Comprehensive data analytics approach for the assessment of Indian thermal power plants
摘要
Thermal power plants remain the backbone of India’s electricity system, contributing a major share to the national grid. Differences in technology, year of commissioning, plant capacity, and day-to-day operational practices create noticeable gaps in performance across regions. The present work attempts to provide nationwide data integrated assessment of thermal power plants in India. The raw data taken from Central Electricity Authority (CEA) and the National Power Portal consisting of 60-year dataset having 2785 units with an installed capacity greater than 244.24 GW was cleaned and standardized using Python, and examined with a mix of descriptive statistics, correlation analysis, and visualizations. The results reveal clear patterns. The Western region has got highest installed capacity (95,277.49 MW) followed by North (55,819.96 MW), Southern (52,803.34 MW), Eastern (37,889.71 MW), and North Eastern Region (2450.96) regions. The percentage contribution of sector-wise installed capacity follows the order: Private sector (34.9%) followed by State sector (32.8%) followed by Central Sector (32.3%). Amongst 20 players generating thermal power, National Thermal Power Corporation (NTPC) is dominant in terms of its installed capacity (54,387 MW). Installed capacity versus prime mover showed the dominance of steam-based power plants (219,083 MW). Future studies could build on this work by incorporating real-time plant data, detailed fuel quality assessments, and environmental impact measures to deliver even more accurate and applicable evaluations.