Power load prediction method and system

Abstract

The invention discloses a power load prediction method and a system, and belongs to the technical field of power, and the method comprises the steps: decomposing an original load sequence through employing a lumped empirical mode decomposition algorithm; calculating the approximate entropy of each modal component and combining the approximate entropies to obtain a reconstructed new sequence; wherein each new subsequence is predicted by a load prediction model of the extreme learning machine; and superposing the prediction result of each sub-sequence to obtain a final prediction value. The prediction analysis of the actual power grid load data by using the method provided by the invention shows that the method effectively improves the prediction precision.

Description

technical field [0001] The invention relates to the field of electric power technology, in particular to a method and system for electric load forecasting. Background technique [0002] At present, there are many methods of load forecasting. The traditional forecasting methods mainly include regression analysis, time series, and trend extrapolation. These methods all use mathematical ideas to establish corresponding forecasting models, rely on historical data, and are difficult to solve the randomness of load. Modern forecasting techniques include fuzzy forecasting, support vector machines, and neural networks. For the neural network, the static network (back propagation, BP) is widely used. Although it has a certain self-learning ability, its convergence speed is slow and it is easy to fall into a local minimum, which limits its application. As a relatively new neural network algorithm, neural network (Extreme Learning Machine, ELM) can randomly select hidden layer node p...

AI Technical Summary

Problems solved by technology

However, the EMD decomposition method is difficult to avoid the occurrence of modal aliasing, and the obtained false IMF will have an adverse effect on the prediction accuracy

Images