Demand Response in HEMSs Using DRL and the Impact of Its Various Configurations and Environmental Changes

Article Engineering, Electrical & Electronic

DRL-HEMS: Deep Reinforcement Learning Agent for Demand Response in Home Energy Management Systems Considering Customers and Operators Perspectives

Aya A. Amer et al.

Summary: This article proposes a data-driven multi-objective DRL-HEMS solution that optimizes household energy consumption, reduces electricity cost, and considers resident comfort and transformer loading condition.

IEEE TRANSACTIONS ON SMART GRID (2023)

Add to Collection

Article Energy & Fuels

Optimal Management for EV Charging Stations: A Win-Win Strategy for Different Stakeholders Using Constrained Deep Q-Learning

Athanasios Paraskevas et al.

Summary: Decarbonization of the transportation sector is of great significance due to the increase in energy demand and emissions. The adoption of electric vehicles (EVs) is a promising option, but pricing and scheduling strategies for public charging stations are crucial. A deep reinforcement learning approach is proposed to optimize pricing and charging control in public EV charging stations, considering the interests of different stakeholders and achieving both profit maximization and customer satisfaction.

ENERGIES (2022)

Add to Collection

Review Energy & Fuels

Review on Interpretable Machine Learning in Smart Grid

Chongchong Xu et al.

Summary: This paper discusses the importance of machine learning in the smart grid field and the definition, motivations, and classification of interpretability. As the smart grid is a critical infrastructure area, machine learning models must be interpretable to increase user trust and improve system reliability. However, most machine learning models currently lack interpretability and remain black boxes.

ENERGIES (2022)

Add to Collection

Article Green & Sustainable Science & Technology

Multi-Stage Incentive-Based Demand Response Using a Novel Stackelberg-Particle Swarm Optimization

Suchitra Dayalan et al.

Summary: This study aims to implement an incentive-based demand response (IBDR) strategy from the perspectives of service providers and consumers. It utilizes optimization methods to analyze and compare different entities in the system.

SUSTAINABILITY (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Mixed Deep Reinforcement Learning Considering Discrete-continuous Hybrid Action Space for Smart Home Energy Management

Chao Huang et al.

Summary: In this paper, deep reinforcement learning algorithms are developed for optimizing home energy systems. The proposed mixed deep reinforcement learning algorithm effectively handles the challenge of discrete-continuous hybrid action space, while the safe-MDRL algorithm handles unsafe actions that violate system constraints.

JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY (2022)

Add to Collection

Article Energy & Fuels

Home Energy Management System Embedded with a Multi-Objective Demand Response Optimization Model to Benefit Customers and Operators

Aya Amer et al.

Summary: This paper presents a Home Energy Management System (HEMS) that optimizes the load demand and distributed energy resources, taking into account several factors to achieve the optimal demand/generation profile. Simulation results show that the system can reduce electricity costs, decrease demand peaks, and minimize transformer lifespan loss.

ENERGIES (2021)

Add to Collection

Article Energy & Fuels

Real-Time Autonomous Residential Demand Response Management Based on Twin Delayed Deep Deterministic Policy Gradient Learning

Yujian Ye et al.

Summary: This paper introduces a novel real-time demand response management strategy for residential households based on the twin delayed deep deterministic policy gradient (TD3) learning approach, which enables learning of neural-network-based and fine-grained demand response management policies in a multi-dimensional action space by exploiting high-dimensional sensory data.

ENERGIES (2021)

Add to Collection

Article Automation & Control Systems

Multiagent Reinforcement Learning for Energy Management in Residential Buildings

Mehdi Ahrarinouri et al.

Summary: This article explores the multiagent reinforcement learning approach for residential multicarrier energy management, employing Q-learning to provide the optimal solution and using a scenario-based method to address uncertainties. The simulated results demonstrate that the proposed method leads to lower cost schemes for consumers compared to traditional optimization-based energy management programs.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2021)

Add to Collection

Article Engineering, Electrical & Electronic