PROJECT TITLE :
A Nearly Optimal Packet Scheduling Algorithm for Input Queued Switches with Deadline Guarantees
Deadline guaranteed packet scheduling for switches may be a elementary issue for providing guaranteed QoS in digital networks. It's a historically tough NP-onerous problem if 3 or a lot of deadlines are concerned. All existing algorithms have too low throughput to be employed in follow. A key reason is they use packet deadlines as default priorities to make a decision that packets to drop whenever conflicts occur. Though such a priority structure will ease the scheduling by specializing in one deadline at a time, it hurts the throughput greatly. Since deadlines do not necessarily represent the actual importance of packets, we have a tendency to will greatly improve the throughput if deadline induced priority isn't enforced. This paper 1st presents an algorithm that guarantees the utmost throughput for the case where only two totally different deadlines are allowed. Then, an algorithm referred to as iterative scheduling with no priority (ISNOP) is proposed for the overall case where k > 2 totally different deadlines could occur. Not solely will this algorithm have dramatically higher average performance than all existing algorithms, but conjointly guarantees approximation ratio of 2. ISNOP would offer a sensible sensible resolution for the traditionally troublesome packet scheduling drawback.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here