Energy Efficiency Assessment and Prediction Based on Indicator System, PSO + AHP − FCE Model and Regression Algorithm.

Energy-intensive enterprises lack a scientific and effective energy efficiency assessment framework and methodology. This lack leads to an inaccurate understanding of energy usage and its benefits. As a result, there is energy wastage and loss. This wastage and loss negatively affect product costs. They also present a challenge to effective energy management. To address these issues, this paper introduces a novel, comprehensive energy efficiency evaluation system. This system integrates both qualitative and quantitative measures. It proposes an evaluation model based on the Particle Swarm Optimization (PSO) combined with the Analytic Hierarchy Process (AHP) and Fuzzy Comprehensive Evaluation (FCE), wherein PSO is employed to optimize the weights determined by AHP, ensuring that the significance attributed to various indicators is scientific, objective, and rational. The FCE method is utilized to convert diverse factors affecting corporate energy efficiency, across different types and scales, into standardized 0–1 values, enabling a comparative analysis of the impact of each process and indicator on energy efficiency. Furthermore, the paper introduces an energy efficiency prediction model employing a multivariate linear regression algorithm, which demonstrates a good fit, facilitating the transition from retrospective energy efficiency evaluation to proactive improvements. Utilizing data on actual consumption of water, electricity, and steam from an enterprise, along with expert assessments on the implementation levels of new processes, technologies, equipment, personnel scheduling proficiency, steam recovery rates, and adherence to policies and assessments, a simulation experiment of the proposed model was conducted using Python. The evaluation yielded an energy efficiency score of 0.68; this is consistent with the real-world scenario of the studied enterprise. The predicted mean square error of 9.035416039503998 ×   10 − 9 indicates a high model accuracy, validating the practical applicability and effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]