Federated Learning for Short-Term Residential Load Forecasting

Load forecasting is an essential task performed within the energy industry to help balance supply with demand and maintain a stable load on the electricity grid. As supply transitions towards less reliable renewable energy generation, smart meters will prove a vital component to facilitate these forecasting tasks. However, smart meter adoption is low among privacy-conscious consumers that fear intrusion upon their fine-grained consumption data. In this work we propose and explore a federated learning (FL) based approach for training forecasting models in a distributed, collaborative manner whilst retaining the privacy of the underlying data. We compare two approaches: FL, and a clustered variant, FL+HC against a non-private, centralised learning approach and a fully private, localised learning approach. Within these approaches, we measure model performance using RMSE and computational efficiency. In addition, we suggest the FL strategies are followed by a personalisation step and show that model performance can be improved by doing so. We show that FL+HC followed by personalisation can achieve a ~5% improvement in model performance with a ~10x reduction in computation compared to localised learning. Finally we provide advice on private aggregation of predictions for building a private end-to-end load forecasting application.

• Publication year

  2021

• Venue

  IEEE Open Access Journal of Power and Energy

• Publication date

  2021-05-27

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.1109/OAJPE.2022.3206220arXiv 2105.13325
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Artificial Intelligence for Load Forecasting: History, Illusions, and Opportunities

  2022cited by this paper
• Electricity Consumer Characteristics Identification: A Federated Learning Approach

  2021cited by this paper
• Federated learning with hierarchical clustering of local updates to improve training on non-IID data

  2020cited by this paper
• Electrical Load Forecasting Using Edge Computing and Federated Learning

  2020cited by this paper
• Towards Federated Learning for HVAC Analytics: A Measurement Study

  2020cited by this paper
• Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network

  2019cited by this paper
• Robust and Communication-Efficient Federated Learning From Non-i.i.d. Data

  2019cited by this paper
• Modeling and forecasting building energy consumption: A review of data-driven techniques

  2019cited by this paper
• Conventional models and artificial intelligence-based models for energy consumption forecasting: A review

  2019cited by this paper
• Energy Demand Prediction with Federated Learning for Electric Vehicle Networks

  2019cited by this paper
• PyTorch: An Imperative Style, High-Performance Deep Learning Library

  2019cited by this paper
• The Non-IID Data Quagmire of Decentralized Machine Learning

  2019cited by this paper
• Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches †

  2018cited by this paper
• Federated Optimization in Heterogeneous Networks

  2018cited by this paper
• Deep Learning for Household Load Forecasting—A Novel Pooling Deep RNN

  2018cited by this paper
• Deep neural networks for energy load forecasting

  2017cited by this paper
• Federated Multi-Task Learning

  2017cited by this paper
• Communication-Efficient Learning of Deep Networks from Decentralized Data

  2016cited by this paper
• Deep Learning

  2016cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• A comparison of consumer perceptions towards smart homes in the UK, Germany and Italy: reflections for policy and future research

  2014cited by this paper
• Smart meter data: Balancing consumer privacy concerns with legitimate applications

  2012cited by this paper
• Large Scale Distributed Deep Networks

  2012cited by this paper
• Short term load forecasting using fuzzy adaptive inference and similarity

  2009cited by this paper
• Load Forecasting Using Support Vector Machines: A Study on EUNITE Competition 2001

  2004cited by this paper
• Long Short-Term Memory

  1997influential reference
• Learning long-term dependencies with gradient descent is difficult

  1994cited by this paper

• From hardness assumptions to energy-secure protocols: A systematic survey of Euclidean lattice-based cryptography

  2026cites this paper
• Leveraging cutting-edge technologies into energy management smart buildings: An era of revolution

  2026cites this paper
• A hyperparameter-space clustering methodology of residential electricity loads

  2025cites this paper
• Federated Online Learning for adaptive load forecasting across decentralized nodes

  2025cites this paper
• FedPLF: A Federated Framework for Personalized Electricity Load Forecasting

  2025cites this paper
• FedCCL: Federated Clustered Continual Learning Framework for Privacy-Focused Energy Forecasting

  2025cites this paper
• Personalized Federated Learning With Cost-Oriented Load Forecasting for Home Energy Management Systems

  2025cites this paper
• A comparative analysis of federated learning strategies for short-term photovoltaic power forecasting

  2025cites this paper
• Federated Short-Term Household Load Forecasting with FedProx and Differential Privacy

  2025cites this paper
• CFL-ICCV: Clustered federated learning framework with an intra-cluster cross-validation mechanism for DER forecasting

  2025cites this paper
• The Architecture of a Virtual Intelligent Energy System for Sustainable Traction Grids

  2025influential citation
• Day-Ahead Forecasting with Federated LSTM to Plan Energy Sharing in a Community Microgrid

  2025cites this paper
• Federated Learning for Smart Cities: A Thematic Review of Challenges and Approaches

  2025cites this paper
• A survey on Clustered Federated Learning: Taxonomy, Analysis and Applications

  2025cites this paper
• A Cross-Regional Load Forecasting Method Based on a Pseudo-Distributed Federated Learning Strategy

  2025cites this paper
• Deep learning for time series forecasting: a survey

  2025cites this paper
• Similarity-driven truncated aggregation framework for privacy-preserving short term load forecasting

  2025cites this paper
• Electrical Load Forecasting Over Multihop Smart Metering Networks With Federated Learning

  2025cites this paper
• FedForecaster: An Automated Federated Learning Approach for Time-series Forecasting

  2025cites this paper
• A federated LSTM network for load forecasting using multi-source data with homomorphic encryption

  2025cites this paper
• A Hybrid Mud Ring Algorithm and Continual Spatio-Temporal Graph Convolutional Networks for Short-Term Residential Load Forecasting in Smart Grids

  2025cites this paper
• Heuristic based federated learning with adaptive hyperparameter tuning for households energy prediction

  2025cites this paper
• Enhancing Power Grid Efficiency with Machine Learning for Climate Change Mitigation

  2025cites this paper
• Federated Learning for Decentralized Electricity Market Optimization: A Review and Research Agenda

  2025cites this paper
• Edge-Enabled Federated Learning for Predictive Energy Modeling in Multi-Building Systems

  2025influential citation
• A Triple-Optimized Extreme Learning Machine Model for Power Load Forecasting

  2025cites this paper
• Federated learning for solar energy applications: A case study on real-time fault detection

  2024cites this paper
• Bulk Power Systems Emergency Control Based on Machine Learning Algorithms and Phasor Measurement Units Data: A State-of-the-Art Review

  2024cites this paper
• Federated Domain Separation for Distributed Forecasting of Non-IID Household Loads

  2024cites this paper
• Forecasting energy power consumption using federated learning in edge computing devices

  2024cites this paper
• Addressing Heterogeneity in Federated Load Forecasting with Personalization Layers

  2024cites this paper
• Powering the Future of IoT: Federated Learning for Optimized Power Consumption and Enhanced Privacy

  2024cites this paper
• Federated autoML learning for community building energy prediction

  2024cites this paper
• From Time-Series to Hybrid Models: Advancements in Short-Term Load Forecasting Embracing Smart Grid Paradigm

  2024cites this paper
• Advancing Power System Services With Privacy-Preserving Federated Learning Techniques: A Review

  2024cites this paper
• Adaptive DFL‐based straggler mitigation mechanism for synchronous ring topology in digital twin networks

  2024cites this paper
• Industrial IoT Sensor Data Federation in an Enterprise for an Early Failure Prediction

  2024influential citation
• Advancing Accuracy in Energy Forecasting using Mixture-of-Experts and Federated Learning

  2024cites this paper
• Decentralized Federated Anomaly Detection in Smart Grids: A P2P Gossip Approach

  2024cites this paper
• Empowering federated learning techniques for privacy-preserving PV forecasting

  2024cites this paper
• Low-carbon operation strategy of virtual power plant considering progressive demand response

  2024cites this paper
• A Comprehensive Survey on Load Forecasting Hybrid Models: Navigating the Futuristic Demand Response Patterns through Experts and Intelligent Systems

  2024cites this paper
• Privacy-Preserving Energy Forecasting in Smart Homes using Federated Learning and SecureBoost

  2024cites this paper
• Formal Logic-guided Robust Federated Learning against Poisoning Attacks

  2024cites this paper
• Electrical Load Forecasting in Smart Grid: A Personalized Federated Learning Approach

  2024cites this paper
• Enhancing Short-Term Energy Forecasting in Distributed Systems Through Federated Learning

  2024cites this paper
• Robustness Against Data Integrity Attacks in Decentralized Federated Load Forecasting

  2024cites this paper
• Exploring Federated Learning for Energy Consumption Forecasting in Smart Homes

  2024cites this paper
• 5G Traffic Forecasting using Federated Learning

  2023cites this paper
• Efficient community electricity load forecasting with transformer and federated learning

  2023cites this paper
• A review of federated learning in renewable energy applications: Potential, challenges, and future directions

  2023cites this paper
• A Federated Learning Approach to Predict Energy Consumption

  2023cites this paper
• Crossing Roads of Federated Learning and Smart Grids: Overview, Challenges, and Perspectives

  2023cites this paper
• Mitigating Concept Drift in Distributed Contexts with Dynamic Repository of Federated Models

  2023cites this paper
• PSO-GA-based Federated Learning for Predicting Energy Consumption in Smart Buildings

  2023cites this paper
• Assessing Probabilistic Load Forecasting Accuracy Against Customer Privacy Constraints At a Low Aggregate Level

  2023cites this paper
• Federated Learning Assisted Distributed Energy Optimization

  2023cites this paper
• Interaction Characteristics Modeling of Microgrid Clusters Based on Federated Learning

  2023cites this paper
• Analyzing Federated Learning Aggregation and Distributed Personalization Algorithms Towards Understanding Users’ Residential Electric Load Patterns

  2023cites this paper
• Comparative Analysis of Data-Driven Algorithms for Building Energy Planning via Federated Learning

  2023cites this paper
• Secure short-term load forecasting for smart grids with transformer-based federated learning

  2023influential citation
• The role of ‘living laboratories’ in accelerating the energy system decarbonization

  2022cites this paper
• A Secure Federated Learning Framework for Residential Short-Term Load Forecasting

  2022cites this paper
• Federated Learning for 5G Base Station Traffic Forecasting

  2022cites this paper
• Federated Learning for Short-term Load Forecasting

  year unknowncites this paper
• Enhanced Adversarial Attack Resilience in Energy Networks through Energy and Privacy Aware Federated Learning

  year unknowncites this paper