# Optimal Demand Response Using Device Based Reinforcement Learning

arXiv: https://arxiv.org/abs/1401.1549 · HTML: https://mlsanity.com/paper/1401.1549/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jan 2014.

## Built on by (most cited first, 7 of 7)

- [Deep Multiagent Reinforcement Learning: Challenges and Directions](https://mlsanity.com/paper/2106.15691/) (2021)
- [Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces](https://mlsanity.com/paper/1905.09700/) (2019)
- [Meta-Reinforcement Learning for Building Energy Management System](https://mlsanity.com/paper/2210.12590/) (2022)
- [Deep Learning for Intelligent Demand Response and Smart Grids: A Comprehensive Survey](https://mlsanity.com/paper/2101.08013/) (2021)
- [Applications of blockchain and artificial intelligence technologies for enabling prosumers in smart grids: A review](https://mlsanity.com/paper/2202.10098/) (2022)
- [An Efficient Distributed Multi-Agent Reinforcement Learning for EV Charging Network Control](https://mlsanity.com/paper/2308.12921/) (2023)
- [Applications of Reinforcement Learning in Deregulated Power Market: A Comprehensive Review](https://mlsanity.com/paper/2205.08369/) (2022)

## Abstract (arXiv)

Demand response (DR) for residential and small commercial buildings is estimated to account for as much as 65% of the total energy savings potential of DR, and previous work shows that a fully automated Energy Management System (EMS) is a necessary prerequisite to DR in these areas. In this paper, we propose a novel EMS formulation for DR problems in these sectors. Specifically, we formulate a fully automated EMS's rescheduling problem as a reinforcement learning (RL) problem, and argue that this RL problem can be approximately solved by decomposing it over device clusters. Compared with existing formulations, our new formulation (1) does not require explicitly modeling the user's dissatisfaction on job rescheduling, (2) enables the EMS to self-initiate jobs, (3) allows the user to initiate more flexible requests and (4) has a computational complexity linear in the number of devices. We also demonstrate the simulation results of applying Q-learning, one of the most popular and classical RL algorithms, to a representative example.