Smart Building Dataset on Thermal Comfort and Energy Use in 100-Seat Lecture Rooms for Hot and Dry Climate of Rajasthan (Jaipur)

The  current dataset has been developed to support research in energy optimization and intelligent control of smart buildings under extreme climate conditions. The data was collected from two university lecture halls in Jaipur, India, each designed to accommodate 100 students, and represents the hot and dry climatic characteristics of the region. To capture the influence of air-conditioning (AC) operation on both energy consumption and indoor comfort, the dataset is divided into two scenarios: one with AC in operation and the other without AC. For each condition, both daily and hourly measurements were recorded across a full year, resulting in a data span of 365 daily entries and 365 \u00d7 24 hourly entries for each file. The thermal comfort data are stored in separate files, with variables including Date\/Time, Relative Humidity (%), Fanger PMV, Pierce PMV ET, Pierce PMV SET, Kansas University TSV, Air Temperature (\u00b0C), Operative Temperature (\u00b0C), Discomfort Hours (hrs), and Dry-Bulb Temperature (\u00b0C). These metrics provide comprehensive insights into human comfort perception by integrating both subjective comfort indices and objective temperature-related measurements. For instance, Predicted Mean Vote (PMV) and Thermal Sensation Vote (TSV) indices quantify comfort levels, while discomfort hours represent deviations from optimal indoor conditions.The energy consumption data are stored in distinct files for both daily and hourly formats. Variables include Lighting, Computer, Occupancy, Solar Gains through Windows, Zone\/System Sensible Cooling, and Total Latent Load. Daily values are expressed in kilowatt-hours (kWh), whereas hourly values are represented in kilowatts (kW). The dataset thus captures internal energy gains and system loads with respect to varying occupancy, solar exposure, and cooling requirements. Present dataset records lecture hall system load, including sensible cooling and total cooling (kWh daily, kW hourly), supporting smart building energy analysis under Jaipur\u2019s hot and dry climate.The present dataset contains six structured files: Daily and Hourly Thermal Comfort, Daily and Hourly System Load, and Daily and Hourly Internal Gains. The files are organized in a tabular format, making them compatible with standard data analytics and machine learning workflows. This dataset provides a unique opportunity for researchers to explore energy-thermal comfort trade-offs, develop nature-inspired intelligent optimization models, and design smart HVAC control strategies tailored for hot and dry climates. It is particularly relevant for studies on sustainable building design, energy-efficient operations, and climate-specific comfort modeling in educational infrastructures.