Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195013,
        author = {Harshad Rajesh Kharat and Koushal Ravindra Khichade and Bhushan Rajendra Sawant and Gayatri Deepak Malani and Umesh Anandrao Patil},
        title = {Climate Based Energy Consumption Prediction},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {8260-8265},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195013},
        abstract = {Energy consumption has become a major concern for large institutions such as universities, where multiple facilities including classrooms, laboratories, hostels, libraries, and administrative buildings require continuous electricity supply. Efficient energy management is essential to reduce operational costs and support sustainable campus development. However, traditional energy forecasting methods rely on basic statistical approaches and are unable to capture the complex relationships between environmental factors and energy usage. This project, titled “Climate Based Energy Consumption Prediction,” proposes a machine learning- based approach to accurately predict energy consumption using historical data and environmental parameters. The system considers key factors such as temperature, humidity, wind speed, rainfall, solar radiation, and time-based features to analyze energy consumption patterns in a university environment.
The proposed system implements two machine learning models to improve prediction accuracy. The Random Forest Regressor is used for predicting hourly energy consumption based on environmental conditions, while the XGB Regressor is used for forecasting energy usage over a selected future time period using historical time-series data. The system is developed using Python and Flask and includes a web-based dashboard that provides graphical visualization of energy trends and prediction results. The results demonstrate high prediction accuracy, with strong performance metrics such as high R² scores, indicating the effectiveness of the proposed approach in capturing energy consumption patterns. This system helps university administrators make informed decisions regarding energy planning, reduces electricity wastage, and supports sustainable energy management.
Overall, the proposed system shows how machine learning and data analytics can be effectively applied to develop intelligent energy prediction solutions for smart university campuses.},
        keywords = {Assistive Technology, Voice-Input Programming, Web Speech API, Large Language Models, Python Code Generation, Digital Inclusion, Software Accessibility, Flask Web Framework, Natural Language Processing, Speech Recognition Systems, AI-Assisted Programming.},
        month = {March},
        }