Ashraf, Waqar Muhammad; Dua, Vivek; (2024) Driving towards net-zero from the energy sector: Leveraging machine intelligence for robust optimization of coal and combined cycle gas power stations. Energy Conversion and Management , 314 , Article 118645. 10.1016/j.enconman.2024.118645.

Preview

Text Ashraf_1-s2.0-S0196890424005867-main.pdf Download (9MB) | Preview

Abstract

The fossil-based power stations using coal and natural gas are envisioned to support the peak energy demand for the planning of net-zero energy-mix in different economies around the globe. However, the operation optimization of the fossil-based power systems, which is quite challenging, can significantly reduce the emissions discharge to further support the net-zero goal. Herein, we present the data-driven robust optimization framework built on machine learning and two-step robust optimization approach for the operation optimization of the coal and combined cycle gas power stations. The Data Information integrated Neural Network (DINN) models are trained using the operation data of the coal and gas power stations with modelling accuracy more than 0.85 to predict thermal efficiency, power and heat rate of the power stations, and are also validated on the plants’ operation with good accuracy. The model-driven variables significance analysis reveals that steam cycle-based variables have the percentage significance of 79 %, 74 % and 66 %, while gas turbines have the percentage significance of 85 %, 93 % and 78 % towards the thermal efficiency, power and heat rate of coal and combined cycle gas power plant respectively. The two-step robust optimization analysis is carried out to estimate the robust optimal solution at different generation capacities of the two power stations. The optimization driven results are verified on the plants’ operation and improved power stations’ performance is achieved that leads to the highest annual reduction in CO2 measuring 200 ± 10 kt and 62 ± 20 kt respectively corresponding to mid-load capacity generation operation of the coal and combined cycle gas power station. The machine intelligence and optimization approach synergized by domain knowledge of the plants operation can significantly contribute to enhance the performance of the power complexes that supports the net-zero objective from the energy sector.

Download activity - last month

Export as CSVXMLJSON

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as JSONCSVXML

Archive Staff Only

View Item