لطفا منتظر بمانید ...
0% Complete
صفحه اصلی
/
دهمین کنفرانس بین المللی فناوری و مدیریت انرژی
Home Energy Management System Based on Multi-Agent Deep Reinforcement Learning Handling the User’s Thermal Preferences
نویسندگان :
Ahmad Shahabi
1
Hamed Delkhosh
2
Mohsen Parsa Moghaddam
3
1- دانشگاه تربیت مدرس
2- دانشگاه تربیت مدرس
3- دانشگاه تربیت مدرس
کلمات کلیدی :
Deep Reinforcement Learning (DRL)،Home Energy Management System (HEMS)،Thermal Preferences
چکیده :
With the rising presence of digitalization, an increasing number of residents can now manage their smart appliances through home energy management systems (HEMS). However, HEMS faces significant challenges, including the complexity of user comfort modeling, various uncertainties in parameters, and the inherent difficulty of high-dimensional decision-making in dynamic environment. To overcome these issues, this paper proposes a data-driven framework for HEMS based on multi-agent reinforcement learning (MARL). In this model, a thermal comfort preference model is introduced to handle the user’s uncertain behavior. Also, a long short-term memory (LSTM)-based machine is developed for accurately predicting photovoltaic (PV) generation time-series. Finally, after combining PV predictions with thermal comfort assessments, a deep-double Q-network (DDQN) algorithm is applied to achieve optimal decision-making in HEMS. Numerical experiments show that the proposed method effectively tackles the challenge of high-dimensional integrated decision making under uncertainty.
لیست مقالات
لیست مقالات بایگانی شده
ارائه یک روش کلیدزنی ترکیبی PWM برای توزیع متقارن توان در ماژول‌های اینورتر آبشاری پل H
حسین منصوری زاده - مجید حسین پور
Studying the Implementation of the Smartening Road Map of Iran's Electricity Distribution Network
Peyman Zare - Rasoul Zare - Hossein Ghadimi - Bakhshali Sabery - Iraj Faraji Davoudkhani - Ahad Babaei Bork Abad
Thermodynamic Assessment and Optimization of a Solar-Thermal Natural Gas-Driven Polygeneration System: Energy, Exergy and Exergoeconomic Analysis
Mohammad Mahdi Forootan - Mahdi Asadi - Abolfazl Ahmadi - Rouhollah Ahmadi
A Novel Fuzzy/SMC based Energy Management Strategy for Hybrid Energy Storage System in an Isolated DC Microgrid
Puria Safari - Ehsan Farrokhi - Hoda Ghoreishy
Performance optimization of hybrid energy system considering hydrogen storage system and fuel cell under real-time load response program
Sayyad Nojavan - Hassan Khoudeh
طراحی کنترل‌کننده PIDA برای کنترل مبدل DC-DC بوست با استفاده از الگوریتم SMA
حسین شایقی - نیما عیسی زاده فلاحتی - مجید حسین‌پور - رضا مهاجری
A new model for calculating the cost of operation for different types of energy distribution systems in a comparative way
Mohammad TaghiTahooneh - Aidin Shaghaghi - Mohammad Yahyaeifar - Reza Dashti - Sahand Heidary - Rahim Zahedi
طراحی سیستم تبرید اجکتوری خورشید گازی متناسب با اقلیم گرم و خشک
رضا سعیدی سرقلعه - مازیار چنگیزیان - محمد رضا صفاریان - مصطفی کیانی ده‌کیانی
Optimal Energy Operation in DC Microgrids Including Hydro-Pumped Storage in the presence Demand Response Program
Sayyad Nojavan - Amir Attar
Evaluating Fuel Station Rooftops for Solar Energy Generation and Supporting Grid-Connected EV Charging Infrastructure
Armin Bagherian - Mahdi Hasanpour Nordoz - Mohammad Mohsen Hayati - Mehdi Abapour - Morteza Nazari-Heris - Miadreza Shafie-khah
بیشتر
ثمین همایش، سامانه مدیریت همایش ها و جشنواره ها - نگارش 44.12.4
