Application of parallel Elman neural network to hourly area solar PV plant generation estimation

Abstract

Summary Based on existing power generation data, an hourly area solar power estimation model using the parallel Elman neural network with solar radiation and system conversion efficiency is proposed. The accuracy and reliability of the assessment were verified using the information/data of solar photovoltaic power stations in various regions and timescales. Using the established appraisal algorithm involving K‐means evaluation and inverse distance weighting, regional forecasting of solar power generation was achieved. The prediction accuracy was also investigated using the actual details of the photovoltaic power stations. The results of the proposed model can assist the electricity dispatcher to not only precisely monitor the trend of solar power generation in different areas, but also coordinate with traditional power plants to meet the load demand more accurately. The proposed method can benefit power dispatching involving a larger scale of intermittent and unstable solar power electricity in the future.

Machine Learning Approaches for One-Day Ahead Soil Temperature Forecasting

“…An output gate learns to protect other units from unrelated memory content saved in the memory cell. A forget gate teaches how long the value is in the memory cell ( Hochreiter & Schmidhuber 1997;Piotrowski et al 2015;Salman et al 2018;Zahroh et al 2019;Cai et al 2020;Cho et al 2020).…”