IoT workload distribution impact between edge and cloud computing in a smart grid application

Abstract

The advent of Internet of Things is now part of our reality. Increasing amounts of data are being continuously generated and monitored through widespread sensing technologies such as personal smartphones, large scale smart cities sensor deployments and smart electrical grids. However, the ability to aggregate and act upon such data gathered by sensors is still a significant research and industrial challenge. Devices that are able to collect and act on data at network edges are bounded by the amount of data that can be sent over networks. In this paper, we analyze the impact of workload distribution in a smart grid application, evaluating how we can increase processing rates by leveraging each time more powerful edge node processors. Our results show that our test bed application, leveraging cloud nodes processing and processing windows, is able to achieve processing rates of approximately 800k measurements per second using four edge node processors and a single cloud node.