An Efficient Battery-Charging Algorithm with ANN based MPPT Method for Off-Grid PV Systems

2022 IEEE 21st international Ccnference on Sciences and Techniques of Automatic Control and Computer Engineering (STA) Pub Date : 2022-12-19 DOI:10.1109/STA56120.2022.10019093

Yacine Triki, Ahcen Triki, A. Bechouche, D. Abdeslam, R. Porumb

{"title":"An Efficient Battery-Charging Algorithm with ANN based MPPT Method for Off-Grid PV Systems","authors":"Yacine Triki, Ahcen Triki, A. Bechouche, D. Abdeslam, R. Porumb","doi":"10.1109/STA56120.2022.10019093","DOIUrl":null,"url":null,"abstract":"In this paper, an efficient battery-charging algorithm is proposed for off-grid photovoltaic (PV) systems. This algorithm operates according to the three-stage charging procedure. It is based on a neural maximum power point tracking (MPPT) strategy, which exploits an adaptive linear neuron (ADALINE). The proposed charging algorithm is implemented in PV-battery charging system with a dc-dc boost converter. Based on the battery state of charge, the imposed charging current and voltage limits, and solar insolation, the suggested algorithm selects the appropriate charging stage, namely MPPT bulk stage, absorption stage and float stage. To validate the proposal effectiveness, simulation tests are performed. According to the prEN 50530 standard MPPT dynamic tests, the results indicates that the suggested adaptive neural network based MPPT technique allows to achieve unity efficiency under high irradiance levels, even for fast profiles. Under low irradiance level, an average efficiency of 99.33% is obtained. Moreover, performance of the three-stage charge controller is also successfully demonstrated.","PeriodicalId":430966,"journal":{"name":"2022 IEEE 21st international Ccnference on Sciences and Techniques of Automatic Control and Computer Engineering (STA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE 21st international Ccnference on Sciences and Techniques of Automatic Control and Computer Engineering (STA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/STA56120.2022.10019093","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

In this paper, an efficient battery-charging algorithm is proposed for off-grid photovoltaic (PV) systems. This algorithm operates according to the three-stage charging procedure. It is based on a neural maximum power point tracking (MPPT) strategy, which exploits an adaptive linear neuron (ADALINE). The proposed charging algorithm is implemented in PV-battery charging system with a dc-dc boost converter. Based on the battery state of charge, the imposed charging current and voltage limits, and solar insolation, the suggested algorithm selects the appropriate charging stage, namely MPPT bulk stage, absorption stage and float stage. To validate the proposal effectiveness, simulation tests are performed. According to the prEN 50530 standard MPPT dynamic tests, the results indicates that the suggested adaptive neural network based MPPT technique allows to achieve unity efficiency under high irradiance levels, even for fast profiles. Under low irradiance level, an average efficiency of 99.33% is obtained. Moreover, performance of the three-stage charge controller is also successfully demonstrated.

查看原文本刊更多论文

一种基于神经网络的离网光伏系统最优充电算法

针对离网光伏系统，提出了一种高效的电池充电算法。该算法按照三级收费程序运行。该算法基于神经网络最大功率点跟踪(MPPT)策略，该策略利用自适应线性神经元(ADALINE)。所提出的充电算法在采用dc-dc升压变换器的光伏电池充电系统中得以实现。该算法根据电池的充电状态、规定的充电电流和电压限值以及日照情况，选择合适的充电阶段，即MPPT大容量充电阶段、吸收充电阶段和浮子充电阶段。为了验证该建议的有效性，进行了仿真测试。根据prEN 50530标准MPPT动态测试，结果表明，基于自适应神经网络的MPPT技术可以在高辐照水平下实现统一效率，即使是快速轮廓。在低辐照度下，平均效率为99.33%。此外，还成功地验证了三级电荷控制器的性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2022 IEEE 21st international Ccnference on Sciences and Techniques of Automatic Control and Computer Engineering (STA)

自引率

0.00%

发文量