A Dataset of the Operating Station Heat Rate for 806 Indian Coal Plant Units using Machine Learning

Abstract

India aims to achieve net-zero emissions by 2070 and has set an ambitious target of 500 GW of renewable power generation capacity by 2030. Coal plants currently contribute to more than 60\% of India's electricity generation in 2022. Upgrading and decarbonizing high-emission coal plants became a pressing energy issue. A key technical parameter for coal plants is the operating station heat rate (SHR), which represents the thermal efficiency of a coal plant. Yet, the operating SHR of Indian coal plants varies and is not comprehensively documented. This study extends from several existing databases and creates an SHR dataset for 806 Indian coal plant units using machine learning (ML), presenting the most comprehensive coverage to date. Additionally, it incorporates environmental factors such as water stress risk and coal prices as prediction features to improve accuracy. This dataset, easily downloadable from our visualization platform, could inform energy and environmental policies for India's coal power generation as the country transitions towards its renewable energy targets.

Figures (9)

• Figure 1: Geographical locations of the operating 806 Indian coal plant units in the research scope. The existing coal-fired power capacity consists of 157 GW from 704 subcritical units and 69 GW from 102 supercritical units
• Figure 2: Four steps to predict the operating SHR using ML models for the database
• Figure 3: Feature distributions of the unit-level characteristics (a) Plant ages at year 2020 (years) (b) Power capacity (MW) (c) Average load factor and (d) Station heat rate (MMBtu/MWh); The orange bars represent distributions of subcritical coal plants, and the blue bars represent distributions of supercritical coal plants karthik_ganesan_coal_2021
• Figure 4: Environmental and geographical prediction features: (a) Water stress level hofste_aqueduct_2019 (b) Coal prices karthik_ganesan_coal_2021 and (c) Power system regions iea_interregional_2020; The grey or shaded areas in the maps (a) and (b) mean that no data is available or no coal plants are built in the area.
• Figure 5: Three evaluation score ranking (MSE, MAE, and MAPE) for the SHR predictions of (a) Subcritical units and (b) Supercritical units. The scores of the top two best models are labeled to the right of the bar.