Smart priority queue algorithms for self-optimizing event storage

Low run-time overhead, self-adapting storage policies for priority queues called Smart Priority Queue (SPQ) techniques are developed and evaluated. The proposed SPQ policies employ a lowcomplexity linear queue for near-head activities and a rapid-indexing variable bin-width calendar queue for distant events. The SPQ configuration is determined by monitoring queue access behavior using cost-scoring factors and then applying heuristics to adjust the organization of the underlying data structures. We show that optimizing storage to the spatial distribution of queue access can decrease HOLD operation cost between 25% and 250% over existing algorithms such as calendar queues. An SPQ-based scheduler for discrete event simulation has been implemented and was used to evaluate the resulting efficiency, components of access time, and queue usage distributions of the existing and proposed algorithms. Keyword: Discrete event simulation; Priority queue; Adaptive algorithm 1.0 Introduction We present Smart Priority Queue (SPQ) policies for inserting, deleting, retrieving items in the event queues of discrete event simulators. A fundamental capability required is an efficient means of storing and selecting the events contained in the process queue. The SPQ techniques decrease average access overhead by selecting a more efficient storage structure for the particular distribution of events encountered during simulation. Rather than specifying a single management scheme for the priority queue of simulator events, the SPQ approach dynamically selects between