Solar energy prediction method based on dynamic condition Boltzmann machine

Abstract

The invention discloses a solar energy prediction method based on a dynamic condition Boltzmann machine. The solar energy prediction method comprises the following steps of: obtaining parameters of a condition Boltzmann machine; establishing a model of a dynamic condition Boltzmann machine; training the dynamic condition Boltzmann machine, and obtaining parameters of a trained dynamic condition Boltzmann machine model; and adopting the trained dynamic condition Boltzmann machine parameters and sample vectors to obtain a solar energy prediction value by means of Gibbs sampling. The adopted condition Boltzmann machine model can effectively and dynamically capture data changes based on a time sequence, so that the model can be adopted to learn the change rule of solar energy data, and the accuracy of real-time prediction is improved; in addition, a data mining method is adopted to obtain a most similar sample in real time, and the most similar sample is used as an input sample, so that the accuracy of real-time prediction is further improved.

Description

technical field [0001] The invention belongs to the field of machine learning, and more specifically relates to a solar energy prediction method based on a dynamic conditional Boltzmann machine. Background technique [0002] Since the new energy generated by solar power and wind power has the characteristics of instability and dynamic changes, the problem of mismatch between load and new energy has become a bottleneck for the storage system to use new energy; According to the dynamic change trend, the job scheduling and energy consumption arrangement of the data center should be adjusted accordingly, so as to improve the utilization rate of new energy and reduce the dependence on the grid power supply. [0003] Existing new energy forecasting methods include physical model forecasting, statistical model forecasting and artificial intelligence forecasting, etc.; physical model forecasting methods have good results for long-term forecasting (3-10 days), but for ultra-short-ter...

AI Technical Summary

Problems solved by technology

[0003] Existing new energy forecasting methods include physical model forecasting, statistical model forecasting and artificial intelligence forecasting, etc.; physical model forecasting methods have good results for long-term forecasting (3-10 days), but for ultra-short-term forecasting (0-4 hours) The effect is not good; the short-term prediction effect of the statistical model prediction method is better; but it is not suitable for long-term prediction because of its lack of learning ability; the artificial intelligence prediction method is suitable for short-term and long-term prediction, including multiple linear regression algorithm, artificial neural network (ANN ) algorithm, support vector machine (SVM) algorithm, but in the case of sudden weather changes, the prediction error of these methods is relatively large

Images