Optimal Demand Response Using Device-Based Reinforcement Learning

Wen, Zheng; O’Neill, Daniel C.; Maei, Hamid Reza

doi:10.1109/tsg.2015.2396993

Cited by 245 publications

(121 citation statements)

References 20 publications

(41 reference statements)

Supporting

Mentioning

121

Contrasting

Order By: Relevance

“…The authors implemented a price based demand response and included a PV panel in the system model and reported an approximate daily energy cost saving of 15%. Wen et al proposed a demand response energy management systems for small buildings that enables automated device scheduling in response to electrical price fluctuations [85]. The authors implement Q learning with the aim of taking advantage of the estimated 65% of potential energy savings for small buildings by efficient device scheduling and report improvements upon the baseline.…”

Section: Home Management Systemsmentioning

confidence: 99%

A review of reinforcement learning for autonomous building energy management

Mason

Grijalva

2019

Computers & Electrical Engineering

225

View full text Add to dashboard Cite

The area of building energy management has received a significant amount of interest in recent years. This area is concerned with combining advancements in sensor technologies, communications and advanced control algorithms to optimize energy utilization. Reinforcement learning is one of the most prominent machine learning algorithms used for control problems and has had many successful applications in the area of building energy management. This research gives a comprehensive review of the literature relating to the application of reinforcement learning to developing autonomous building energy management systems. The main direction for future research and challenges in reinforcement learning are also outlined.

show abstract

Section: Home Management Systemsmentioning

confidence: 99%

A review of reinforcement learning for autonomous building energy management

Mason

Grijalva

2019

Computers & Electrical Engineering

225

View full text Add to dashboard Cite

show abstract

“…Weng et al [21], demonstrate a fully automated energy management system (EMS) using reinforcement learning (RL) techniques. The energy management and appliance scheduling problem is solved by observe, learn and adapt (OLA) algorithm which adds more intelligence to EMS.…”

Section: Related Workmentioning

confidence: 99%

An Optimized Home Energy Management System with Integrated Renewable Energy and Storage Resources

et al. 2017

View full text Add to dashboard Cite

Traditional power grid and its demand-side management (DSM) techniques are centralized and mainly focus on industrial consumers. The ignorance of residential and commercial sectors in DSM activities degrades the overall performance of a conventional grid. Therefore, the concept of DSM and demand response (DR) via residential sector makes the smart grid (SG) superior over the traditional grid. In this context, this paper proposes an optimized home energy management system (OHEMS) that not only facilitates the integration of renewable energy source (RES) and energy storage system (ESS) but also incorporates the residential sector into DSM activities. The proposed OHEMS minimizes the electricity bill by scheduling the household appliances and ESS in response to the dynamic pricing of electricity market. First, the constrained optimization problem is mathematically formulated by using multiple knapsack problems, and then solved by using the heuristic algorithms; genetic algorithm (GA), binary particle swarm optimization (BPSO), wind driven optimization (WDO), bacterial foraging optimization (BFO) and hybrid GA-PSO (HGPO) algorithms. The performance of the proposed scheme and heuristic algorithms is evaluated via MATLAB simulations. Results illustrate that the integration of RES and ESS reduces the electricity bill and peak-to-average ratio (PAR) by 19.94% and 21.55% respectively. Moreover, the HGPO algorithm based home energy management system outperforms the other heuristic algorithms, and further reduces the bill by 25.12% and PAR by 24.88%.

show abstract

“…As such, multi‐agent systems in particular have been recommended for usage in power systems applications by the IEEE Power and Energy Society . AIMD frameworks, market‐based approaches, particle swarm optimisation game theory inspired, and reinforcement learning are such examples. In addition, solutions such as probabilistic approaches can be seen as a hybrid approach.…”

Section: State‐of‐the‐art For Dr Approaches and Evaluation Toolsmentioning

confidence: 99%

Optimising residential electric vehicle charging under renewable energy: Multi‐agent learning in software simulation and hardware‐in‐the‐loop evaluation

et al. 2019

View full text Add to dashboard Cite

Summary The integration of intermittent renewable energy sources coupled with the increasing demand of electric vehicles (EVs) poses new challenges to the electrical grid. To address this, many solutions based on demand response have been presented. These solutions are typically tested only in software‐based simulations. In this paper, we present the application in hardware‐in‐the‐loop (HIL) of a recently proposed algorithm for decentralised EV charging, prediction‐based multi‐agent reinforcement learning (P‐MARL), to the problem of optimal EV residential charging under intermittent wind power and variable household baseload demands. P‐MARL is an approach that can address EV charging objectives in a demand response aware manner, to avoid peak power usage while maximising the exploitation of renewable energy sources. We first train and test our algorithm in a residential neighbourhood scenario using GridLAB‐D, a software power network simulator. Once agents learn optimal behaviour for EV charging while avoiding peak power demand in the software simulator, we port our solution to HIL while emulating the same scenario, in order to decrease the effects of agent learning on power networks. Experimental results carried out in a laboratory microgrid show that our approach makes full use of the available wind power, and smooths grid demand while charging EVs for their next day's trip, achieving a peak‐to‐average ration of 1.67, down from 2.24 in the baseline case. We also provide an analysis of the additional demand response effects observed in HIL, such as voltage drops and transients, which can impact the grid and are not observable in the GridLAB‐D software simulation.

show abstract

Optimal Demand Response Using Device-Based Reinforcement Learning

Cited by 245 publications

References 20 publications

A review of reinforcement learning for autonomous building energy management

A review of reinforcement learning for autonomous building energy management

An Optimized Home Energy Management System with Integrated Renewable Energy and Storage Resources

Optimising residential electric vehicle charging under renewable energy: Multi‐agent learning in software simulation and hardware‐in‐the‐loop evaluation

Contact Info

Product

Resources

About