Snow identification method and system for photovoltaic power station based on multi-source fusion and hierarchical lag

By using a time-series state machine with multi-source data fusion and a hierarchical lag-holding mechanism, the snow accumulation status of photovoltaic power plants is identified, solving the problems of high false alarm rate and hardware dependence in existing technologies, and achieving efficient and accurate snow accumulation monitoring.

CN122332771APending Publication Date: 2026-07-03BEIJING HUANENG XINRUI CONTROL TECH
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
BEIJING HUANENG XINRUI CONTROL TECH
Filing Date
2026-03-18
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

Existing methods for monitoring snow accumulation in photovoltaic power plants rely on a single threshold, resulting in a high false alarm rate. They cannot accurately determine the end time of snow accumulation events and require additional hardware or manual intervention, while ignoring the lag effect of snow melting.

Method used

By fusing multi-source data, the gain attenuation index and voltage deviation are calculated. Combined with a time-series state machine with a graded hysteresis hold mechanism, the inefficient state of the inverter is identified, the inefficiency ratio coefficient at the site level is generated, the snow accumulation status is determined by combining the ambient temperature, and time-domain filtering is performed to verify and generate a snow accumulation event report.

Benefits of technology

It improves the accuracy of snow accumulation identification, avoids misjudgment due to single device failure, reduces hardware costs, is suitable for promotion in existing power plants, and solves the problem of judgment jitter in critical states of traditional methods.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122332771A_ABST
    Figure CN122332771A_ABST
Patent Text Reader

Abstract

This disclosure provides a method and system for identifying snow accumulation in photovoltaic power plants based on multi-source fusion and hierarchical lag. The method includes: collecting numerical weather forecast data, environmental monitoring data, electrical operation data, and physical mechanism data to construct a multi-source feature dataset; calculating the gain attenuation index and voltage deviation of each inverter to form snow accumulation feature indicators; identifying the inefficient state of a single inverter based on these indicators, and statistically calculating the proportion of inefficient inverters across the entire plant to generate a plant-level inefficiency proportion coefficient; inputting this coefficient into a time-series state machine with a hierarchical lag holding mechanism, and combining it with ambient temperature to determine the snow accumulation state of the photovoltaic array; finally, performing time-domain filtering verification on the snow accumulation state sequence to generate a snow accumulation event report. This invention requires no additional hardware and effectively solves the problems of high false alarm rate and fluctuating state during the snow melting period in existing technologies by utilizing plant-level statistical features and hierarchical lag logic, achieving accurate identification and quantitative assessment of snow accumulation events.
Need to check novelty before this filing date? Find Prior Art