Photovoltaic power climbing event imprecise probability prediction method and system considering daily periodic influence

Abstract

The invention discloses a photovoltaic power climbing event inaccurate probability prediction method and system considering daily periodic influence, and the method comprises the steps: obtaining theoutput power data of a photovoltaic power station and the meteorological data of the position of the photovoltaic power station, and enabling the data to serve as sample data; constructing a reliability network node variable set and a state set of each node variable; constructing an optimal credibility network structure for photovoltaic power generation climbing prediction under the sample data byusing a greedy search algorithm; counting the prior probabilities of different climbing states in the historical data, estimating the inaccurate condition probability associated with each credibilitynetwork node by using the IDM, and constructing a condition credibility set; and performing reliability network probability reasoning of photovoltaic power generation climbing to obtain an inaccurateprediction result of the photovoltaic power climbing probability under a given meteorological condition. The probability prediction error caused by insufficient climbing event samples can be effectively avoided, and more comprehensive decision information is provided for power grid operation scheduling.

Description

technical field [0001] The present invention relates to the technical field of photovoltaic power ramp events, and in particular to an inaccurate probability prediction method and system for photovoltaic power ramp events considering the influence of daily periodicity. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] In recent years, the rapid development of renewable energy power generation and its penetration rate in the power grid have continued to increase. While effectively alleviating environmental pollution and resource crises, it also poses challenges to the safe and stable operation of the power grid due to its inherent randomness and volatility. In particular, the power ramp event of photovoltaic power plants, that is, large fluctuations in output power in a short period of time, may cause damage to the power balance of the grid, ...

AI Technical Summary

Problems solved by technology

[0007] Aiming at the problem of inappropriate alarms in the existing forecast of photovoltaic power ramp events, the present invention proposes a method and system for inaccurate probability prediction of photovoltaic power ramp events considering the influence of daily periodicity, which can effectively avoid insufficient samples of ramp events. The resulting probability prediction error provides more comprehensive decision-making information for power grid operation scheduling

Images