• Home
  • Search
  • Online transfer learning (OTL) for accelerating deep reinforcement learning (DRL) for building energy management
  • Cite Icon1
  • https://doi.org/10.1080/19401493.2025.2511826Copy DOI Icon

Online transfer learning (OTL) for accelerating deep reinforcement learning (DRL) for building energy management

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Buildings account for over one-third of global energy consumption and emissions, primarily from heating and cooling operations. Intelligent optimisation through predictive controls, such as deep reinforcement learning (DRL), offers significant potential for energy efficiency. However, DRL faces challenges in generalisation and impractical retraining when applied to different buildings, limiting its scalability. Prior online transfer learning (OTL) approaches relied on simulation or rule-based methods but lacked live learning and real-time optimisation. This study proposes an OTL strategy combining autonomous simulation-based DRL policy pretraining with real-time fine-tuning for rapid adaptation to new buildings. Using the Soft Actor-Critic (SAC) algorithm, it was tested on commercial building energy management simulations. Results showed 18%+ reductions in HVAC energy consumption and 8%+ improvement in thermal comfort compared to rule-based and non-transfer DRL baselines. Empirical validation highlights OTL's potential in overcoming DRL's cold start and training burdens, paving the way for broader deployment in sustainable energy management.

Similar Papers
  • Research Article
  • Citations94

Online transfer learning strategy for enhancing the scalability and deployment of deep reinforcement learning control in smart buildings

  • Jan 10, 2023
  • Applied Energy
  • Davide Coraci +3
  • Dissertation

Data-driven energy management system for smart buildings

  • Jan 01, 2024
  • Hongyuan Ding
  • PDF
  • Research Article
  • Citations5

Deep imitation reinforcement learning with expert demonstration data

  • Oct 31, 2018
  • The Journal of Engineering
  • Menglong Yi +3
  • Conference Article
  • Citations1

Path following and obstacle avoidance of tracked vehicle via deep reinforcement learning with model predictive control as reference

  • Aug 09, 2023
  • Ting-Chien Chen +4
  • Research Article
  • Citations56

Towards a fossil-free urban transport system: An intelligent cross-type transferable energy management framework based on deep transfer reinforcement learning

  • Mar 28, 2024
  • Applied Energy
  • Ruchen Huang +2
  • Research Article
  • Citations33

Expert-guided imitation learning for energy management: Evaluating GAIL’s performance in building control applications

  • Jun 25, 2024
  • Applied Energy
  • Mingzhe Liu +4
  • Research Article
  • Citations19

Optimization of Home Energy Management Systems in Smart Cities Using Bacterial Foraging Algorithm and Deep Reinforcement Learning for Enhanced Renewable Energy Integration

  • Jan 01, 2024
  • International Transactions on Electrical Energy Systems
  • Mohammed Naif Alatawi
  • Research Article
  • Citations16

Real-Time Control of A2O Process in Wastewater Treatment Through Fast Deep Reinforcement Learning Based on Data-Driven Simulation Model

  • Dec 22, 2024
  • Water
  • Fukang Hu +3
  • Research Article
  • Citations18

Enabling intelligent transferable energy management of series hybrid electric tracked vehicle across motion dimensions via soft actor-critic algorithm

  • Mar 06, 2024
  • Energy
  • Hongwen He +3
  • Dissertation

Modeling and Optimization of Wastewater Treatment Plants with Deep Learning and Reinforcement Learning

  • Jan 01, 2025
  • Esmaeel Mohammadi
  • Research Article

Current Applications and Future Prospects of Deep Reinforcement Learning in Energy Management for Hybrid Power Systems

  • May 03, 2026
  • Energies
  • Zhao Li +2
  • Research Article
  • Citations5

Review of Smart Microgrid Platform Integrating AI and Deep Reinforcement Learning for Sustainable Energy Management

  • Jan 01, 2025
  • International Journal of Future Engineering Innovations
  • Chijioke Paul Agupugo +4
  • Book Chapter

A Hybrid Intelligent Framework for Smart Grid Load Forecasting and Wind Energy Optimization Using Deep Learning, Reinforcement Learning, and Genetic AI

  • Nov 14, 2025
  • Saurabh Pandey
  • Research Article
  • Citations22

On the Feasibility Guarantees of Deep Reinforcement Learning Solutions for Distribution System Operation

  • Mar 01, 2023
  • IEEE Transactions on Smart Grid
  • Mohammad Mehdi Hosseini +1
  • PDF
  • Research Article
  • Citations12

Research on Energy Management of Hydrogen Fuel Cell Bus Based on Deep Reinforcement Learning Considering Velocity Control

  • Aug 17, 2023
  • Sustainability
  • Yang Shen +7
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.