Electrical Load Forecasting Using Edge Computing and Federated Learning

In the smart grid, huge amounts of consumption data are used to train deep learning models for applications such as load monitoring and demand response. However, these applications raise concerns regarding security and have high accuracy requirements. In one hand, the data used is privacy-sensitive. For instance, the fine-grained data collected by a smart meter at a consumer’s home may reveal information on the appliances and thus the consumer’s behaviour at home. On the other hand, the deep learning models require big data volumes with enough variety and to be trained adequately. In this paper, we evaluate the use of Edge computing and federated learning, a decentralized machine learning scheme that allows to increase the volume and diversity of data used to train the deep learning models without compromising privacy. This paper reports, to the best of our knowledge, the first use of federated learning for household load forecasting and achieves promising results. The simulations were done using Tensorflow Federated on the data from 200 houses from Texas, USA.

[1]  Blaise Agüera y Arcas,et al.  Communication-Efficient Learning of Deep Networks from Decentralized Data , 2016, AISTATS.

[2]  Matthew Rowe,et al.  The Real-Time Optimisation of DNO Owned Storage Devices on the LV Network for Peak Reduction , 2014 .

[3]  Xiaohua Li,et al.  Electric load forecasting in smart grids using Long-Short-Term-Memory based Recurrent Neural Network , 2017, 2017 51st Annual Conference on Information Sciences and Systems (CISS).

[4]  Norman Chung-Fai Tse,et al.  Short-term load forecasting coupled with weather profile generation methodology , 2018 .

[5]  Sherali Zeadally,et al.  Design and Performance Analysis of a Virtual Ring Architecture for Smart Grid Privacy , 2014, IEEE Transactions on Information Forensics and Security.

[6]  Tassilo Klein,et al.  Differentially Private Federated Learning: A Client Level Perspective , 2017, ArXiv.

[7]  Zhiguo Ding,et al.  A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art , 2019, IEEE Access.

[8]  Madeleine Gibescu,et al.  Deep learning for estimating building energy consumption , 2016 .

[9]  Ali Ouni,et al.  Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches † , 2018, Energies.

[10]  Yuguang Fang,et al.  A Privacy-Preserving Scheme for Incentive-Based Demand Response in the Smart Grid , 2016, IEEE Transactions on Smart Grid.

[11]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[12]  Yuan Zhang,et al.  Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network , 2019, IEEE Transactions on Smart Grid.

[13]  Ran Li,et al.  Deep Learning for Household Load Forecasting—A Novel Pooling Deep RNN , 2018, IEEE Transactions on Smart Grid.

[14]  Jun Jason Zhang,et al.  Evolutionary Deep Learning-Based Energy Consumption Prediction for Buildings , 2019, IEEE Access.

[15]  Bruce Stephen,et al.  Incorporating Practice Theory in Sub-Profile Models for Short Term Aggregated Residential Load Forecasting , 2017, IEEE Transactions on Smart Grid.

[16]  Hyun Kim,et al.  Untraceability of Group Signature Schemes based on Bilinear Mapping and Their Improvement , 2007, Fourth International Conference on Information Technology (ITNG'07).

[17]  David J. Hill,et al.  Short-Term Residential Load Forecasting Based on Resident Behaviour Learning , 2018, IEEE Transactions on Power Systems.

[18]  Jin Song Dong,et al.  Smart Grid Metering Networks: A Survey on Security, Privacy and Open Research Issues , 2019, IEEE Communications Surveys & Tutorials.

[19]  Michele Lanza,et al.  Advances in Artificial Neural Networks , 2020 .

[20]  Khe Chai Sim,et al.  An Investigation Into On-device Personalization of End-to-end Automatic Speech Recognition Models , 2019, INTERSPEECH.

[21]  Sarvar Patel,et al.  Practical Secure Aggregation for Federated Learning on User-Held Data , 2016, ArXiv.

[22]  Daniel L. Marino,et al.  Building energy load forecasting using Deep Neural Networks , 2016, IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society.