Spark Booster-An Optimized IoT Architecture for Energy Sector Delving Predictive Analysis on Energy Usage With Stochastic Monte Carlo Method

Optimal energy distribution and Energy management in a dynamic environment in smart city applications is a challenging task that requires a more optimised method to predict energy consumption. This research presents a novel data-driven Internet of Things (IoT) architecture called Spark Booster to enhance the prediction accuracy of energy consumption in a dynamic environment. The proposed architecture integrates the Stochastic Monte Carlo method and Markov chain modelling to simulate diversified energy usage scenarios and analyse energy data for accurate prediction of energy consumption. The proposed architecture is an adaptive one with real-time data acquisition and edge analytics for energy consumption prediction. The experimental results demonstrate a significant improvement in the prediction accuracy and robustness compared to the conventional architectures. The Sparks Boost architecture offers a scalable solution for both residential and industrial applications. The proposed optimized architecture enables optimal energy distribution, reducing resource wastage for supporting sustainability.