A federated and transfer learning based approach for households load forecasting

Abstract

The escalating global population and increased smart-devices demand have made electricity load estimation a significant challenge for relevant authorities. Even with advancements in Artificial Intelligence, pinpointing both immediate and long-term electricity requirements remain a challenging and complex task. Predicting electricity usage at the household level can offer insights into this trend, aiding in the development of efficient load management strategies. However, creating individual predictive models for every household is a resource-intensive task. The current research proposes a streamlined approach that merges clustering analysis with federated and transfer learning to craft household-level predictive models. Firstly, clustering analysis is employed to discern electricity usage patterns, forming cluster-specific datasets. Subsequently, a federated learning model is introduced to each identified cluster, ensuring that the foundational model is finely calibrated to the unique consumption patterns inherent to each group. To evaluate the effectiveness of our approach, we employed Root Mean Square Error and Mean Absolute Error as evaluation metrics. During the evaluation phase, the transfer learning approach is employed, fine-tuning our root model on 70% of the data and testing its performance on the remaining 30%. The robustness of the proposed methodology is validated using a comprehensive dataset detailing electricity usage across Australian households. When bench-marked against prevailing methodologies, our proposed model consistently demonstrates either closer or superior predictive accuracy, emphasizing its potential as a formidable tool in real-time electricity consumption forecasting.