Prediction matching and consumption control method of thermal storage electric boiler and clean energy

Abstract

Prediction matching and consumption control method of thermal storage electric boiler and clean energy, step 1, collect meteorological factor data and photovoltaic power station abandoned photovoltaic power data, and obtain training sample set after normalization processing, step 2, design including input layer, implicit layer and output layer of the fuzzy Bayesian neural network model, and select the excitation function, training function and learning function, step 3, the best network prediction model obtained is applied in the distributed photovoltaic power generation system to obtain information in different weather conditions. The amount of photovoltaic power station abandoned under the conditions of factors; Step 4, under the condition of predicting the photovoltaic power station abandonment, considering the economic performance indicators, by referring to the predicted photovoltaic abandonment amount, the combined operation of the photovoltaic power station and the thermal storage electric boiler can achieve the maximum benefit And the index with the greatest environmental benefit, promote the distributed thermal storage electric boiler to limit the consumption of photovoltaic power, and solve the problems of inflexible consumption, low consumption efficiency and insufficient consumption capacity.

Description

technical field [0001] The invention relates to the field of new energy consumption, in particular to the use of distributed thermal storage electric boilers to absorb new energy systems. Background technique [0002] my country is rich in solar energy resources, in addition to meeting the power generation needs of photovoltaic power plants, it also faces a large number of abandoned solar problems. The consumption of new energy is conducive to the energy saving of the power grid, improving economic benefits and promoting the long-term development of power enterprises. [0003] Due to the uncertainty of meteorological environmental information, geographical conditions, astronomy and other factors, the output of the solar photovoltaic power generation system is a random variable with non-stationary, instantaneous change and dynamic characteristics, with strong volatility, weak anti-interference ability, intermittent and Uncontrollable distributed energy sources with periodic ...

AI Technical Summary

Problems solved by technology

[0006] In view of the above existing problems, the present invention proposes a distributed heat storage electric boiler consumption clean energy system based on the fuzzy Bayesian neural network prediction model, which is to solve the existing inflexible consumption methods, low consumption efficiency and low consumption capacity. Insufficient problem

Images