Inaccurate probabilistic prediction method and system for photovoltaic power ramp events considering daily periodicity

Abstract

The invention discloses an inaccurate probability prediction method and system for a photovoltaic power climbing event considering daily periodic influence, including: obtaining the output power data of a photovoltaic power station and the meteorological data of the location of the photovoltaic power station as sample data; constructing a reliability network The node variable set and the state set of each node variable; use the greedy search algorithm to construct the optimal reliability network structure of photovoltaic power generation climbing prediction under the sample data; count the prior probability of different climbing states in the historical data, and use IDM to estimate the The inaccurate conditional probability associated with degree network nodes is used to construct a conditional reliability set; the reliability network probabilistic inference of photovoltaic power generation ramp-up is carried out, and the inaccurate prediction result of photovoltaic power ramp-up probability under given meteorological conditions is obtained. The invention can effectively avoid probability prediction errors caused by insufficient samples of climbing events, and provide more comprehensive decision-making information 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