Sine normalization method for power forecast model of wind power plant

Abstract

The invention discloses a sine normalization method for a power forecast model of a wind power plant, and belongs to the field of wind power forecast. The method comprises the following steps of: 1), obtaining n groups of numerical weather forecast data and output power data of the wind power plant; 2), initializing a BP (Back Propagation) neural network; 3), carrying out linear normalization processing on wind speed, wind direction sine, wind direction cosine, temperature, atmospheric pressure and humidity respectively, carrying out sine normalization processing on the output power data of the wind power plant; and 4), forecasting by using x'new as an input value of the BP neural network, and carrying out backward normalization on the obtained forecast result. The sine normalization method for the power forecast model of the wind power plant, disclosed by the invention, has the beneficial effects that the strong universality is realized; the forecast precision of a neural network power forecast model is improved remarkably; and the method is simple and feasible, and can be implemented without varying out modification on the original neural network power forecast model.

Description

technical field [0001] The invention belongs to the field of wind power forecasting, in particular to a sinusoidal normalization method for a wind farm power forecasting model. Background technique [0002] In recent years, the rapid development of wind power and large-scale grid-connection have brought huge challenges to the dispatching and operation of the power system. Wind power forecasting is one of the effective means to improve the peak-shaving and frequency-regulating capabilities of the power system and the grid's ability to accept wind power. Wind power forecasting is to establish a mapping relationship between parameters affecting power input and output power values. The neural network model is widely used in the field of power prediction due to its strong generalization ability, nonlinear mapping ability and fault tolerance. The establishment of the neural network model is a dynamic learning process called "training". This process requires a large amount of hist...

AI Technical Summary

Problems solved by technology

Second, the transfer function of the neural network basically adopts the sigmoid function, and the curve of the function is as follows figure 1 As shown, an excessively large input value will make the function output in a "saturation" state, that is, the difference between the input values ​​is no longer sensitive, and normalization makes the input value within a relatively small range, so that The function output is relatively "active"

Third, the difference between the expected power output value and the actual power output value directly deter

Images