An online health monitoring system for photovoltaic arrays based on the B/S architecture

2018 International Conference on New Energy and Future Energy System

Tian, Y.^1 ; Chen, Z.C.^1 ; Zhou, H.F.^1 ; Wu, L.J.^1 ; Long, C.^2 ; Lin, P.J.^1 ; Cheng, S.Y.^1

College of Physics and Information Engineering, Fuzhou University, Fuzhou

350116, China^1

Institute of Energy, School of Engineering, Cardiff University, Cardiff

CF24 3AA, United Kingdom^2

关键词: Classification accuracy;    Different operating conditions;    Extreme learning machine;    Maximum power point;    On-line health monitoring;    On-line monitoring system;    Photovoltaic arrays;    Working efficiency;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/188/1/012064/pdf
DOI  :  10.1088/1755-1315/188/1/012064

来源: IOP

【 摘 要 】

In order to improve the working efficiency of the photovoltaic (PV) array inspection system, the application of online monitoring systems for the PV arrays is quickly rising. In this paper, an online PV array monitoring combining with B/S architecture, Python language, and Flask framework is developed to monitor and diagnose the status of PV arrays which can display the data of the PV array and facilitate the staff to monitor the working status of PV array. When a fault occurs, the staff can also register the fault information on the website quickly. The developed system is composed of three parts: data acquisition, data transmission and PV online monitoring website. Firstly, the system uses the Raspberry Pi3 to collect the data when the PV array operates in maximum power point (MPP), and the acquired data is stored locally in the Raspberry Pi. And then, the data is uploaded to the PC side via the FileZilla server software and further transmitted to online monitoring website. Finally, the PV array online monitoring website displays received data, and perform the fault diagnosis of PV array using a kernel based Extreme Learning Machine (KELM). Experimental results show that the total classification accuracy for ten different operating conditions can reach 97.2%.