Smart Green Energy Management for Campus - An Integrated Machine Learning and Reinforcement Learning Model

Aug 4, 2026

The growing need for energy efficiency and renewable integration drives sustainability efforts in modern campus environments. This work presents a smart green energy management system that combines a machine learning predictive model with reinforcement learning to optimize energy consumption and solar generation. Historical data from three campus buildings support short-term forecasting for both consumption and solar output. Results using XGBoost with RL achieve strong accuracy and are presented alongside a web-based interface for real-time monitoring and decision-making, reducing grid dependency.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages18

Reading Time45 min

AccessFree to download

Highlights

Main findings and implications

Abstract

Keywords

Introduction

San Jose State University SJSU ScholarWorks Faculty Research, Scholarly, and Creative Activity 2-1-2025 Smart Green Energy Management for Campus: An Integrated Machine Learning and Reinforcement Learning Model Charan Teja Madabathula San Jose State University Kunal Agrawal San Jose State University Vijen Mehta San Jose State University Swathi Kasarabada San Jose State University Sai Srimai Kommamuri San Jose State University See next page for additional authors Follow this and additional works at: [https://scholarworks.sjsu.edu/faculty_rsca](https://scholarworks.sjsu.edu/faculty_rsca) Recommended Citation Charan Teja Madabathula, Kunal Agrawal, Vijen Mehta, Swathi Kasarabada, Sai Srimai Kommamuri, Guannan Liu, and Jerry Gao. "Smart Green Energy Management for Campus: An Integrated Machine Learning and Reinforcement Learning Model" Smart Cities (2025) . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)smartcities8010030 This Article is brought to you for free and open access by SJSU ScholarWorks. It has been accepted for inclusion in Faculty Research, Scholarly, and Creative Activity by an authorized administrator of SJSU ScholarWorks. For more information, please contact [scholarworks@sjsu.edu](scholarworks@sjsu.edu). Authors Charan Teja Madabathula, Kunal Agrawal, Vijen Mehta, Swathi Kasarabada, Sai Srimai Kommamuri, Guannan Liu, and Jerry Gao This article is available at SJSU ScholarWorks: [https://scholarworks.sjsu.edu/faculty_rsca/5972](https://scholarworks.sjsu.edu/faculty_rsca/5972) 7.0 11.2 Article Smart Green Energy Management for Campus: An Integrated Machine Learning and Reinforcement Learning Model Charan Teja Madabathula, Kunal Agrawal, Vijen Mehta, Swathi Kasarabada, Sai Srimai Kommamuri, Guannan Liu and Jerry Gao Special Issue Big Data and AI Services for Sustainable Smart Cities Edited by Prof. Dr. Jerry Gao, Dr. Fanjing Meng, Dr. Iraklis Varlamis and Dr. Paul Townend [https://doi.org/10.3390/smartcities8010030](https://doi.org/10.3390/smartcities8010030) Article Smart Green Energy Management for Campus: An Integrated Machine Learning and Reinforcement Learning Model Charan Teja Madabathula 1, Kunal Agrawal 1, Vijen Mehta 1, Swathi Kasarabada 1, Sai Srimai Kommamuri 1, Guannan Liu 1, * and Jerry Gao 2, * Academic Editor: Pierluigi Siano Received: 11 November 2024 Revised: 22 January 2025 Accepted: 11 February 2025 Published: 13 February 2025 Citation: Madabathula, C.T.; Agrawal, K.; Mehta, V.; Kasarabada, S.; Kommamuri, S.S.; Liu, G.; Gao, J. Smart Green Energy Management for Campus: An Integrated Machine Learning and Reinforcement Learning Model. Smart Cities 2025, 8, 30 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)smartcities8010030 Copyright: © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by/4.0/](licenses/by/4.0/)) . 1 Department of Applied Data Science, San Jose State University, San Jose, CA 95192, USA; [charanteja.madabathula@sjsu.edu](charanteja.madabathula@sjsu.edu) (C.T.M.); [kunal.agrawal@sjsu.edu](kunal.agrawal@sjsu.edu) (K.A.); [vijen.mehta@sjsu.edu](vijen.mehta@sjsu.edu) (V.M.); [swathi.kasarabada@sjsu.edu](swathi.kasarabada@sjsu.edu) (S.K.); [saisrimai.kommamuri@sjsu.edu](saisrimai.kommamuri@sjsu.edu) (S.S.K.) 2 Department of Computer Engineering, San Jose State University, San Jose, CA 95192, USA * Correspondence: [guannan.liu@sjsu.edu](guannan.liu@sjsu.edu) (G.L.); [jerry.gao@sjsu.edu](jerry.gao@sjsu.edu) (J.G.) Highlights What are the main 􀀂ndings? 􀀏 A smart green energy management system integrating machine-learning model and reinforcement learning is proposed in this work to optimize e

FAQs

What does the proposed Smart Green Energy Management for Campus system optimize?

It optimizes energy consumption and solar generation for a campus setting using a combined machine learning and reinforcement learning approach.

How is the prediction model validated in the study?

The system is trained and evaluated using historical data from three campus buildings, with performance reported using metrics such as RMSE, MAE, and MAPE.

What solution is provided to support real-time campus energy decisions?

A web-based interface is proposed for real-time energy monitoring and decision-making, enabling users to forecast shortages and manage energy usage effectively.

Aug 4, 2026

Upload by Seraphina