Electric power load prediction method based on long-short-term memory neural network

Abstract

The invention discloses an electric power load prediction method based on a long-short-term memory neural network. The method comprises the following steps: inputting power load data of historical moments, regional characteristic factors and a specified time period required to be predicted; carrying out training modeling on the power load data and the regional characteristic factors at historicalmoments by adopting an LSTM network, and generating a neural network model of power load prediction; predicting the electric load through the established neural network model; and finally, outputtingan electric load prediction result of the region at the appointed time through an output unit. The method has the advantages that the neural network model can be built according to the data over the years and the building characteristic factors, the power consumption load in the appointed time period can be accurately predicted, and the power consumption load prediction accuracy is effectively improved.

Description

technical field [0001] The invention relates to an electric load forecasting method based on a long-short-term memory neural network, and belongs to the technical field of electric power system load forecasting. Background technique [0002] Ensuring the accuracy of power grid load forecasting is crucial to reducing the economic loss of the power grid and ensuring the safe operation of the power grid. Over the years, improving the accuracy of electric load forecasting has been the focus of research. However, due to the variety of energy sources in the power grid and the different energy utilization methods, the load data of the power grid is highly volatile and random, resulting in low load forecasting accuracy, and it is difficult to accurately fit the distribution of load data. [0003] With the continuous acceleration of power grid intelligence, the increase of data volume and the volatility and randomness of data make the traditional load forecasting methods more and mo...

AI Technical Summary

Problems solved by technology

The common neural network uses machine learning methods to find the nonlinear mapping relationship between load influencing factors and load, ignoring the correlation relationship between sequence data between continuous load samples

Load data, as a typical time series, has nonlinearity and correlation. Traditional methods only establish a nonlinear relationship between the input characteristics and output power of a single sample, which loses the strong correlation between continuous sequence samples, and its prediction accuracy is limited.

Images