Wind Power Forecasting by the BP Neural Network with the Support of Machine Learning

Abstract

The goal of the research is to increase the accuracy of wind power forecasts while maintaining the power system’s stability and safety. First, the wireless sensor network (WSN) is used to collect the meteorological data of wind power plants in real time. Second, the real-time data collected by WSN are combined with the meteorological forecast data of some meteorological organizations. Then, the fruit fly optimization algorithm (FOA) is improved, and the improved fruit fly optimization algorithm (IFOA) and back propagation neural network (BPNN) are combined to construct the wind power forecast model. Finally, the signal reception of the WSN and the error of wind power forecast under different receiving distances and different antenna heights are tested. The results show that with the increase of receiving and transmitting distance, the signal strength decreases, the packet loss rate increases, and the electromagnetic wave of wind plants will cause some interference to the signal strength. The fly optimization algorithm-back propagation (IFOA-BP) wind power forecast model has a better effect than other models in wind power prediction and can better fit the actual tested wind power. Its root mean square error (RMSE) and mean absolute error (MAE) are 0.16 and 0.11, respectively. The research results provide a reference for improving the forecast accuracy of wind power.

GA−Reinforced Deep Neural Network for Net Electric Load Forecasting in Microgrids with Renewable Energy Resources for Scheduling Battery Energy Storage Systems

“…It is possible to fall into local optimum and low convergence accuracy. In literature [22], the fruit fly optimization algorithm (FOA) was improved, and the improved FOA (IFOA) algorithm was combined with the backpropagation neural network (BPNN) to build a wind power generation prediction model. The results show that the signal strength decreases and the packet loss rate increases with the increase in the transceiver distance, and the electromagnetic wave of the wind power plant will cause some interference with the signal strength.…”

Interval Forecasting Method of Aggregate Output for Multiple Wind Farms Using LSTM Networks and Time-Varying Regular Vine Copulas

“…Specifically, ref. [17,18] constructed a backpropagation (BP) neural network and ref. [19] constructed a support vector machine (SVM) model for wind power forecasting.…”

Multistep Wind Power Prediction Using Time-Varying Filtered Empirical Modal Decomposition and Improved Adaptive Sparrow Search Algorithm-Optimized Phase Space Reconstruction–Echo State Network

“…However, solving the nonlinearity problem in time series by using these models is difficult, thereby hindering high-accuracy prediction. Compared with physical models and statistical models, prediction models based on ML methods, such as extreme learning machine (ELM), backpropagation neural network (BPNN), recurrent neural network (RNN), convolutional Neural Networks (CNN), and long short-term memory (LSTM), can better analyze nonlinear time series and have thus been favored by numerous researchers [15][16][17][18][19]. Ding et al [20] employed the numerical weather prediction wind speed, trend, and detail terms as the inputs of the weighted time series and used the two-way gated recursive unit neural network to correct the wind speed error of the weather forecast and used the modified data to predict the final wind speed.…”

“…However, when confronted with the non-linearity and non-stationarity inherent in wind power data, LSTM may encounter challenges in achieving high predictive accuracy. Tian et al [16] employed the Backpropagation Neural Network (BPNN) for wind power forecasting. BPNN is trained using a backpropagation algorithm, which can address the non-linearity of wind power forecasting to a certain extent.…”