AI-coherent data-driven forecasting model for a combined cycle power plant. (15th June 2023)

• Record Type: Journal Article
• Authors: Danish, Mir Sayed Shah; Nazari, Zahra; Senjyu, Tomonobu
• Is Part Of: Energy conversion and management. Volume 286(2023)
• Publication Date: 2023-06-15
• Subjects: Parameter-based models -- Data-driven-based models -- Quasi-Newton method -- Machine learning method -- Neural networks -- Energy efficiency -- Energy optimization -- Combined cycle power plant -- AI-powered energy system; Direct energy conversion -- Periodicals; Energy storage -- Periodicals; Energy transfer -- Periodicals; Énergie -- Conversion directe -- Périodiques; Direct energy conversion; Periodicals; 621.3105
• DOI: 10.1016/j.enconman.2023.117063
• Languages: English
• ISSNs: 0196-8904

Abstract

Highlights: AI model improved the CCPP efficiency by 2.23% by optimizing environmental control. A high goodness-of-fit of 94.46 % leads to a 12.1 MW increase in generation. Clean, organized data is vital to modeling data-driven systems. Systematic approach cuts emissions, boosts efficiency, improves cost-effectiveness. Abstract: This study investigates the transformation of energy models to align with machine learning requirements as a promising tool for optimizing the operation of combined cycle power plants (CCPPs). By modeling energy production as a function of environmental and control variables, this methodology offers an innovative way to achieve energy-efficient power generation in the context of the data-driven application. This study focuses on developing a thorough AI-coherent modeling approach for CCPP optimization, preferring an interdisciplinary perspective and coming up with a comprehensive, insightful analysis. The proposed numerical model using Broyden Fletcher Goldfarb Shanno (BFGS) algorithm enhances efficiency by simulating various operating scenarios and adjusting optimal parameters, leading to a high yield power generation of 2.23 % increase from 452 MW to 462.1 MW by optimizing the environmental factors. This study deals with data-driven modeling based on historical data to make predictions without prior knowledge of the system's parameter, demonstrating several merits in identifying patterns that can be difficult for human analysts to detect, high accuracy when trained on large datasets, and the potential to improve over time with new data. The proposed modeling approach and methodology can be expanded as a valuable tool for forecasting and decision-making in complex energy systems.