Energy storage micro-grid cooperative scheduling method based on photovoltaic prediction and related equipment

By fusing historical photovoltaic power generation data with meteorological sensor data and applying photovoltaic output prediction models, combined with energy storage system status assessment, and dynamically adjusting scheduling decision parameters, the problem of insufficient transmission of uncertain photovoltaic output information in energy storage microgrids was solved, and the energy flow coordination balance and stable operation of microgrids were achieved.

CN122456478APending Publication Date: 2026-07-24HENGKAI ELECTRIC CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
HENGKAI ELECTRIC CO LTD
Filing Date
2026-06-22
Publication Date
2026-07-24

AI Technical Summary

Technical Problem

Existing energy storage microgrid dispatching methods cannot effectively transmit the uncertainty information of photovoltaic output prediction, resulting in frequent over-limits of energy storage systems or power imbalances in grid interaction under scenarios with large fluctuations in photovoltaic output, making it difficult to ensure the stable operation of the microgrid.

Method used

By fusing historical photovoltaic power generation data with meteorological sensor data, a feature dataset is generated. A pre-trained photovoltaic power output prediction model is used to predict photovoltaic power output, resulting in a result that includes the predicted value and confidence interval. The result is then combined with the energy storage state of charge, grid interaction margin, and load demand for comprehensive evaluation. The scheduling decision parameters are dynamically adjusted to achieve coordinated energy flow allocation among photovoltaic arrays, energy storage systems, local loads, and the grid.

Benefits of technology

In scenarios with fluctuating photovoltaic output, it ensures the coordinated balance and stable operation of microgrid energy flow, avoids the disconnect between prediction results and scheduling decisions, and realizes adaptive adjustment of scheduling schemes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122456478A_ABST
    Figure CN122456478A_ABST
Patent Text Reader

Abstract

The application provides a kind of energy storage microgrid collaborative scheduling method based on photovoltaic prediction and related equipment, the method comprises: the fusion processing of photovoltaic power generation historical data and meteorological sensor data is obtained feature data set;Photovoltaic output prediction is carried out to the pre-trained photovoltaic output prediction model, and the photovoltaic output prediction result containing prediction value and confidence interval is obtained;According to photovoltaic output prediction result and confidence interval, the state of charge of energy storage, grid interaction margin and load demand are comprehensively evaluated, and dynamic scheduling decision parameter is obtained;According to dynamic scheduling decision parameter, the energy flow between photovoltaic array, energy storage system, local load and grid is collaboratively distributed, and scheduling execution scheme is obtained.The uncertainty information of photovoltaic output prediction is introduced into the scheduling decision process, and the collaborative balance and stable operation of microgrid energy flow are guaranteed in the photovoltaic output fluctuation scene.
Need to check novelty before this filing date? Find Prior Art