Load-intensive urban smart park demand aggregation modeling method

Abstract

The invention discloses a load-intensive urban smart park demand aggregation modeling method, which starts with a database structure and a data source form of an energy management platform in a smartpark, proposes an original data integration and selection method, and extracts an energy consumption data set needing to be mined and processed. On this basis, a load-intensive urban smart park demandaggregation original data processing method is provided, energy consumption data of the load-intensive urban smart park is processed, and the utilization efficiency of the data is improved by processing, recognizing and correcting bad source data; then, energy consumption characteristics of the load-intensive urban smart park demand data are mined by applying a fuzzy clustering technology, and aload-intensive urban smart park demand aggregation model is established; by applying the result of demand aggregation modeling to park energy optimization scheduling, load optimization operation of multiple types of users in the load-intensive urban smart park can be realized, and thus the overall energy efficiency of the smart park is improved.

Description

technical field [0001] The invention relates to the technical field of energy comprehensive utilization, in particular to the energy comprehensive utilization of load-intensive urban smart parks, and in particular to a demand aggregation modeling method for load-intensive urban smart parks. Background technique [0002] At present, end users on the energy demand side of load-intensive urban smart parks have gradually become a collection of energy storage, combined cooling, heating and power supply, and loads. They have certain self-energy coordination capabilities. Load-intensive urban smart parks There are mainly three typical end users: industrial users, public institutions and data centers, each of which has different energy-consuming equipment and characteristics, which are specifically reflected in the following three aspects: [0003] (1) There are obvious differences in the characteristic curves of various typical end-user cooling, heating and electrical loads. The l...

AI Technical Summary

Problems solved by technology

[0004] (2) There are differences in various typical end-user energy supply equipment and energy supply forms

(3) There are differences in the solution methods of the coordinated control model for different end-user energy optimization utilization

[0009] (2) There are differences in various typical end-user energy supply equipment and energy supply forms

(3) There are differences in the solution methods of the coordinated control model for different end-user energy optimization utilization

[0011] There are many types of end users in load-intensive urban smart parks, such as industrial users, public institutions, residential users, and data centers. They have different energy-consuming equipment and characteristics, and data storage and sources are different. From the perspective of the entire park cluster control for these users poses great difficulties

Images