Venkata Siva Prasad Machina, Koduru Sriranga Suprabhath, S. Madichetty
{"title":"冬季太阳能光伏系统故障检测——一种深度学习方法","authors":"Venkata Siva Prasad Machina, Koduru Sriranga Suprabhath, S. Madichetty","doi":"10.1109/TPEC54980.2022.9750828","DOIUrl":null,"url":null,"abstract":"In recent times, the scenario of power systems is undergoing a rapid change. The evolution of microgrids has created a great scope for integrating renewable power generation into the grid, which ultimately achieves the goal for clean energy. DC microgrid (DCMG) is a preferable power system setup, as most of the daily appliances used in our households work on direct current (DC). Solar photovoltaic (SPV) systems contribute the most to DC power generating systems. The operation of SPV systems is better understood by analyzing the current-voltage (I-V) characteristics. Current and voltage values obtained from the solar panel are highly variable and depend on the weather conditions. The electric faults in the SPV systems will reduce the efficiency. During the summer season, normal sunny day and normal cloudy day are classified correctly. In winter season during some aberrant weather conditions for solar power generation like wind, snowy and cloudy, the current values are classified as faulty operation. This misclassification is avoided using machine learning (ML) and deep learning (DL) algorithms. Dataset includes electrical faults and normal operations; the ML and DL models are trained on this dataset with different activation functions and optimizers. Evaluation metric accuracy is calculated. Python3.8.6 has been used as a programming language to detect faults.","PeriodicalId":185211,"journal":{"name":"2022 IEEE Texas Power and Energy Conference (TPEC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Fault Detection in Solar Photovoltaic Systems During Winter Season- A Deep Learning Approach\",\"authors\":\"Venkata Siva Prasad Machina, Koduru Sriranga Suprabhath, S. Madichetty\",\"doi\":\"10.1109/TPEC54980.2022.9750828\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In recent times, the scenario of power systems is undergoing a rapid change. The evolution of microgrids has created a great scope for integrating renewable power generation into the grid, which ultimately achieves the goal for clean energy. DC microgrid (DCMG) is a preferable power system setup, as most of the daily appliances used in our households work on direct current (DC). Solar photovoltaic (SPV) systems contribute the most to DC power generating systems. The operation of SPV systems is better understood by analyzing the current-voltage (I-V) characteristics. Current and voltage values obtained from the solar panel are highly variable and depend on the weather conditions. The electric faults in the SPV systems will reduce the efficiency. During the summer season, normal sunny day and normal cloudy day are classified correctly. In winter season during some aberrant weather conditions for solar power generation like wind, snowy and cloudy, the current values are classified as faulty operation. This misclassification is avoided using machine learning (ML) and deep learning (DL) algorithms. Dataset includes electrical faults and normal operations; the ML and DL models are trained on this dataset with different activation functions and optimizers. Evaluation metric accuracy is calculated. Python3.8.6 has been used as a programming language to detect faults.\",\"PeriodicalId\":185211,\"journal\":{\"name\":\"2022 IEEE Texas Power and Energy Conference (TPEC)\",\"volume\":\"18 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-02-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE Texas Power and Energy Conference (TPEC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/TPEC54980.2022.9750828\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE Texas Power and Energy Conference (TPEC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TPEC54980.2022.9750828","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Fault Detection in Solar Photovoltaic Systems During Winter Season- A Deep Learning Approach
In recent times, the scenario of power systems is undergoing a rapid change. The evolution of microgrids has created a great scope for integrating renewable power generation into the grid, which ultimately achieves the goal for clean energy. DC microgrid (DCMG) is a preferable power system setup, as most of the daily appliances used in our households work on direct current (DC). Solar photovoltaic (SPV) systems contribute the most to DC power generating systems. The operation of SPV systems is better understood by analyzing the current-voltage (I-V) characteristics. Current and voltage values obtained from the solar panel are highly variable and depend on the weather conditions. The electric faults in the SPV systems will reduce the efficiency. During the summer season, normal sunny day and normal cloudy day are classified correctly. In winter season during some aberrant weather conditions for solar power generation like wind, snowy and cloudy, the current values are classified as faulty operation. This misclassification is avoided using machine learning (ML) and deep learning (DL) algorithms. Dataset includes electrical faults and normal operations; the ML and DL models are trained on this dataset with different activation functions and optimizers. Evaluation metric accuracy is calculated. Python3.8.6 has been used as a programming language to detect faults.