A Data-Driven Energy Router Modeling and Optimal Control Method

Abstract

The invention provides a data-driven energy router modeling and optimization control method, which divides the power data corresponding to the ports of the energy router into two types: load demand set and scheduling set, and collects the electrical data of each port when the energy router is running. After obtaining enough data samples, the mathematical mapping model between the two types of ports is established online using data mining technology as a constraint on the power relationship between ports. At the same time, the mathematical constraint forms corresponding to different optimization modes are established, the optimal scheduling mode of the energy router is transformed into an index optimization problem with constraints, and the group optimization algorithm is called to obtain optimal scheduling parameters. Then establish a data-driven model between the optimal optimal scheduling parameters and the demand load, so as to realize the real-time optimal control of the energy router under different operating loads. It has high portability and high real-time optimization capabilities, and can be used to improve various Operational performance indicators of energy routers.

Description

technical field [0001] The invention belongs to the technical field of micro-grids, and in particular relates to a data-driven energy router modeling and optimization control method. Background technique [0002] Due to the decreasing reserves of traditional non-renewable energy, and the use of non-renewable energy will have a negative impact on the global environment, in recent years, low-carbon, environmentally friendly and sustainable new energy power generation (such as wind power, photovoltaic power generation) has gradually become one of the important forms of power generation. one. However, compared with traditional power generation methods, new energy power generation methods have the characteristics of intermittency, volatility, uncertainty, and distribution, and their massive access poses new challenges to the operation and control of distribution networks. The centralized power generation mode is transformed into a distributed and centralized power generation mod...

AI Technical Summary

Problems solved by technology

Among them, the optimal scheduling method is mainly divided into two categories: the first category is to obtain the physical model between each node with a clear mechanism through the analysis of the internal power electronics topology of the energy router, and combine the physical model to refine it to the internal nodes. However, this method relies on a complete understanding of the internal structure of the energy router, has poor portability, and is greatly affected by changes in system parameters; the second type is to directly collect the data of each port, according to a certain The optimization index or mode of the energy router is used to schedule each port without the internal parameters and mechanism model of the energy router. Adjustment speed is slow

Images