C. Nsengimana, Xiu Jun Shen, X. Han, Ling-ling Li, Haiyu Wang
{"title":"基于改进萤火虫算法优化支持向量机的光伏短期功率预测","authors":"C. Nsengimana, Xiu Jun Shen, X. Han, Ling-ling Li, Haiyu Wang","doi":"10.1109/IS3C50286.2020.00095","DOIUrl":null,"url":null,"abstract":"With the current increasing demand in energy consumption, there is a huge increase of prominent energy problems that require us to imperatively seek for the new green energy sources. Photovoltaic power generation is one of the most feasible power generation methods due to its high cleanliness and static characteristics. This paper proposes a photoelectric power prediction method based on an improved firefly algorithm to optimize support vector machines (SVM) for short-term prediction. We effectively combine the regression support vector machine (SVR) with the modified firefly algorithm (MFFA) and use the firefly estimation method to determine the best fitness penalty factor c and kernel function g, so that the support vector machine can better predict the photovoltaic power. In order to make the firefly algorithm to optimize the support vector machine faster, we improved the firefly algorithm step factor $a$ and introduced a weight coefficient ϖ, Compared with conventional techniques, this method has better prediction results and prediction speed is also better than the traditional intelligent optimization models. Let's take the data from a photovoltaic base in the Desert Knowledge Australian Solar Energy Centre (DKASC) as an example.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Short-term Photovoltaic Power Forecasting Based on Improved Firefly Algorithm to optimize support vector machine\",\"authors\":\"C. Nsengimana, Xiu Jun Shen, X. Han, Ling-ling Li, Haiyu Wang\",\"doi\":\"10.1109/IS3C50286.2020.00095\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"With the current increasing demand in energy consumption, there is a huge increase of prominent energy problems that require us to imperatively seek for the new green energy sources. Photovoltaic power generation is one of the most feasible power generation methods due to its high cleanliness and static characteristics. This paper proposes a photoelectric power prediction method based on an improved firefly algorithm to optimize support vector machines (SVM) for short-term prediction. We effectively combine the regression support vector machine (SVR) with the modified firefly algorithm (MFFA) and use the firefly estimation method to determine the best fitness penalty factor c and kernel function g, so that the support vector machine can better predict the photovoltaic power. In order to make the firefly algorithm to optimize the support vector machine faster, we improved the firefly algorithm step factor $a$ and introduced a weight coefficient ϖ, Compared with conventional techniques, this method has better prediction results and prediction speed is also better than the traditional intelligent optimization models. Let's take the data from a photovoltaic base in the Desert Knowledge Australian Solar Energy Centre (DKASC) as an example.\",\"PeriodicalId\":143430,\"journal\":{\"name\":\"2020 International Symposium on Computer, Consumer and Control (IS3C)\",\"volume\":\"42 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 International Symposium on Computer, Consumer and Control (IS3C)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IS3C50286.2020.00095\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 International Symposium on Computer, Consumer and Control (IS3C)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IS3C50286.2020.00095","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Short-term Photovoltaic Power Forecasting Based on Improved Firefly Algorithm to optimize support vector machine
With the current increasing demand in energy consumption, there is a huge increase of prominent energy problems that require us to imperatively seek for the new green energy sources. Photovoltaic power generation is one of the most feasible power generation methods due to its high cleanliness and static characteristics. This paper proposes a photoelectric power prediction method based on an improved firefly algorithm to optimize support vector machines (SVM) for short-term prediction. We effectively combine the regression support vector machine (SVR) with the modified firefly algorithm (MFFA) and use the firefly estimation method to determine the best fitness penalty factor c and kernel function g, so that the support vector machine can better predict the photovoltaic power. In order to make the firefly algorithm to optimize the support vector machine faster, we improved the firefly algorithm step factor $a$ and introduced a weight coefficient ϖ, Compared with conventional techniques, this method has better prediction results and prediction speed is also better than the traditional intelligent optimization models. Let's take the data from a photovoltaic base in the Desert Knowledge Australian Solar Energy Centre (DKASC) as an example.