Wind-solar bus load self-adaptive prediction method and device and computer equipment

Abstract

The invention discloses a wind-solar bus load self-adaptive prediction method and device and computer equipment. The method comprises the steps of preprocessing load data of a wind-solar bus and corresponding meteorological data, performing mapping and normalization processing on the preprocessed load data of the wind-solar bus and the corresponding meteorological data, carrying out day and nightload segmentation integration prediction based on mode feature matchingon the mapped and normalized load data of the wind-solar bus and the corresponding meteorological data to obtain a final to-be-predicted day load prediction result, and according to the obtained final to-be-predicted day load prediction result, carrying out adaptive feature weight adjustment based on a particle swarm algorithmto predict the load of the wind-solar bus. By means of the mode, for the wind-solar bus with the distributed new energy, under the conditions that a distributed new energy prediction mechanism is incomplete and corresponding real-time prediction meteorological data is missing, self-adaptive prediction can be conducted on the wind-solar bus.

Description

technical field [0001] The invention relates to the technical field of power system bus load forecasting, in particular to a wind-solar bus load self-adaptive forecasting method, device and computer equipment. Background technique [0002] Accurate bus load forecasting plays an important role in the transmission capacity calculation of the power grid, power balance, operation plan arrangement, daily safety check and other links. The bus load is defined as the sum of the terminal loads supplied by the main transformer of the substation. Compared with the system load, the base of the bus load prediction is small, its stability is relatively weak, and the load changes quickly and the change trend is not obvious. It is difficult to achieve accurate prediction. In addition, with the rapid construction of distributed new energy in my country, the proportion of distributed new energy load in the power grid is gradually increasing, and the high intermittency, volatility and randomn...

AI Technical Summary

Problems solved by technology

In recent years, intelligent methods with strong self-learning and complex nonlinear function fitting capabilities have been widely used in the field of forecasting, and have also provided new ideas for forecasting methods based on the changing law of the bus load itself. Existing research includes the use of The hybrid method of fuzzy system and artificial neural network, the method of short-term bus load forecasting using aggregation model, and the hybrid forecasting method composed of auxiliary forecasting state estimation and multi-layer perceptron neural network, etc. The number and types of data have high requirements, and in the case of insufficient data or insufficient data, it is impossible to achieve better prediction results

Especially for the wind-solar bus with distributed new energy, the imperfect distributed new energy forecasting mechanism and the lack of corresponding real-time forecast meteorological data make the currently widely used intelligent forecasting algorithm unable to apply to the wind-solar bus under this situation predict

Images