Federated Learning with Hyperparameter-based Clustering for Electrical Load Forecasting

Electrical load prediction has become an integral part of power system operation. Deep learning models have found popularity for this purpose. However, to achieve a desired prediction accuracy, they require huge amounts of data for training. Sharing electricity consumption data of individual households for load prediction may compromise user privacy and can be expensive in terms of communication resources. Therefore, edge computing methods, such as federated learning, are gaining more importance for this purpose. These methods can take advantage of the data without centrally storing it. This paper evaluates the performance of federated learning for short-term forecasting of individual house loads as well as the aggregate load. It discusses the advantages and disadvantages of this method by comparing it to centralized and local learning schemes. Moreover, a new client clustering method is proposed to reduce the convergence time of federated learning. The results show that federated learning has a good performance with a minimum root mean squared error (RMSE) of 0.117kWh for individual load forecasting.

[1]  Shahzad Muzaffar,et al.  Short-Term Load Forecasts Using LSTM Networks , 2019, Energy Procedia.

[2]  Rob J. Hyndman,et al.  Forecasting Uncertainty in Electricity Smart Meter Data by Boosting Additive Quantile Regression , 2016, IEEE Transactions on Smart Grid.

[3]  Mohamed Atri,et al.  A survey on machine learning in Internet of Things: Algorithms, strategies, and applications , 2020, Internet Things.

[4]  James Yu,et al.  Prediction of office building electricity demand using artificial neural network by splitting the time horizon for different occupancy rates , 2021 .

[5]  Petr Musilek,et al.  Quantile Regression and Clustering Models of Prediction Intervals for Weather Forecasts: A Comparative Study , 2019, Forecasting.

[6]  Petr Musilek,et al.  Distributed Learning Applications in Power Systems: A Review of Methods, Gaps, and Challenges , 2021, Energies.

[7]  Yusuf Yaslan,et al.  Empirical mode decomposition based denoising method with support vector regression for time series prediction: A case study for electricity load forecasting , 2017 .

[8]  Sung Wook Baik,et al.  A Novel CNN-GRU-Based Hybrid Approach for Short-Term Residential Load Forecasting , 2020, IEEE Access.

[9]  Andreas Svensson,et al.  Probabilistic forecasting of electricity consumption, photovoltaic power generation and net demand of an individual building using Gaussian Processes , 2018 .

[10]  Jinsong Wu,et al.  Blockchain-Based Federated Learning for Intelligent Control in Heavy Haul Railway , 2020, IEEE Access.

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

[12]  Choong Seon Hong,et al.  Federated Learning based Energy Demand Prediction with Clustered Aggregation , 2021, 2021 IEEE International Conference on Big Data and Smart Computing (BigComp).

[13]  Woohyun Kim,et al.  Electricity load forecasting using advanced feature selection and optimal deep learning model for the variable refrigerant flow systems , 2020 .

[14]  Robert Fildes,et al.  Measuring Forecasting Accuracy: Problems and Recommendations (by the Example of SKU-Level Judgmental Adjustments) , 2014 .

[15]  Lukumon O. Oyedele,et al.  Genetic algorithm-determined deep feedforward neural network architecture for predicting electricity consumption in real buildings , 2020, Energy and AI.

[16]  Joakim Widén,et al.  Very short term load forecasting of residential electricity consumption using the Markov-chain mixture distribution (MCM) model , 2021 .

[17]  Sahm Kim,et al.  Short term electricity load forecasting for institutional buildings , 2019, Energy Reports.

[18]  Petr Musilek,et al.  Forecasting Photovoltaic Power Production using a Deep Learning Sequence to Sequence Model with Attention , 2020, 2020 International Joint Conference on Neural Networks (IJCNN).

[19]  Jordi Vilaplana,et al.  EMPOWERING, a Smart Big Data Framework for Sustainable Electricity Suppliers , 2018, IEEE Access.

[20]  Danna Zhou,et al.  d. , 1840, Microbial pathogenesis.

[21]  K. H. Toft,et al.  Transformations of trust in society: A systematic review of how access to big data in energy systems challenges Scandinavian culture , 2021 .

[22]  Elliott Skomski,et al.  Sequence-to-sequence neural networks for short-term electrical load forecasting in commercial office buildings , 2020 .

[23]  Yulin Ma,et al.  An Improved LSTM Model for Behavior Recognition of Intelligent Vehicles , 2020, IEEE Access.

[24]  P. Alam,et al.  H , 1887, High Explosives, Propellants, Pyrotechnics.

[25]  Xifeng Guo,et al.  A short-term load forecasting model of multi-scale CNN-LSTM hybrid neural network considering the real-time electricity price , 2020 .

[26]  Xinwei Shen,et al.  A Federated Learning Framework for Smart Grids: Securing Power Traces in Collaborative Learning , 2021, ArXiv.

[27]  Miss A.O. Penney.  (b) , 1974, The New Yale Book of Quotations.

[28]  Xing Wu,et al.  FedMed: A Federated Learning Framework for Language Modeling , 2020, Sensors.

[29]  Antonello Monti,et al.  A cloud-based smart metering infrastructure for distribution grid services and automation , 2017, Sustainable Energy, Grids and Networks.

[30]  Roberto Riggio,et al.  Centralized and Federated Learning for Predictive VNF Autoscaling in Multi-Domain 5G Networks and Beyond , 2021, IEEE Transactions on Network and Service Management.

[31]  Wei Shi,et al.  Federated learning of predictive models from federated Electronic Health Records , 2018, Int. J. Medical Informatics.

[32]  Li Li,et al.  A review of applications in federated learning , 2020, Comput. Ind. Eng..

[33]  Marco Savi,et al.  Short-Term Energy Consumption Forecasting at the Edge: A Federated Learning Approach , 2021, IEEE Access.

[34]  Soumaya Cherkaoui,et al.  Electrical Load Forecasting Using Edge Computing and Federated Learning , 2020, ICC 2020 - 2020 IEEE International Conference on Communications (ICC).

[35]  Hongkai Xiong,et al.  FedMax: Enabling a Highly-Efficient Federated Learning Framework , 2020, 2020 IEEE 13th International Conference on Cloud Computing (CLOUD).

[36]  Farshid Keynia,et al.  Short-term electricity load and price forecasting by a new optimal LSTM-NN based prediction algorithm , 2021, Electric Power Systems Research.