Construction of a Sustainable Development-Oriented Business Evaluation System for New-Type Power Systems

The world-wide development of sustainable energy requires immediate expansion of new energy infrastructure through renewable energy technologies together with smart grids systems. Due to its multi-dimensional characteristics the industry proves hard to evaluate because environmental and social aspects merge with economic and technological considerations. The solution aims to develop an ML-based AI system for sustainable business evaluation which ranks new-type power system companies. The system provides decision-makers alongside investors and regulators with an integrated data-based solution which enables them to assess and analyze sustainability performances of these firms. The examination collects basic information from utilities through their environmental reports along with their financial performance indicators along with their technological innovation indicators and social benefit scores. Standardization combined with outlier handling measures serve as preprocessing techniques to assure that data remains of high quality. The process includes feature extraction together with linear Discriminant Analysis (LDA) for identifying essential sustainability performance indicators which include carbon offsetting measures along with energy efficiency metrics and scalability aspects. The scalable shuffled frog leaping algorithm-adapted logistic regression (SSFLA-LR) model serves well due to its data handling abilities of high dimensions and its output interpretability. The sustainability evaluation model using SSFLA-LR runs on Python 3.9 shows efficient results in identifying high sustainability potential companies through their displayed environmental and social and economic metrics. With 5-fold cross-validation SSFLA-LR yields accuracy of 94.0% and precision of 93.12% together with a recall of 94.40% and an F1 Score of 93.74%. The proposed AI evaluation method provides an effective method to analyze business enterprise performance in emerging power networks that drives sustainable development.