Intra-day optimization operation strategy for providing stacking service through load side energy storage

Abstract

The invention relates to an intra-day optimization operation strategy for providing stacking service by load side energy storage. A 'look-ahead-value function approximation' mixed intra-day operation strategy of an online rolling optimization two-stage robust approximation dynamic programming model is provided and can optimize a power reference point in real time in a finite time window. In a day-ahead stage, a post-decision state approximate value function is introduced by applying an approximate dynamic programming thought so as to represent long-term expected net benefits in different time period states, and offline training is carried out on the approximate value function by utilizing a differential learning algorithm. In the intra-day operation process, the online rolling optimization two-stage robust approximation dynamic programming model dynamically obtains the power reference point of each time period on the basis of the rolling update prediction of the electricity price and the load, a frequency uncertainty set and a long-term time domain approximate value function. The strategy provided by the invention not only can effectively guarantee the frequency regulation capability of the load side energy storage, but also can quickly evaluate the long-term influence of real-time decision through the offline training-online application mode of the approximate value function, and well balance global economic benefits and online operation overhead.

Description

technical field [0001] The invention belongs to the field of operation control of battery energy storage systems, and relates to an intraday optimal operation strategy for load-side energy storage to provide stacking services. Background technique [0002] With the establishment and improvement of the power market system and the rapid improvement of battery technology performance, the number and scale of load-side energy storage have increased significantly. Load-side energy storage can effectively reduce the power purchase cost of power users by responding to the real-time electricity price in the market and "low storage and high discharge". Due to the relatively high cost of energy storage batteries, the economic benefits of the above-mentioned single application mode are usually difficult to balance the initial investment cost. If considering the flexible participation in the power auxiliary service market on the basis of electricity price response, it will help to tap i...

AI Technical Summary

Problems solved by technology

The SMPC online rolling optimization two-stage robust-stochastic optimization model, although taking into account the random stage can expand the optimization time domain and improve operational efficiency, it also makes the problem solving scale too large, making it difficult to meet the optimization time limit requirements

Images