A method for identifying the effective accuracy of reservoir dispatching forecast information based on data mining

Abstract

The invention discloses a reservoir scheduling forecast information effective precision identification method based on data mining. The reservoir scheduling forecast information effective precision identification method comprises steps of adopting a dynamic planning method to obtain an optimal scheduling locus of the reservoir, performing disturbance on forecast information according to a given error level to generate forecast information according with the given error level, adopting a random forest method to establish a mapping relation between the reservoir optimal scheduling locus and a decision variety and forecast information, which is a random forest decision three; counting the related decision variety according to the random forest decision three; and gradually increasing an error level and repeating the above-mentioned steps, wherein a previous error level is an effective precision when forecast information does not exist in the obtained related decision variety. The invention can effectively identify effective forecast precision beneficial for reservoir optimization scheduling, can fully excavate useful forecast information and provides a reference basis which is more simple and strong in operability to the reservoir scientific decision.

Description

technical field [0001] The invention belongs to the technical field of reservoir dispatching, and relates to a method for identifying the effective accuracy of reservoir dispatching forecast information based on data mining. Background technique [0002] Reservoirs, as water conservancy structures for retaining flood water and regulating water flow, usually have functions such as irrigation, power generation, and flood control, and play an important role in making water resources more suitable for the development of human society and maintaining the ecological environment. Optimal scheduling considering future forecast information can effectively improve the benefits of the reservoir system, but the forecast information often contains uncertainty, which leads to scheduling risks and loss of benefits, and information with different forecast accuracy has different impacts on reservoir scheduling. How to identify the effective accuracy that can guide reservoir decision-making, ...

AI Technical Summary

Problems solved by technology

[0006] Existing forecast accuracy assessment methods only consider the difference between forecast information and measured values, but do not consider its impact on reservoir operation

However, the current reservoir scheduling methods often directly use the forecast results that meet a certain accuracy, and do not make full use of the existing information. Therefore, it is necessary to identify effective forecast information in combination with reservoir scheduling.

Images