.png){kind=icon}
Return
Demand response-based multi-agent deep reinforcement learning control framework for heating systems
.png){kind=icon}
PRE
AI
DOI：10.1016/j.applthermaleng.2025.127957.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Applied MADRL with MAPPO for efficient district heating system control. • A multi-zone RC model simulates thermal and hydraulic dynamics for predictions. • MAPPO-based control optimizes energy efficiency in multi-user district heating systems.
Keywords:
MADRL
MAPPO
district heating system
multi-zone RC model
energy efficiency
Journal
IF:
6.9
Papers:
2.8W
Citations:
10.6W
Organization
Cited Papers
Energy management based on multi-agent deep reinforcement learning for a multi-energy industrial park.png)
APPLIED ENERGY
OAAI
APPLIED ENERGYIF11
OAAIShareSaveDemand-response in building heating systems: A Model Predictive Control approachAPPLIED ENERGYOAAI
APPLIED ENERGYIF11
OAAIShareSaveA laboratory test of an Offline-trained Multi-Agent Reinforcement Learning Algorithm for Heating SystemsAPPLIED ENERGYOAAI
APPLIED ENERGYIF11
OAAIShareSaveThe role of thermostatic radiator valves for the control of space heating in UK social-rented householdsENERGY AND BUILDINGS
ENERGY AND BUILDINGSIF7.1
PREAI
ShareSaveShareSaveAn improved equivalent temperature drop method for evaluating the operating performances of ASHP units under frosting conditions considering their configuration and operationENERGY AND BUILDINGS
ENERGY AND BUILDINGSIF7.1
PREAI
ShareSaveAutomatic generation of multi-zone RC models using smart thermostat data from homesENERGY AND BUILDINGS
ENERGY AND BUILDINGSIF7.1
PREAI
ShareSaveA Thermo-Hydraulic couplings model for residential heating system based on Demand-side Regulation: Development and calibrationENERGY AND BUILDINGS
ENERGY AND BUILDINGSIF7.1
PREAI
ShareSave
View more