Optimal Energy Management of a Grid-Tied Solar PV-Battery Microgrid: A Reinforcement Learning Approach

نویسندگان

چکیده

In the near future, microgrids will become more prevalent as they play a critical role in integrating distributed renewable energy resources into main grid. Nevertheless, sources, such solar and wind can be extremely volatile are weather dependent. These coupled with demand lead to random variations on both generation load sides, thus complicating optimal management. this article, reinforcement learning approach has been proposed deal non-stationary scenario, which management system (EMS) is modelled Markov decision process (MDP). A novel modification of control problem presented that improves use stored battery dynamic not subjected future high grid tariffs. comprehensive reward function also developed decreases infeasible action explorations improving performance data-driven technique. Q-learning algorithm then minimize operational cost microgrid under unknown information. To assess EMS, comparison study between trading EMS model non-trading case performed using typical commercial curve PV profile over 24-h horizon. Numerical simulation results indicate agent learns select an optimized schedule minimizes (cost power purchased from utility wear cost) all studied cases. However, comparing costs, latter one was found decrease costs by 4.033% summer season 2.199% winter season.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Efficient Energy Management for a Grid-Tied Residential Microgrid

In this paper, an effective energy management system (EMS) for application in integrated building and microgrid system is introduced and implemented as a multi-objective optimization problem. The proposed architecture covers different key modelling aspects such as distributed heat and electricity generation characteristics, heat transfer and thermal dynamics of sustainable residential buildings...

متن کامل

Implementation of Optimal Load Balancing Strategy for Hybrid Energy Management System in DC/AC Microgrid with PV and Battery Storage

The proposed paper presents the DC/AC microgrid modeling using the Energy storage units and photovoltaic (PV) panels. The modal consists of a two stage power conversion. The power is supplied to the both DC and AC loads by this PV solar panels. The suitable way to explore the PV generation model is by using manufacturer datasheet. A bidirectional converter is connected to the battery storage sy...

متن کامل

Multi Attribute Investment Planning of a Grid-Connected Diesel/Wind/PV/Battery Hybrid Energy System

Recently, along with the depletion of fossil fuels and growing electrical requirements, more attention has been paid on utilizing Renewable Energy Sources (RESs). The Chichest tourism complex is located 20 km far from Orumieh, Iran which has been supplied through the main distribution grid connection. But, recently the trend is to expand the share of RESs in supplying microgrids demand. Hence, ...

متن کامل

Dynamic Modelling of Advanced Battery Energy Storage System for Grid-Tied AC Microgrid Applications

© 2013 Sarasua et al., licensee InTech. This is an open access chapter distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Dynamic Modelling of Advanced Battery Energy Storage System for Grid-Tied AC Microgr...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Energies

سال: 2021

ISSN: ['1996-1073']

DOI: https://doi.org/10.3390/en14092700