Hydropower station risk assessment method based on multi-core parallel runoff probability density prediction

Abstract

The invention discloses a hydropower station risk assessment method based on multi-core parallel runoff probability density prediction. The method comprises the steps: 1, acquirig and preprocessing runoff and related feature data; 2, arranging the preprocessed data sets by using a rolling prediction method, and dividing the data sets into a training set and a test set; 3, constructing an MPRVFL model of the multi-core parallel random vector function chain network, averagely dividing a training set, and respectively carrying out parallel training on the model; 4, substituting the test set intothe trained MPRVFL model, and performing probability density prediction on the obtained conditional quantile to obtain a prediction result and a corresponding probability; and 5, grading runoff probability density prediction results, counting the number of abandoned water and load tasks which cannot be completed in the runoff probability density prediction results, and calculating corresponding risk probabilities. Computer idle resources are fully utilized, the running efficiency of the model is further improved while the runoff prediction precision is improved, and therefore a decision basiscan be provided for long-term hydrological prediction in runoff.

Description

technical field [0001] The invention belongs to the field of hydropower energy optimization, and specifically relates to a hydropower station risk assessment method based on multi-core parallel runoff probability density prediction. Background technique [0002] The utilization and development of water resources is conducive to promoting social and economic development, improving the structure of energy consumption, and slowing down the environmental pollution caused by the consumption of coal, oil and other resources. In the development and utilization of water resources, runoff prediction and risk assessment of hydropower stations are important issues. Accurate and reliable runoff prediction and hydropower station risk assessment are effective means and key links to optimize the allocation of water resources, realize the rational operation of the power grid, and obtain economic benefits. Because runoff is affected by natural conditions such as precipitation, landform, and...

AI Technical Summary

Problems solved by technology

[0004] Existing runoff forecasting methods need to collect more basic data, the increasingly complex models are time-consuming to solve, and the computational cost becomes a constraint for runoff forecasting

In addition, most runoff prediction models in the past are deterministic prediction models, which can only obtain point prediction results of runoff, and it is difficult to reflect the influence of uncertain factors on runoff volatility

Images