Prediction method for power fluctuations in cross regional consumption and transportation under the integration of new energy

Abstract

Against the backdrop of the increasing development of the new energy industry, the volatility of new energy output poses significant challenges to regional power grid balance and energy absorption. Therefore, this article proposes a prediction method for cross regional transmission power fluctuations under new energy integration conditions. A comprehensive and representative sample dataset was constructed by comprehensively considering factors such as fluctuations in new energy output, capacity confidence, and peak shaving characteristic parameters, combined with numerical weather forecast data. Normalize the sample data to eliminate dimensional differences between parameters. The sparrow search algorithm is used to optimize the weights and thresholds of the double hidden layer BP neural network, effectively avoiding local optimization problems caused by over training. The experimental results show that this method has significant advantages in predicting power fluctuations in cross regional absorption and transportation of new energy, with a predicted power to power ratio of over 0.85.