Statistical Machine Learning Model for Distributed Energy Planning in Industrial Park

Abstract

With the advancement of industrial modernization, industrial parks have become the main body of new energy production and consumption. However, due to the large demand for energy in industrial agglomeration, the way of energy utilization is changing to sustainable. The direct connection of distributed energy resources in industrial parks, including photovoltaic (PV) power generation systems, has an important impact on its planning and operation. Furthermore, weather scenarios can have an impact on distributed PV generation, and the uncertainty in PV power output will, in turn, affect the uncertainty in industrial park planning. Therefore, this paper aims to address the issues of inaccurate prediction of distributed electricity generation during the planning period and the non-uniform distribution of energy resources such as electricity, heating, and cooling. This is achieved through the application of statistical machine learning (SML). This paper intends to incorporate the ideas of SML into the model for industrial park distributed energy random opportunity-constrained planning, aiming to resolve the problems of non-uniform distribution of distributed energy sources within the park, along with uncertainty in their outputs and high overall investment costs. The model takes the planning, construction, and operating costs of the industrial park as the objective function, uses the lost load cost to ensure the safety of the industrial park, and uses the Chebyshev’s inequality probability to limit the output characteristics of distributed energy equipment. In terms of operation, the planning period is subdivided into heating period, cooling period, and transition period, and the balance of electricity, heat, and cold is considered. Finally, an actual example of an industrial park is used to verify the effectiveness of this method. Experimental validation shows that this approach can ensure safety requirements in industrial parks during the heating season, cooling season, and transitional periods by flexibly adjusting the confidence threshold. Simultaneously, it delivers significant economic benefits.

Received: 29 October 2023 | Revised: 2 January 2024 | Accepted: 11 January 2024

Conflicts of Interest

The authors declare that they have no conflicts of interest to this work.

Data Availability Statement

The data that support the findings of this study are openly available at http://doi.org/10.5281/zenodo.10609094.

Author Contribution Statement

Xiurong Zhang: Conceptualization, Methodology, Formal analysis, Investigation, Resources, Writing - review & editing, Supervision, Project administration, Funding acquisition. Chen Zhang: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data curation, Writing - original draft, Visualization. Xianping Wu: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data curation, Writing - original draft, Visualization. Saddam Aziz: Resources, Supervision, Project administration, Funding acquisition.