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{200535,
        author = {Tangudu sai praveen and Dr. V Usha Bala and R. Lavanya and R. Eswar Kamal and G. Sri Chaitra and M. Poojita Sai},
        title = {Smart energy automation real time energy prediction and optimization using particle swarm optimization},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {2099-2108},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200535},
        abstract = {The continuous rise in global electricity demand, driven by rapid urbanization and widespread adoption of electronic appliances, has intensified the challenge of residential energy management. Conventional electricity metering systems provide only cumulative consumption data at the close of each billing cycle, offering little actionable insight into real-time usage behaviour. This delayed visibility limits consumer awareness and makes proactive energy conservation difficult, ultimately contributing to escalating electricity costs, unnecessary energy wastage, and adverse environmental effects.
To address these shortcomings, this paper proposes a Smart Energy Automation System that integrates Internet of Things (IoT) sensing, cloud-based data management, Machine Learning (ML) forecasting via Extreme Gradient Boosting (XGBoost), and Particle Swarm Optimization (PSO) for intelligent energy optimization. IoT-enabled current and voltage transducers, interfaced with a NodeMCU ESP8266 microcontroller, capture electrical parameters from household appliances in real time. The acquired data is relayed to a cloud platform for centralized storage, visualization, and analytical processing. The XGBoost regression model is trained on historical consumption records to forecast future energy usage and predict monthly electricity bills with high accuracy. PSO performs gradient-free hyperparameter tuning of the predictive model and drives demand-side load scheduling by minimizing peak consumption costs while respecting user comfort constraints. An automated alert mechanism flags anomalous energy events, enabling timely corrective intervention.
Experimental evaluation in a residential setting confirms that the proposed system accurately monitors and forecasts energy consumption, detects abnormal usage events, and delivers measurable reductions in electricity expenditure through PSO-guided scheduling. The architecture is low- cost, scalable, and readily deployable in residential and small commercial environments, advancing both smart home automation and sustainable energy utilization.},
        keywords = {Smart Energy Automation, IoT Energy Monitoring, XGBoost, Particle Swarm Optimization, Real-Time Energy Prediction, Household Energy Management, NodeMCU ESP8266, Machine Learning, Anomaly Detection, Smart Home.},
        month = {May},
        }