Hengpu Qiao, Feng Wang, Shengli Xie, Yaqing Wang, Ya Chen, Jingya Fan
{"title":"Power Prediction of Photovoltaic Power Generation Based on EMA Decomposition and FITS-GRU-MKAN","authors":"Hengpu Qiao, Feng Wang, Shengli Xie, Yaqing Wang, Ya Chen, Jingya Fan","doi":"10.1155/cplx/5502137","DOIUrl":null,"url":null,"abstract":"<p>The electricity generation of photovoltaic systems is influenced by many complex and changing factors, which cause large variations and uncertainties and bring difficulties to the safe and stable operation of power grids. It is important to make accurate medium-to-long-term predictions for reliable grid connection and support for power system planning. In this study, a photovoltaic power prediction model based on exponential weighted moving average decomposition and a neural network structure is presented. The decomposition procedure separates the long-term trends from the data, removes noise, and improves the forecasting accuracy. Moreover, a parallel network is used to process the decomposed signals in both time and frequency domains, so as to effectively capture the nonlinear characteristics of photovoltaic power generation. Experimental results indicate that the proposed model has excellent predictive ability. Specifically, under sunny, cloudy, and rainy conditions, our model achieves RMSE values of 0.267, 0.639, and 0.418, respectively, achieving lower RMSE and higher <i>R</i><sup>2</sup> than transformer, LSTM, and TimeNet baselines on this dataset. The <i>R</i><sup>2</sup> scores reached 0.979, 0.855, and 0.912, demonstrating superior stability and accuracy for medium-to-long-term forecasting.</p>","PeriodicalId":50653,"journal":{"name":"Complexity","volume":"2026 1","pages":""},"PeriodicalIF":1.6000,"publicationDate":"2026-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/cplx/5502137","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Complexity","FirstCategoryId":"5","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1155/cplx/5502137","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATHEMATICS, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0
Abstract
The electricity generation of photovoltaic systems is influenced by many complex and changing factors, which cause large variations and uncertainties and bring difficulties to the safe and stable operation of power grids. It is important to make accurate medium-to-long-term predictions for reliable grid connection and support for power system planning. In this study, a photovoltaic power prediction model based on exponential weighted moving average decomposition and a neural network structure is presented. The decomposition procedure separates the long-term trends from the data, removes noise, and improves the forecasting accuracy. Moreover, a parallel network is used to process the decomposed signals in both time and frequency domains, so as to effectively capture the nonlinear characteristics of photovoltaic power generation. Experimental results indicate that the proposed model has excellent predictive ability. Specifically, under sunny, cloudy, and rainy conditions, our model achieves RMSE values of 0.267, 0.639, and 0.418, respectively, achieving lower RMSE and higher R2 than transformer, LSTM, and TimeNet baselines on this dataset. The R2 scores reached 0.979, 0.855, and 0.912, demonstrating superior stability and accuracy for medium-to-long-term forecasting.
期刊介绍:
Complexity is a cross-disciplinary journal focusing on the rapidly expanding science of complex adaptive systems. The purpose of the journal is to advance the science of complexity. Articles may deal with such methodological themes as chaos, genetic algorithms, cellular automata, neural networks, and evolutionary game theory. Papers treating applications in any area of natural science or human endeavor are welcome, and especially encouraged are papers integrating conceptual themes and applications that cross traditional disciplinary boundaries. Complexity is not meant to serve as a forum for speculation and vague analogies between words like “chaos,” “self-organization,” and “emergence” that are often used in completely different ways in science and in daily life.