Adaptive solar power generation forecasting using enhanced neural network with weather modulation

作     者：Sujeeth, T. Ramesh, C. Palwe, Sushila Ramu, Gandikota Basha, Shaik Johny Upadhyay, Deepak Chanthirasekaran, K. Sivasankari, K. Rajaram, A. 

作者机构：Department of CSE Siddartha Educational Academy Group of Institutions Andhra Pradesh Tirupati India Department of Mechanical Engineering M. Kumarasamy College of Engineering Karur India Department of Computer Engineering and Technology MIT-WPU Maharashtra India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Telangana Hyderabad India  Andhra Pradesh Mylavaram India Department of Computer Science and Engineering Graphic Era hill univeristy Dehradun India Department of Electronics and Communication Engineering Saveetha Engineering College Chennai India Department of Electronics and Communication Engineering Akshaya College of Engineering and Technology Coimbatore India Department of Electronics and Communication Engineering E.G.S. Pillay Engineering College Nagapattinam India 

出 版 物：《Journal of Intelligent and Fuzzy Systems》 (J. Intelligent Fuzzy Syst.)

年 卷 期：2024年第46卷第4期

页      面：10955-10968页

核心收录：

学科分类：12[管理学] 0808[工学-电气工程] 080802[工学-电力系统及其自动化] 08[工学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 070802[理学-空间物理学] 0708[理学-地球物理学] 0807[工学-动力工程及工程热物理] 0706[理学-大气科学] 0835[工学-软件工程] 0714[理学-统计学（可授理学、经济学学位）] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Solar power generation 

摘      要：Solar power generation forecasting plays a vital role in optimizing grid management and stability, particularly in renewable energy-integrated power systems. This research paper presents a comprehensive study on solar power generation forecasting, evaluating traditional and advanced machine learning methods, including ARIMA, Exponential Smoothing, Support Vector Regression, Random Forest, Gradient Boosting, and Physics-based Models. Moreover, we propose an innovative Enhanced Artificial Neural Network (ANN) model, which incorporates Weather Modulation and Leveraging Prior Forecasts to enhance prediction accuracy. The proposed model is evaluated using real-world solar power generation data, and the results demonstrate its superior performance compared to traditional methods and other machine learning approaches. The Enhanced ANN model achieves an impressive Root Mean Square Error (RMSE) of 0.116 and a Mean Absolute Percentage Error (MAPE) of 36.26%. The integration of Weather Modulation allows the model to adapt to changing weather conditions, ensuring reliable forecasts even during adverse scenarios. Leveraging Prior Forecasts enables the model to capture short-term trends, reducing forecasting errors arising from abrupt weather changes. The proposed Enhanced ANN model showcases its potential as a promising tool for precise and reliable solar power generation forecasting, contributing to the efficient integration of solar energy into the power grid and advancing sustainable energy practices. © 2024 – IOS Press.