We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Solar and Wind Energy Forecasting for Green and Intelligent Migration of Traditional Energy Sources.
- Authors
Mohsin, Syed Muhammad; Maqsood, Tahir; Madani, Sajjad Ahmed
- Abstract
Fossil-fuel-based power generation leads to higher energy costs and environmental impacts. Solar and wind energy are abundant important renewable energy sources (RES) that make the largest contribution to replacing fossil-fuel-based energy consumption. However, the uncertain solar radiation and highly fluctuating weather parameters of solar and wind energy require an accurate and reliable forecasting mechanism for effective and efficient load management, cost reduction, green environment, and grid stability. From the existing literature, artificial neural networks (ANN) are a better means for prediction, but the ANN-based renewable energy forecasting techniques lose prediction accuracy due to the high uncertainty of input data and random determination of initial weights among different layers of ANN. Therefore, the objective of this study is to develop a harmony search algorithm (HSA)-optimized ANN model for reliable and accurate prediction of solar and wind energy. In this study, we combined ANN with HSA and provided ANN feedback for its weights adjustment to HSA, instead of ANN. Then, the HSA optimized weights were assigned to the edges of ANN instead of random weights, and this completes the training of ANN. Extensive simulations were carried out and our proposed HSA-optimized ANN model for solar irradiation forecast achieved the values of MSE = 0.04754, MAE = 0.18546, MAPE = 0.32430%, and RMSE = 0.21805, whereas our proposed HSA-optimized ANN model for wind speed prediction achieved the values of MSE = 0.30944, MAE = 0.47172, MAPE = 0.12896%, and RMSE = 0.55627. Simulation results prove the supremacy of our proposed HSA-optimized ANN models compared to state-of-the-art solar and wind energy forecasting techniques.
- Subjects
CLEAN energy; SOLAR energy; RENEWABLE energy sources; WIND power; WIND forecasting; SOLAR radiation; ENERGY consumption; ARTIFICIAL neural networks
- Publication
Sustainability (2071-1050), 2022, Vol 14, Issue 23, p16317
- ISSN
2071-1050
- Publication type
Article
- DOI
10.3390/su142316317