Power load prediction method

Abstract

The invention belongs to the technical field of power load prediction, and specifically relates to a power load prediction method. The power load prediction method comprises the following steps: S1, constructing a training data set and a test data set of a prediction model; S2, establishing a prediction model based on a hierarchical parallel Bayesian neural network; S3, inputting training samplesin the training data set into the prediction model based on the hierarchical parallel Bayesian neural network for training; and S4, inputting test data into a trained prediction model for prediction so as to obtain a power load prediction result. According to the invention, the power load is predicted by using the prediction model of the hierarchical parallel Bayesian neural network; the practicability of the model provided by the invention is verified by using actual power grid load data; and high prediction precision is achieved.

Description

Technical field [0001] The invention belongs to the technical field of electric load forecasting, and specifically relates to a method for electric load forecasting. Background technique [0002] Electric energy is currently the most important energy source in the world. However, the shortcomings of the difficulty of electric energy storage have not been effectively solved. This requires the power generation plan and load demand to achieve a dynamic balance. Therefore, high-precision load forecasting is the normal and safe operation of the power system. An important guarantee for power supply quality. At present, with the rapid development of new energy power generation, load fluctuations are also increasing. The main reason is that the randomness of new energy sources is strong. The access of a large number of distributed new energy sources has a strong impact on the load of the regional power grid. Bringing huge challenges, so high-precision and practical load forecasting tech...

AI Technical Summary

Problems solved by technology

However, the traditional BP neural network has the problem of local minimum in the prediction process, and the generalization ability is not ideal

However, most of the above model research mainly focuses on the construction of single-layer forecasting models, and does not consider the specific operation form of the actual power grid load forecasting, that is, the actual situation that the historical load data of the day before the forecasting day cannot be completely collected.

Images