Robust-regression-based distributed photovoltaic generating electricity-stealing identification method

Abstract

The invention discloses a robust-regression-based distributed photovoltaic generating electricity-stealing identification method. The method comprises the following steps: (1), establishing a historical information database; (2), carrying out determination and filtering on abnormal data existing in historical data; (3), carrying out processing by using a robust regression model algorithm to obtain an irradiation power curve; (4), carrying out operation to obtain a corresponding photovoltaic generation power; (5), carrying out calculation to obtain a theoretic generating capacity; and (6), carrying out determination. The method has the following beneficial effects: (1), with the robust regression model algorithm, the influence on the model precision by the abnormal data can be reduced and concrete modeling of a photovoltaic system inversion model and a photovoltaic conversion model can be avoided; and (2), electricity-stealing suspicion determination is carried out based on three-layer screening architecture, so that accuracy of abnormal determination of the photovoltaic electric quantity and the electricity-stealing determination reliability are high and the electricity-stealing checking pertinency is improved.

Description

technical field [0001] The invention relates to a method for identifying electricity theft in distributed photovoltaic power generation based on robust regression, and belongs to the technical field of photovoltaic power generation monitoring. Background technique [0002] At present, common distributed photovoltaic power generation stealing methods include mains rectification and inverter method, mains reconnection method, photovoltaic meter boosting method, and photovoltaic meter boosting method. The mains rectification and inverter method directly uses the rectifier device to rectify the mains into DC, and connects it in parallel to the DC side of the photovoltaic power generation system, and converts it into AC power for the grid through the photovoltaic grid-connected inverter. Using this solution, users can directly use the rectifier device to pretend to be a photovoltaic cell module to generate electricity without installing a photovoltaic cell panel. Mains reconnect...

AI Technical Summary

Problems solved by technology

There are certain deficiencies in this monitoring method. First of all, when this method predicts photovoltaic power, it needs to comprehensively consider the influence of photovoltaic cell loss, inverter loss and AC side grid-connected loss on photovoltaic output power. The photovoltaic cell loss includes battery temperature characteristics Loss, module matching loss, photovoltaic module surface dust loss, photovoltaic cell aging loss and DC line loss, inverter loss includes maximum power tracking energy loss and inverter process loss, AC side grid connection loss includes AC line loss and transformer loss

Since there are many factors affecting the grid-connected output power of photovoltaic power generation, there must be certain calculation errors in the photovoltaic power predicted by this method.

Secondly, this method uses the instantaneous output power as the basis for judging whether to steal electricity or not. There may be a physical deviation between the meteorological sampling time and the power sampling time, resulting in the inconsistency between the calculated power and the sampling power time. If the interval is not selected properly, would lead to misjudgment

Images