Adaptive Real-Time Vehicle Usage Patterns with Cloud-Enabled Bayesian Networks

In this research, we provide a new real-time method for managing vehicle utilization patterns using cloud-enabled Bayesian networks (BN). Traditional solutions often employ static models and batch processing to account for the ever-changing nature of vehicle utilization. The objective is to use cloud-enabled BN to improve real-time vehicle utilisation monitoring, optimise fleet management, and make better decisions. To improve the precision and responsiveness of consumption predictions, businesses are increasingly turning to cloud computing, enabling continuous, real-time data stream processing. To weather, traffic patterns, and historical data, among other elements that impact vehicle utilization, BN provide a strong foundation for modelling complicated connections. To increase the accuracy of its adaptive use pattern forecasts, the system updates probabilistic associations in real time using incoming data. Fleet managers may optimize resource allocation, improve service delivery, and achieve overall operational efficiency via incorporating cloud computing, enabling scalable and efficient processing. In metropolitan areas, where use patterns might change quickly, this method helps manage vehicle fleets more adaptively and responsively. It showcases the practicality and advantages of our method in simulations and case studies, showing how it can change the game for fleet management techniques. It highlights the revolutionary power of BN offered by the cloud in improving the efficiency and responsiveness of fleet operations.