Short-term load predicting method of power grid

Abstract

The invention relates to a short-term load predicting method of a power grid. The method comprises the steps: step 1, acquiring historical data and pre-treating the data; step2, decomposing the historical load sample data into a plurality of different-frequency sub-sequences by using wavelet decomposition; step 3, performing single-branch reconstruction to each sub-sequence; step 4, dynamically choosing training samples and establishing a neural network predicting model optimized by a vertical and horizontal intersection algorithm; step 5, predicting each sub-sequence 24 hours in advance by using the optimal neural network predicting model; and step 6, superposing the predicted value of each sub-sequence to obtain a whole prediction result. The inherent defects of the neutral network can be overcome by optimizing BP neutral network parameters by a brand-new swarm intelligence algorithm, that is, the vertical and horizontal intersection algorithm instead of the traditional algorithm; the burr problem caused by the impact load processing is solved by the wavelet decomposition, the precision declining resulting from the removal of the effective load in the burr pre-treatment is solved and the predicted value of the hybrid algorithm is more approximate to the actual measured load value.

Description

technical field [0001] The invention relates to a short-term load forecasting method of a regional power grid, in particular to a short-term load forecasting method of a power grid using a hybrid wavelet transform and a crossover algorithm to optimize a neural network. Background technique [0002] At present, the most widely used method in load forecasting is artificial neural network forecasting. Among them, BP neural network has been widely used in the field of forecasting because of its self-organization and self-learning ability, which can realize any nonlinear mapping from input to output. However, the BP algorithm uses the gradient descent method to adjust the weights and thresholds, resulting in slow convergence and easy to fall into local optimum. As more influencing factors and learning samples are taken into consideration, the amount of calculation and the number of weights of the neural network will increase dramatically. In addition, when a large number of...

AI Technical Summary

Problems solved by technology

Among them, using PSO to optimize BP neural network parameters, although the convergence speed is fast, when considering the increase of load factors, the scale of decision variables will increase rapidly, and PSO is prone to premature phenomenon when solving large-scale optimization problems; using ACO to optimize BP neural network Optimization does not solve the premature problem. Although ACO improves the generalization ability of the neural network, in order to maintain the diversity of the population, the ant colony algorithm adopts a complex algorithm structure and more control parameters, which affects its practicability.

[0004] The above algorithms have their own advantages and disadvantages, which improve the performance of the neural network to a certain extent, but the common challenge they usually face is the problem of premature convergence.

So far, large-scale neural network optimization problems are still a great challenge for heuristic algorithms to solve large-scale multimodal optimization problems

Images