Big data-based electrical load prediction system

Abstract

The invention discloses a big data-based electrical load prediction system. According to the system, a prediction is carried out on the electric load capacity of one place in the future by an error back-propagation neural network method; the error back-propagation neural network method comprises an input layer, a hidden layer and an output layer; a mathematic model of the error back-propagation neural network method can be established through a function relationship among the input layer, the hidden layer and the output layer; input layer information corresponds to historical data of the electric load capacity; output layer information corresponds to predicted data of the electric load capacity; and the hidden layer corresponds to the function relationship between the predicted data and the historical data. According to the big data-based electrical load prediction system, the prediction is carried out the electric load capacity in the future by the error back-propagation neural network method; and the mathematic model of the error back-propagation neural network method is established, so that the prediction result is relatively accurate; the error can be accurately calculated; and a great convenience is brought to life.

Description

Technical field [0001] The invention relates to the field of power systems, in particular to a power load forecasting system based on big data. Background technique [0002] In the power system, if the total electricity load of a city in the next month can be known in advance, the power plant can adjust the operating time of the generator set, arrange the shutdown time of a generator in advance, and perform maintenance, which can be effective Extend the service life of the generator and improve its efficiency and reliability. For another example, if the total electricity load of a certain area in the next month can be known in advance, then the substation can adjust the operating time of the transformer group, arrange the downtime of a certain transformer in advance, and perform maintenance, which can effectively extend the transformer’s Life span and improve its efficiency and reliability. Similarly, if a mine or a factory can predict the electricity consumption in the next sta...

AI Technical Summary

Problems solved by technology

[0057] The exponential smoothing method described above is an interval prediction method limited by historical data. It is not accurate enough to predict the future trend of things, and it is even more unreasonable for the obvious increase or decrease trend of historical data.

Although, some books introduce that when the historical data presents a "linear trend", it can be processed by multiplying the difference between the output of primary smoothing and the output of secondary smoothing by α / (1-α), but what is "linear trend" And why this method is adopted, the book does not give a rigorous explanation

Therefore, the exponential smoothing method lacks sufficient theoretical basis and the prediction results are often disappointing; the selection of the number of moving items and smoothing coefficients is often different from person to person, and it is difficult to determine; the estimation error cannot be given

Images