Smart grid classification and fuzzy neural network based natural gas load prediction method

Abstract

The invention discloses a smart grid classification and fuzzy neural network based natural gas load prediction method and relates to the technical field of short-term load forecasting technology. The smart grid classification and fuzzy neural network based natural gas load prediction method comprises performing correlation analysis through Matlab to confirm an input variable; establishing a smart grid with a horizontal coordinate and a vertical coordinate to be the data and the average temperature through processed history data; selecting history data which is similar to a to-be-predicted date through the smart grid to train and predict a prediction model; performing de-noising processing through wavelets and training and predicting fuel gas loads through a fuzzy neural network with high adaptivity in combination with the complexity and multi-exterior-factor influences of the fuel gas load prediction process, wherein a process of modifying model parameters through errors is added to a training process and accordingly improvement of the final prediction accuracy is facilitated. The smart grid classification and fuzzy neural network based natural gas load prediction method can provide forceful reference for natural gas dispatching and confirms to material and technological foundation of a market development demand.

Description

technical field [0001] The invention relates to the technical field of short-term load forecasting, in particular to a natural gas short-term load forecasting method based on intelligent grid classification and fuzzy neural network. Background technique [0002] Now, natural gas has become the third largest energy source in the world. my country is currently following the world situation and actively calling for the construction of an environment-friendly and resource-saving society. During this period, the planned demand for natural gas will double that of 2005. The annual consumption of natural gas will also rise from the current 40 billion cubic meters to 100 billion cubic meters, and by 2020, it will reach about 200 billion cubic meters. Therefore, the development of natural gas will definitely drive the rapid development of urban natural gas. Immediately afterwards, it faced a series of problems such as: replacement of urban gas sources, urban gas pipeline network plan...

AI Technical Summary

Problems solved by technology

However, there are great differences in the physical characteristics, storage methods, and transportation methods of natural gas and electricity. In terms of physical characteristics, the physical characteristics of natural gas mainly include liquid and gaseous states, so the impact of external conditions such as ambient temperature on natural gas load forecasting is far greater than that of natural gas. Impact on power load forecasting; in terms of storage methods, natural gas needs to be stored through pipelines, and if it is stored too much, it will cause excessive pressure in the pipeline and cause danger, and if it is too little, it will cause insufficient pressure to meet normal gas demand, while electricity is not used at all Storage; In terms of transportation, natural gas is transported through pipelines, so it cannot be transported through wires like electricity and can reach the destination in real time

The above characteristics of natural gas make gas load forecasting more difficult, so even though there are many more mature forecasting methods for power load forecasting, they are not applicable to natural gas load forecasting, and it is still necessary to find a load forecasting method that suits the characteristics of natural gas itself.

Images