• Miss. Priti Dinkar Marke
• Dr. Mirza Ansar Beg
• Prof. Manishkumar M. Tayade
• Prof. Trishul G. Bharsakale

The rapid growth of distributed renewable energy has positioned campus microgrids as a significant model for clean, resilient, and cost-effective power systems. Solar photovoltaic (PV) generation is an attractive option; however, its intermittency introduces uncertainty that challenges reliable microgrid operations. This research proposes an integrated framework for day-ahead and short-term forecasting of solar generation combined with optimal scheduling of storage systems and campus electrical loads. Forecasting leverages machine learning (ML), weather features, and time-series modeling to improve prediction accuracy. Scheduled dispatch ensures peak shaving, demand shifting, efficient battery cycling, and enhanced renewable utilization. The framework demonstrates improvements in operational reliability, reduced grid dependency, and enhanced energy efficiency, establishing an intelligent approach to sustainable energy planning for academic institutions.

Solar Forecasting, Microgrid Scheduling, Machine Learning, Renewable Energy, Load Management.

"FORECASTING AND SCHEDULING RENEWABLE ENERGY FOR A CAMPUS MICROGRID", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 12, page no.d484-d488, December-2025, Available :http://www.jetir.org/papers/JETIR2512359.pdf

"FORECASTING AND SCHEDULING RENEWABLE ENERGY FOR A CAMPUS MICROGRID", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 12, page no. ppd484-d488, December-2025, Available at : http://www.jetir.org/papers/JETIR2512359.pdf