Using Osmotic Services Composition for Dynamic Load Balancing of Smart City Applications
Arthur Souza, Zhenyu Wen, Nélio Cacho, Alexander B. Romanovsky, Philip James, Rajiv Kumar Ranjan · 2018
Edge computing takes computation away from the Cloud closer to the physical world. Therefore, it reduces the cost of communication bandwidth between IoT devices and the Cloud. However, Edge computing imposes certain limitations in computation power because due to poor hardware capacity of the devices. This restriction may significantly affect the performance of the deployed applications, especially Smart City applications. This limitations also could be aggravated by unpredictable human behaviors wich will easily make the Edge computation node overloaded. Osmotic computing is a new IoT application programming paradigm that provides an opportunity to balance the workload between Edge and Cloud therefore to overcome the load imbalance problem of Smart City applications. To this end, we propose an Osmotic Execution Framework that leverages state-of-the-art microservices techniques to deploy and execute a Smart City application in a distributed environment including Edge and Cloud. Finally, we evaluate load balancing through latency time analysis of our framework with a real-world smart parking application.