Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Capacity-constrained demand response in smart grids using deep reinforcement learning

Shafagh Abband Pashaki, Sepehr Maleki, Amir Badiee

TL;DR

Simulation results show that the proposed approach effectively reduces peak demand and smooths the aggregated load profile, leading to an approximately 22.82% reduction in the peak-to-average ratio compared to the no-demand-response case.

Abstract

This paper presents a capacity-constrained incentive-based demand response approach for residential smart grids. It aims to maintain electricity grid capacity limits and prevent congestion by financially incentivising end users to reduce or shift their energy consumption. The proposed framework adopts a hierarchical architecture in which a service provider adjusts hourly incentive rates based on wholesale electricity prices and aggregated residential load. The financial interests of both the service provider and end users are explicitly considered. A deep reinforcement learning approach is employed to learn optimal real-time incentive rates under explicit capacity constraints. Heterogeneous user preferences are modelled through appliance-level home energy management systems and dissatisfaction costs. Using real-world residential electricity consumption and price data from three households, simulation results show that the proposed approach effectively reduces peak demand and smooths the aggregated load profile. This leads to an approximately 22.82% reduction in the peak-to-average ratio compared to the no-demand-response case.

Capacity-constrained demand response in smart grids using deep reinforcement learning

TL;DR

Simulation results show that the proposed approach effectively reduces peak demand and smooths the aggregated load profile, leading to an approximately 22.82% reduction in the peak-to-average ratio compared to the no-demand-response case.

Abstract

This paper presents a capacity-constrained incentive-based demand response approach for residential smart grids. It aims to maintain electricity grid capacity limits and prevent congestion by financially incentivising end users to reduce or shift their energy consumption. The proposed framework adopts a hierarchical architecture in which a service provider adjusts hourly incentive rates based on wholesale electricity prices and aggregated residential load. The financial interests of both the service provider and end users are explicitly considered. A deep reinforcement learning approach is employed to learn optimal real-time incentive rates under explicit capacity constraints. Heterogeneous user preferences are modelled through appliance-level home energy management systems and dissatisfaction costs. Using real-world residential electricity consumption and price data from three households, simulation results show that the proposed approach effectively reduces peak demand and smooths the aggregated load profile. This leads to an approximately 22.82% reduction in the peak-to-average ratio compared to the no-demand-response case.
Paper Structure (18 sections, 16 equations, 12 figures, 9 tables)

This paper contains 18 sections, 16 equations, 12 figures, 9 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Demand response model
  4. Service provider model
  5. End user model
  6. Objective function
  7. Incentive optimisation
  8. Markov decision process for incentive-based demand response
  9. Double Deep Q-Network
  10. Real-time algorithm with LSTM forecasts and DDQN
  11. Experimental analysis
  12. Price and load forecasting
  13. Evaluation
  14. Simulation Setup
  15. Load Reduction and Optimal Incentive Rate
  16. ...and 3 more sections

Figures (12)

  • Figure 1: Hierarchical electricity market model.
  • Figure 2: Schematic of RL to find the optimal incentive rates.
  • Figure 3: Wholesale price forecasting for July 23--29, 2018.
  • Figure 4: Load forecasting of the three end users for July 23--29, 2018.
  • Figure 5: Training and validation episode rewards of the DDQN agent over $N_{\text{ep}} = 2500$ episodes.
  • ...and 7 more figures