Machine Learning Based Predictive Techno-Economic Analysis of Power System

This paper proposes a predictive techno-economic analysis in terms of voltage stability and cost using regression-based machine learning (ML) models effectiveness the is validated. Predictive power system proposed to address need for faster accurate analyses that would aid operation control modern system. Several methods including metaheuristic optimization algorithms, artificial intelligence techniques algorithms are being developed used. ML two modified IEEE 14-bus IEEE-30 bus systems, integrated with renewable energy sources (solar wind) reactive compensative device (STATCOM) features include hour day, solar irradiation, wind velocity, dynamic grid price load. An hour-wise input database model development generated from monthly average data daily curves normally distributed standard deviations. The feasibility tests output generation performed MATLAB. Linear higher order polynomial regression 8760hr Python 3.0 JupyterLab best-fit identified by analysing coefficients determination. were tested 24hr profile. results obtained comparison expected values furnished. Prediction outputs test validate accuracy model.