A Nearly Optimal Packet Scheduling Algorithm for Input Queued Switches with Deadline Guarantees

• Published in: IEEE transactions on computers Vol. 64; no. 6; pp. 1548 - 1563
• Main Authors: Zhang, Baoxian, Wan, Xili, Junzhou, Luo, Shen, Xiaojun
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.06.2015; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Approximation; Deadlines; Global Positioning System; Heuristic; Mathematical analysis; Optimal scheduling; Optimization; Packets (communication); Ports (Computers); Priorities; Quality of service; Scheduling; Scheduling algorithms; Switches; Throughput; deadline guarantee; real time scheduling; packet scheduling; quality of service; minimum cost maximum flow; Input-queued switch
• ISSN: 0018-9340; 1557-9956
• DOI: 10.1109/TC.2014.2329695

Deadline guaranteed packet scheduling for switches is a fundamental issue for providing guaranteed QoS in digital networks. It is a historically difficult NP-hard problem if three or more deadlines are involved. All existing algorithms have too low throughput to be used in practice. A key reason is they use packet deadlines as default priorities to decide which packets to drop whenever conflicts occur. Although such a priority structure can ease the scheduling by focusing on one deadline at a time, it hurts the throughput greatly. Since deadlines do not necessarily represent the actual importance of packets, we can greatly improve the throughput if deadline induced priority is not enforced. This paper first presents an algorithm that guarantees the maximum throughput for the case where only two different deadlines are allowed. Then, an algorithm called iterative scheduling with no priority (ISNOP) is proposed forthe general case where k > 2 different deadlines may occur. Not only does this algorithm have dramatically better average performance than all existing algorithms, but also guarantees approximation ratio of 2. ISNOP would provide a good practical solution for the historically difficult packet scheduling problem.