A Scheme to Improve Stream Transaction Rates for Real-Time IoT Applications

Abstract

Due to the recent proliferation of IoT (Internet of Things) devices, a large amount of stream data such as video data or sensor data is transmitted to remote processing computers. The stream transaction rate is one of the main factors to improve the performance of some IoT applications. For instance, in surveillance systems, the probability to catch a moving person increases as the processing computer analyzes video with a higher transaction rate. To improve stream transaction rates, some schemes reduce communication time between a processing computer and stream data sources. They target periodic stream transactions and assume static transmission intervals. However, the communication and transaction time changes dynamically. Therefore, stream transaction rates can be further improved by changing transmission intervals dynamically depending on it. In this paper, we propose a scheme to improve stream transaction rates by changing transmission intervals dynamically. In our proposed scheme, a processing computer sometimes changes transmission intervals to be the same length as the average transaction time. Moreover, our proposed scheme adopts a progressive quality improvement (PQI) approach to reduce communication and transaction time. Our evaluation results revealed that the proposed scheme can achieve a higher stream transaction rate than a conventional scheme with the PQI approach.