Cross-household Transfer Learning Approach with LSTM-based Demand Forecasting

2026-02-15

AI Summary

This study addresses the high computational cost and poor scalability of training individual hot water demand forecasting models for each household in large-scale heat pump deployments. To overcome this challenge, the authors propose DELTAiF, a novel framework that introduces cross-household transfer learning to residential hot water demand prediction for the first time. Leveraging an LSTM architecture, DELTAiF transfers knowledge from representative source households and fine-tunes the model for target households. The approach substantially reduces training overhead—cutting training time by approximately 67%—while maintaining high prediction accuracy, with R² values ranging from 0.874 to 0.991 and MAPE as low as 0.001–0.017. This work thus provides an efficient and scalable solution for intelligent thermal management in residential settings.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

With the rapid increase in residential heat pump (HP) installations, optimizing hot water production in households is essential, yet it faces major technical and scalability challenges. Adapting production to actual household needs requires accurate forecasting of hot water demand to ensure comfort and, most importantly, to reduce energy waste. However, the conventional approach of training separate machine learning models for each household becomes computationally expensive at scale, particularly in cloud-connected HP deployments. This study introduces DELTAiF, a transfer learning (TL) based framework that provides scalable and accurate prediction of household hot water consumption. By predicting large hot water usage events, such as showers, DELTAiF enables adaptive yet scalable hot water production at the household level. DELTAiF leverages learned knowledge from a representative household and fine-tunes it across others, eliminating the need to train separate machine learning models for each HP installation. This approach reduces overall training time by approximately 67 percent while maintaining high predictive accuracy values between 0.874 and 0.991, and mean absolute percentage error values between 0.001 and 0.017. The results show that TL is particularly effective when the source household exhibits regular consumption patterns, enabling hot water demand forecasting at scale.

Problem

• hot water demand forecasting
• scalability
• residential heat pump
• transfer learning
• energy efficiency

Innovation

• transfer learning
• LSTM
• hot water demand forecasting
• scalable modeling
• heat pump optimization