Search Results (1,165)

This research presents an intelligent, environment-aware navigation framework for smart electric vehicles (EVs), focusing on multi-agent mapping, real-time obstacle recognition, and adaptive route optimization. Unlike traditional navigation systems that primarily minimize cost and distance, this research emphasizes how EVs perceive, map, and interact with their surroundings. Using a distributed mapping approach, multiple EVs collaboratively construct a topological representation of their environment, enhancing spatial awareness and adaptive path planning. Neural Radiance Fields (NeRFs) and machine learning models are employed to improve situational awareness, reduce positional tracking errors, and increase mapping accuracy by integrating real-time traffic conditions, battery levels, and environmental constraints. The system intelligently balances delivery speed and energy efficiency by dynamically adjusting routes based on urgency, congestion, and battery constraints. When rapid deliveries are required, the algorithm prioritizes faster routes, whereas, for flexible schedules, it optimizes energy conservation. This dynamic decision making ensures optimal fleet performance by minimizing energy waste and reducing emissions. The framework further enhances sustainability by integrating an adaptive optimization model that continuously refines EV paths in response to real-time changes in traffic flow and charging station availability. By seamlessly combining real-time route adaptation with energy-efficient decision making, the proposed system supports scalable and sustainable EV fleet operations. The ability to dynamically optimize travel paths ensures minimal energy consumption while maintaining high operational efficiency. Experimental validation confirms that this approach not only improves EV navigation and obstacle avoidance but also significantly contributes to reducing emissions and enhancing the long-term viability of smart EV fleets in rapidly changing environments. Full article

In this paper, we present a multi-sensor platform for predictive maintenance featuring hybrid long-range (LoRa) and 5G connectivity. This hybrid approach combines LoRa’s low-power transmission for energy efficiency with 5G’s real-time data capabilities. The hardware platform integrates multiple sensors to monitor machine health parameters, with data analyzed on the device using pre-trained AI models to assess the machine’s condition. Inferences are transmitted via LoRa to the operator for maintenance scheduling, while a cloud application tracks and stores sensor data. Periodic sensor data bursts are sent via 5G to update the AI model, which is then delivered back to the platform through over-the-air (OTA) updates. We provide a comprehensive overview of the hardware architecture, along with an in-depth analysis of the data generated by the sensors, and its processing methodology. However, the data analysis and the software for ventilation control and its predictive capabilities are not the focus of this paper and are not presented. Full article

This comprehensive survey explores recent advancements in scheduling techniques for efficient deep learning computations on GPUs. The article highlights challenges related to parallel thread execution, resource utilization, and memory latency in GPUs, which can lead to suboptimal performance. The surveyed research focuses on novel scheduling policies to improve memory latency tolerance, exploit parallelism, and enhance GPU resource utilization. Additionally, it explores the integration of prefetching mechanisms, fine-grained warp scheduling, and warp switching strategies to optimize deep learning computations. These techniques demonstrate significant improvements in throughput, memory bank parallelism, and latency reduction. The insights gained from this survey can guide researchers, system designers, and practitioners in developing more efficient and powerful deep learning systems on GPUs. Furthermore, potential future research directions include advanced scheduling techniques, energy efficiency considerations, and the integration of emerging computing technologies. Through continuous advancement in scheduling techniques, the full potential of GPUs can be unlocked for a wide range of applications and domains, including GPU-accelerated deep learning, task scheduling, resource management, memory optimization, and more. Full article

Recently, frequent typhoons and waterlogging disasters have caused severe damage to the power distribution networks in coastal cities. In response to this issue, how to efficiently develop recovery plans and achieve flexible resource coordination has become key for urban power grids in regard to coping with extreme natural disasters. Therefore, this article proposes a multi type flexible resource collaborative scheduling method for power supply restoration in distribution networks which realizes cooperation between maintenance teams and mobile energy storage in the scenario of wind and flood composite disasters, simultaneously completing the transfer of important loads through topology reconstruction. Firstly, a damage model for distribution network nodes and lines under wind–flood composite disasters was established to address the impact of typhoons and waterlogging disasters on the distribution network. Then, based on the inherent characteristics of multiple types of flexible resources, various collaborative recovery models for flexible resources after disasters were established. Finally, the effectiveness of the proposed method was verified through the coupling example of a 33-node distribution network and a 30-node transportation network. Full article

With the rapid global proliferation of electric vehicles (EVs), their integration as a significant load component within power systems increasingly influences the stable operation and planning of electrical grids. However, the high uncertainty and randomness inherent in EV users’ charging behaviors render accurate load forecasting a challenging task. In this context, the present study proposes a Particle Swarm Optimization (PSO)-enhanced Long Short-Term Memory (LSTM) network forecasting model. By combining the global search capability of the PSO algorithm with the advantages of LSTM networks in time-series modeling, a PSO-LSTM hybrid framework optimized for seasonal variations is developed. The results confirm that the PSO-LSTM model effectively captures seasonal load variations, providing a high-precision, adaptive solution for dynamic grid scheduling and charging infrastructure planning. This model supports the optimization of power resource allocation and the enhancement of energy storage efficiency. Specifically, during winter, the Mean Absolute Error (MAE) is 3.896, a reduction of 6.57% compared to the LSTM model and 10.13% compared to the Gated Recurrent Unit (GRU) model. During the winter–spring transition, the MAE is 3.806, which is 6.03% lower than that of the LSTM model and 12.81% lower than that of the GRU model. In the spring, the MAE is 3.910, showing a 2.71% improvement over the LSTM model and a 7.32% reduction compared to the GRU model. Full article

In view of the future of the Internet of Things (IoT), the number of edge devices and the amount of sensing data and communication data are expected to increase exponentially. With the emergence of new computing-intensive tasks and delay-sensitive application scenarios, terminal devices need to offload new business computing tasks to the cloud for processing. This paper proposes a joint transmission and offloading task scheduling strategy for the edge computing-enabled low Earth orbit satellite networks, aiming to minimize system costs. The proposed system model incorporates both data service transmission and computational task scheduling, which is framed as a long-term cost function minimization problem with constraints. The simulation results demonstrate that the proposed strategy can significantly reduce the average system cost, queue length, energy consumption, and task completion rate, compared to baseline strategies, thus highlighting the strategy’s effectiveness and efficiency. Full article

The microgrid is a small-scale, independent power system that plays a crucial role in the transition to carbon-neutral energy systems. Combined heat and power (CHP) systems with energy storage reduce energy waste within microgrids, enhancing energy utilization efficiency. The key challenge for a microgrid integrated with a combined heat and power system is determining the optimal configuration and operation duration under different scenarios to meet users’ electricity and heat demands while minimizing both economic and environmental costs. Thus, this paper presents a bi-objective mathematical model to solve the optimal scheduling problem of the microgrid. The Long Short-Term Memory–Parallel Multi-Objective Energy Valley Optimizer (LSTM-PMOEVO) framework incorporates energy load prediction using LSTM and scheduling planning solved via PMOEVO. These strategies address the challenges posed by unpredictable energy load fluctuations and the complexity of solving such systems. Finally, a public dataset was utilized for the experiments to verify the performance of the proposed algorithm. Comparisons and discussions show that the proposed optimization strategies significantly improve the performance of PMOEVO, demonstrating marked advantages over six classical algorithms. In conclusion, the PMOEVO developed in this paper performs excellently in solving the Scheduling Problem of Biomass-Hybrid microgrids with energy storage considering uncertainty. The work presented in this paper provides a new solution framework for the microgrid-scheduling problem considering uncertainty. In future research, this solution framework will be further advanced for application in real-world scenarios. Full article

Due to increasing energy consumption, green scheduling in the manufacturing industry has attracted great attention. In distributed manufacturing involving heterogeneous plants, accounting for complex work sequences and energy consumption poses a major challenge. To address distributed heterogeneous green hybrid flowshop scheduling (DHGHFSP) while optimising total weighted delay (TWD) and total energy consumption (TEC), a deep reinforcement learning-based evolutionary algorithm (DRLBEA) is proposed in this article. In the DRLBEA, a problem-based hybrid heuristic initialization with random-sized population is designed to generate a desirable initial solution. A bi-population evolutionary algorithm with global search and local search is used to obtain the elite archive. Moreover, a distributional Deep Q-Network (DQN) is trained to select the best local search strategy. Experimental results on 20 instances show a 9.8% increase in HV mean value and a 35.6% increase in IGD mean value over the state-of-the-art method. The results show the effectiveness and efficiency of the DRLBEA in solving DHGHFSP. Full article

Optimization is a key management science methodology utilizing mathematical techniques to determine optimal solutions to a variety of management challenges. The biofuel production process, comparable to existing supply chain operations, consists of complex interconnected activities among three principal components: farms, distribution networks, and refineries. To effectively manage the complex and large-scale biofuel supply chain network, it is essential to employ optimization methodologies such as linear programming and nonlinear programming. However, existing optimization methods are predominantly systematized for generalized issues such as manufacturing production scheduling and supply chain operations management, thus a systematic guideline indicating which techniques should be employed for specific problems in biofuel production and supply relative to the production and management of new and renewable energy sources is absent. Given the crucial need for a continuous increase in biofuel production and efficient management, optimization methods should be implemented. Accordingly, this study compiles optimization techniques suitable for biofuel supply chain operations through a thorough literature review. Particularly, this study examines methods ranging from conventional linear and nonlinear programming to recently utilized simulation-based optimization techniques, spurred by advancements in computing performance. Consequently, researchers and engineers will be equipped to select and implement suitable optimization methods for various challenges in the biofuel production process. Full article

To address the issues of energy wastage and uncertainty impacts associated with high levels of renewable energy integration, a multi-objective distributed robust low-carbon optimization scheduling strategy for hydrogen-integrated Integrated Energy Systems (IES) is proposed. This strategy incorporates a green hydrogen trading mechanism and low-carbon demand response. Firstly, to leverage the low-carbon and clean characteristics of hydrogen energy, an efficient hydrogen utilization model was constructed, consisting of electricity-based hydrogen production, waste heat recovery, multi-stage hydrogen use, hydrogen blending in gas, and hydrogen storage. This significantly enhanced the system’s renewable energy consumption and carbon reduction. Secondly, to improve the consumption of green hydrogen, a novel reward–punishment green hydrogen certificate trading mechanism was proposed. The impact of green hydrogen trading prices on system operation was discussed, promoting the synergistic operation of green hydrogen and green electricity. Based on the traditional demand-response model, a novel low-carbon demand-response strategy is proposed, with carbon emission factors serving as guiding signals. Finally, considering the uncertainty of renewable energy, an innovative optimal trade-off multi-objective distributed robust model was proposed, which simultaneously considered low-carbon, economic, and robustness aspects. The model was solved using an improved adaptive particle swarm optimization algorithm. Case study results show that, after introducing the reward–punishment green hydrogen trading mechanism and low-carbon demand response, the system’s total cost was reduced by approximately 5.16% and 4.37%, and carbon emissions were reduced by approximately 7.84% and 6.72%, respectively. Moreover, the proposed multi-objective distributed robust model not only considers the system’s economy, low-carbon, and robustness but also offers higher solving efficiency and optimization performance compared to multi-objective optimization methods. Full article

In this paper, a dynamic energy-efficient hybrid flow shop (TDEHFSP) scheduling model is proposed, considering random arrivals of new jobs and transport by transfer vehicles. To simultaneously optimise the maximum completion time and the total energy consumption, a co-evolutionary approach (DDQCE) using a double deep Q-network (DDQN) is introduced, where global and local search tasks are assigned to different populations to optimise the use of computational resources. In addition, a multi-objective NEW heuristic strategy is implemented to generate an initial population with enhanced convergence and diversity. The DDQCE incorporates an energy-efficient strategy based on time interval ‘left shift’ and turn-on/off mechanisms, alongside a rescheduling model to manage dynamic disturbances. In addition, 36 test instances of varying sizes, simplified from the excavator boom manufacturing process, are designed for comparative experiments with traditional algorithms. The experimental results demonstrate that DDQCE achieves 40% more Pareto-optimal solutions compared to NSGA-II and MOEA/D while requiring 10% less computational time, confirming that this algorithm efficiently solves the TDEHFSP problem. Full article

The Haidian District was, historically, rich in water resources. However, with urban development, the groundwater levels have declined, and most rivers have lost their ecological baseflows. To restore the aquatic ecosystems, the district has implemented a cyclic water network and advanced water replenishment projects. Nonetheless, the existing replenishment strategies face challenges, such as an insufficient scientific basis, lack of data, and high energy consumption. There is an urgent need to develop a scientifically robust ecological water replenishment system and optimize pump station scheduling to enhance water resource management efficiency. This study addresses the ecological water replenishment needs of seasonal rivers by integrating the Literature method, Rainfall-Runoff method, and R2cross method to develop a comprehensive approach for calculating the ecological flow and water depth. The proposed method simultaneously meets the ecological functionality and landscape requirements of seasonal rivers. Additionally, the SWMM model is employed to design intelligent pump station scheduling rules, optimizing the replenishment efficiency and energy consumption. Through field measurements and data collection, the ecological water demands of the river channels in different areas are assessed. Using a hydrodynamic model, the dynamic variations in the ecological flow and water depth are simulated. For the Cuihu, Daoxianghu, and Yongfeng areas, this study reveals that the current replenishment volume is insufficient to meet the landscape and ecological needs of the rivers. Most rivers require a 20–30% increase in water levels, with the Dazhai qu needing a substantial rise from 0.17 m to 0.3 m, representing an increase of 76%. Additionally, the results demonstrate that intelligent pump station scheduling can significantly reduce operating costs and energy consumption by dynamically adjusting the replenishment timing and flow rates. This approach optimizes the intervals between equipment activation and deactivation, thereby balancing ecological and energy-saving goals. This research not only provides technical support for the precise calculation of ecological replenishment volumes and the intelligent management of pump stations, but also offers scientific references for water resource management in similar regions. The findings will enhance the ecological functions and landscape quality of the rivers in the Haidian District while promoting refined and intelligent regional water resource management. Moreover, this study presents innovative solutions and theoretical foundations for water resource regulation under the backdrop of climate change. Full article

To improve the operational efficiency of the Virtual Power Plant (VPP) and the effectiveness and reliability of scheduling boundary characterization, this paper proposes a time-decoupled distributed optimization algorithm. First, based on the Lyapunov optimization theory, time decoupling is implemented within the VPP, transforming long-term optimization problems into single-period optimization problems, thereby reducing optimization complexity and improving operational efficiency. Second, the Alternating Direction Method of Multipliers (ADMM) framework is used to decompose the optimization problem into multiple subproblems, combined with a hybrid strategy to improve the particle swarm optimization algorithm for solving the problem, thus achieving distributed optimization for the VPP. Finally, to facilitate intra-day interaction between the VPP and the distribution network, the remaining controllable capacity of the VPP’s devices is used as the spinning reserve to address renewable energy fluctuations. A dynamic scheduling boundary model is constructed by introducing wind and solar fluctuation factors. Based on time decoupling and algorithm improvement, the scheduling boundaries are solved and updated on a rolling basis. Simulation results show that, firstly, the time decoupling strategy based on Lyapunov optimization has an error of less than 3%, and the solving time is reduced by 86.11% after decoupling, significantly improving solving efficiency and validating the feasibility and effectiveness of the time decoupling strategy. Secondly, the hybrid strategy-improved particle swarm optimization algorithm achieves improvements in convergence speed and accuracy compared to other algorithms. Finally, the VPP scheduling boundary and scheduling cost characterization times are 115 s and 6.7 s, respectively, effectively meeting the timeliness of VPP and distribution network interaction while ensuring the safety and reliability of the scheduling boundaries. Full article

Dynamic workflow scheduling in cloud environments is a challenging task due to task dependencies, fluctuating workloads, resource variability, and the need to balance makespan and energy consumption. This study presents a novel scheduling framework that integrates Graph Neural Networks (GNNs) with Deep Reinforcement Learning (DRL) using the Proximal Policy Optimization (PPO) algorithm to achieve multi-objective optimization, focusing on minimizing makespan and reducing energy consumption. By leveraging GNNs to model task dependencies within workflows, the framework enables adaptive and informed resource allocation. The agent was evaluated within a CloudSim-based simulation environment using synthetic datasets. Experimental results across benchmark datasets demonstrate the proposed framework’s effectiveness, achieving consistent improvements in makespan and energy consumption over traditional heuristic methods. The framework achieved a minimum makespan of 689.22 s against the second best of 800.72 s in moderate-sized datasets, reducing makespan significantly with improvements up to 13.92% over baseline methods such as HEFT, Min–Min, and Max–Min, while maintaining competitive energy consumption of 10,964.45 J. These findings highlight the potential of combining GNNs and DRL for dynamic task scheduling in cloud environments, effectively balancing multiple objectives. Full article

6TiSCH networks adopt the IEEE 802.15.4e-based TSCH protocol to support efficient and reliable communication in low-power and lossy network (LLN) environments. However, under bursty traffic conditions, the traditional minimal scheduling function (MSF)-based scheduling technique cannot effectively handle the traffic load and suffers from packet queue overflow. In this study, we propose two main techniques to solve these problems. The first technique, dynamic cell cycle adjustment, dynamically adjusts the cell addition and deletion cycles based on the link quality and packet queue utilization to prevent packet queue overflow and efficiently use limited cell resources. The second technique, the parent node 6P transaction forwarding technique, is designed to pre-forward cell addition requests to higher nodes along the path when the cell utilization exceeds a set threshold due to traffic spikes at the lower nodes, so that the higher nodes can perform 6P negotiation immediately without waiting for MAX_NUMCELLS cycles. This minimizes the cell addition delay and prevents packet queue overflow. The simulation results show that the proposed technique has a high packet delivery ratio (PDR), low latency, and energy efficiency compared to conventional MSF, IMSF, and LMSF in various traffic environments. In particular, it maintains stable performance while preventing packet overflow under bursty traffic conditions. This work contributes to the optimization of scheduling and cell negotiation in 6TiSCH networks to improve the network efficiency and reliability in IoT environments. Full article