BS-HTIS: Buffer Sizing for Heterogeneous Traffic and Integrated System

• Published in: IEEE access Vol. 9; pp. 115237 - 115245
• Main Authors: Shi, Huaifeng, Pan, Chengsheng, Wang, Yingzhi
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Bandwidth; buffer sizing; Buffers; Decoupling; Diffserv networks; integrated scheduling; Internet of Things; Job shop scheduling; LRD traffic; Markov processes; Numerical analysis; Overflow; Priority scheduling; Quality of service; Quality of service architectures; Queueing analysis; Scheduling; Sizing; Videos; xsSRD traffic
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2021.3102423

Buffer sizing for switching and routing devices is of significance for guaranteeing the Quality of Service (QoS) of critical services on the Internet of Things (IoT), continuously evolving scheduling mechanisms and complex traffic characteristics pose new challenges for the traditional method of static buffer sizing based on rule-of-thumb. In this paper, the scope of buffer sizing is extended from a basic scheduling system under homogeneous arrival traffic input to an integrated scheduling system under heterogeneous arrival traffic input which is more ubiquitous. In this context, Voices, videos and other heterogeneous data in the IoT are categorized into short-range-dependent (SRD) and long-range-dependent (LRD) traffic, and the integrated scheduling system is decomposed into single-server-single-queue (SSSQ) systems by not only decoupling the complex dependencies among heterogeneous traffic inputs but also taking the impact of SRD and LRD traffic burstiness on the buffer sizing into account. On this basis, expressions for the relation between the minimum buffer size and the maximum overflow probability are presented. The numerical analysis results and simulation analysis results reveal that the average arrival rate, traffic burst level and scheduling priority are positively correlated with the required buffer size, and once the overflow probability is set, the minimum buffer size can be determined correspondingly. The achievements of this paper will provide theoretical guidance for IoT manufacturers and technicians to set buffers more reasonably and use resources more efficiently.