Demand Response for Home Energy Management Using Reinforcement Learning and Artificial Neural Network

Ever-changing variables in the electricity market require energy management systems (EMSs) to make optimal real-time decisions adaptively. Demand response (DR) is the latest approach being used to accelerate the efficiency and stability of power systems. This paper proposes an hour-ahead DR algorith...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on smart grid 2019-11, Vol.10 (6), p.6629-6639
Main Authors: Lu, Renzhi, Hong, Seung Ho, Yu, Mengmeng
Format: Article
Language:English
Subjects:
Algorithms
Artificial intelligence
artificial neural network
Artificial neural networks
Computer simulation
Decision making
Decisions
demand response
Electric appliances
Electric power systems
Electricity pricing
Energy conservation
Energy consumption
Energy costs
Energy management
Energy management systems
Energy policy
Home appliances
home energy management
Household appliances
Load management
Machine learning
Multiagent systems
Neural networks
Power efficiency
Reinforcement learning
Residential energy
Uncertainty
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Ever-changing variables in the electricity market require energy management systems (EMSs) to make optimal real-time decisions adaptively. Demand response (DR) is the latest approach being used to accelerate the efficiency and stability of power systems. This paper proposes an hour-ahead DR algorithm for home EMSs. To deal with the uncertainty in future prices, a steady price prediction model based on artificial neural network is presented. In cooperation with forecasted future prices, multi-agent reinforcement learning is adopted to make optimal decisions for different home appliances in a decentralized manner. To verify the performance of the proposed energy management scheme, simulations are conducted with non-shiftable, shiftable, and controllable loads. Experimental results demonstrate that the proposed DR algorithm can handle energy management for multiple appliances, minimize user energy bills, and dissatisfaction costs, and help the user to significantly reduce its electricity cost compared with a benchmark without DR.
ISSN:1949-3053
1949-3061
DOI:10.1109/TSG.2019.2909266