Abstract
The recent focus on deep learning accuracy ignored economic and environmental cost. Introduction of Green AI is hampered by lack of metrics that balance rewards for accuracy and cost and thus improve selection of best deep learning algorithms and platforms. Recognition and training efficiency universally compare deep learning based on energy consumption measurements for inference and deep learning, on recognition gradients, and on number of classes. Sustainability is assessed with deep learning lifecycle efficiency and life cycle recognition efficiency metrics that include the number of times models are used.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Reuther, A., Michaleas, P., Jones, M., Gadepally, V., Samsi, S., Kepner, J.: Survey and Benchmarking of machine learning accelerators. In: 2019 IEEE High Performance Extreme Computing Conference (HPEC). arXiv:1908.11348v1
Horowitz, M.: Computing’s Energy Problem (and What We Can Do About It). In: 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC). IEEE, 2014, pp. 10–14. http://ieeexplore.ieee.org/document/6757323/
Hennessy, J.L., Patterson, D.A.: A new golden age for computer architecture. Comm. ACM 62(2), 48-60 (2019)https://dl.acm.org/doi/10.1145/3282307
Schwartz, R., Dodge, J., Smith, N.A., Etzioni, O.: “Green AI” (2019). arXiv:1907.10597v3
Cai, E., Juan, D.C., Stamoulis, D., Marculescu, D.: NeuralPower: predict and deploy energy-efficient convolutional neural networks. In: Proceedings of Machine Learning Research 77, pp. 622–637. ACML (2017)
Thompson, N.C., Greenewald, K., Lee, K., Manso, G.F.: The Computational Limits of Deep Learning (2020). arXiv:2007.05558v1
Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., Zhang, J.: Edge intelligence: paving the last mile of artificial intelligence with edge computing (2019). arXiv:1905.10083v1
Zhang, X., Wang, Y., Lu, S., Liu, L., Xu, L., Shi, W.: OpenEI: an open framework for edge intelligence (2019). arXiv:1906.01864v1
Konecny, J., McMahan, H.B., Yu, F.X., Suresh, A.T., Bacon, D.: Federated learning: strategies for improving communication efficiency (2017). arXiv:1610.05492v2
McMahan, H.B., Moore, E., Ramage, D., Hampson, S., Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Proceedings of the 20th International Conference Artificial Intelligence and Statistics (AISTATS), Fort Lauderdale, FL (2017)
Deng, S., Zhao, H., Fang, W., Yin, J., Dustdar, S., Zomaya, A.Y.: Edge intelligence: the confluence of edge computing and artificial intelligence (2020). arXiv: 1909.00560v2
Das, A., Brunschwiler, T.: Privacy is whatwe care about: experimental investigation of federated learning on edge devices. In: Proceedings of First International Workshop on Challenges in Artificial Intelligence and Machine Learning for IoT, pp. 39–42 (2019)
Kasturi, A., Ellore, A.R., Hota, C.: Fusion learning: a one-shot federated learning, ICCS 2020. LNCS 12139, 424–436 (2020)
Xu, Z., Li, L., Zou, W.: Exploring federated learning on battery-powered devices, ACM TURC, May 17–19, Chengdu, China (2019)
Edge TPU: Coral DEV.https://coral.ai/docs/dev-board/datasheet/
NCS2.https://ark.intel.com/content/www/de/de/ark/products/140109/intel-neural-compute-stick-2.html
Jetson.www.nvidia.com/de-de/autonomous-machines/embedded-systems/jetson-nano/
Klingner, S., et al: Firefighter virtual reality simulation for personalized stress det., KI (2020)
Inoue, T., Vinayavekhin, P., Wang, S., Wood, D., Greco, N., Tachibana, R.: Domestic activities classification based on CNN using shuffling and mixing data augmentation, detection and classification of acoustic scenes and events (2018)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks (2019). https://arxiv.org/pdf/1801.04381.pdf
Joy-IT, Germany. https://joy-it.net/de/products/JT-UM25C)
(Rotkreuz, Switzerland. https://web.smart-me.com/en/project/smart-me-plug-2/
Hossin, M., Sulaiman, M.N.: A review on evaluation metrics for data classification evaluations. Int. J. Data Min. Knowl. Manage Process (IJDKP) 5,(2), 1–11 (2015)
Coroama, V.C., Hilty, L.M.: Assessing internet energy intensity: a review of methods and results. Environ. Impact Assess. Rev. 45, 63–68 (2014)
Pihkola, H., Hongisto, M., Apilo, O., Lasanen, M.: Evaluating the energy consumption of mobile data transfer–from technology development to consumer behaviour and life cycle thinking. Sustainability 10, 2494 (2018)
Hodak, M., Gorvenko, M., Dholakia, A.: Towards Power Efficiency in Deep Learning on Data Center Hardware. In: IEEE Big Data 2019 Conference (2019)
You, Y., Zhang, Z., Hsieh, C.-J., Demmel, J., Kreutzer, K.: ImageNet training in minutes (2018). https://arxiv.org/abs/1709.05011
Nilsson, A., Smith, S., Ulm, G., Gustavsson, E., Jirstrand, M.: A performance evaluation of federated learning algorithms. DIDL 2018, Dec. 10–11, Rennes, France (2018)
Sze, V., Hsin, Y., Yang, T.J., Emer, J.S.: Efficient processing of deep neural networks: a tutorial and survey. Proc. IEEE 105(12), 2295–2329 (2017)
Shankar, Structuring your machine learning projects (2020). https://medium.com/structuring-your-machine-learning-projects/satisficing-and-optimizing-metric-24372e0a73c
Cai, H., Gan, C., Wang, T., Zhang, Z., Han, S.: Once-for-all: train one network and specialize it for efficient deployment. ICLR (2020). https://arxiv.org/abs/1908.09791
Brevini, B.: Black boxes, not green: mythologizing artificial intelligence and omitting the environment. July–December: 1–5 Big Data Society, 7, 2053951720935141 (2020)
https://www.growthink.com/content/two-most-important-quotes-business
Ignatov, A., et al.: AI benchmark: running deep neural networks on android smartphones. In: Leal-Taixé, L., Roth, S. (eds.) Computer Vision – ECCV 2018 Workshops. ECCV 2018. Lecture Notes in Computer Science, vol. 11133, pp. 288–314. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11021-5_19
Mastroianni, C., et al.: Special issue on edge intelligence for sustainable smart environments. IEEE Trans. Green Commun. Netw. 6(1), 234–237 (2022)
Savaglio, C., Gerace, P., Di Fatta, G., Fortino, G.: Data mining at the IoT edge. In: 2019 28th International Conference on Computer Communication and Networks (ICCCN). IEEE, pp. 1-6 (2019)
Lenherr, N., Pawlitzek, R., Michel, B.: New universal sustainability metrics to assess edge intelligence. Sustain. Comput.: Inf. Syst. 31, 100580 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lenherr, N., Pawlitzek, R., Michel, B. (2022). Assessing Efficiency Benefits of Edge Intelligence. In: González-Vidal, A., Mohamed Abdelgawad, A., Sabir, E., Ziegler, S., Ladid, L. (eds) Internet of Things. GIoTS 2022. Lecture Notes in Computer Science, vol 13533. Springer, Cham. https://doi.org/10.1007/978-3-031-20936-9_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-20936-9_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20935-2
Online ISBN: 978-3-031-20936-9
eBook Packages: Computer ScienceComputer Science (R0)