa et al. | Optimal renewable resources mix for distribution system energy loss minimization | |
| CN103296701B (en) | Active power control method in wind power plant | |
| CN109978242A (en) | The photovoltaic power generation cluster power forecasting method and device of scale are risen based on statistics | |
| CN112491043B (en) | New energy enrichment power grid power supply planning method and system | |
| CN102593839A (en) | Difference adjustment coefficient setting method of generator excitation system considering all operating manners of power grid | |
| Weinand et al. | Identification of potential off-grid municipalities with 100% renewable energy supply for future design of power grids | |
| Chung et al. | Economic evaluation of renewable energy systems for the optimal planning and design in Korea–a case study | |
| CN110909958A (en) | Short-term load prediction method considering photovoltaic grid-connected power | |
| Gao | Application of improved grey theory prediction model in medium-term load forecasting of distribution network | |
| KR20130074048A (en) | Soc correcting method for energy storage system and soc correcting system thereof | |
| CN107977898B (en) | Generated energy insurance pricing evaluation method of photovoltaic power station | |
| Lauby et al. | Balancing act | |
| CN115954951A (en) | Method and device for calculating reliable output level of new energy | |
| CN111178733B (en) | Abandoned wind power evaluation method based on equivalent electric quantity function method | |
| Yan et al. | Practical flexibility analysis on europe power system with high penetration of variable renewable energy | |
| Kyrylenko et al. | Power Systems Research and Operation: Selected Problems III | |
| Brinkman et al. | Grid modeling for the SunShot vision study | |
| Faranda et al. | SCADA system for optimization of energy exchange with the BESS in a residential case | |
| Yin et al. | Economic and technical comparison of energy storage technologies for renewable accommodation | |
| CN104657787A (en) | Wind power time series combined prediction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |