Electricity demand prosperity index construction method based on electric power big data

Abstract

The invention discloses an electricity demand prosperity index construction method based on electric power big data. The method comprises the following steps: 1, collecting monthly electric quantity data and monthly average temperature data; 2, screening monthly electric quantity data, and removing noise data; 3, converting the monthly electric quantity data after the noise data is removed into a standard synthesis speed increase; 4, selecting effective standard synthesis speed increase data through a principal component analysis method and serving as independent variables of a prediction model, and inputting the independent variables into the pre-constructed prediction model, wherein the output of the prediction model is the optimal prediction electric quantity speed increase; 5, dynamic air temperature correction: establishing a nonlinear model of monthly average air temperature data and standard synthesis acceleration, and correcting the optimal prediction electric quantity acceleration according to the average air temperature data in the next three periods; 6, checking a predicted electric quantity acceleration result; 7, compiling a synthesis index; and 8, outputting the power demand prosperity index. The method is higher in adaptive capacity and low in basic data requirement, and abnormal value judgment and processing do not need to be carried out.

Description

technical field [0001] The invention belongs to the technical field of electric power data analysis and forecasting, and in particular relates to a method for constructing an electricity demand prosperity index based on electric power big data. Background technique [0002] At present, the social and economic environment at home and abroad is extremely complex, "black swan" and "grey rhinoceros" incidents occur frequently, and there are a lot of uncertainties in electricity demand. The harsh external environment requires the power sector to respond to changes in electricity demand in a timely manner, study the law of electricity consumption, and grasp the direction of forecasting. By analyzing power data with high timeliness and accuracy, the value of data is deeply mined, which makes it possible to scientifically predict power demand. [0003] At present, most of the forecasting methods of electricity demand focus on learning past electricity data, constructing a relativel...

Images