Simulations of three adaptive, decentralized controlled, job scheduling algorithms
Computer Networks and ISDN Systems
A distributed load-balancing policy for a multicomputer
Software—Practice & Experience
Adaptive load sharing in homogeneous distributed systems
IEEE Transactions on Software Engineering
A Trace-Driven Simulation Study of Dynamic Load Balancing
IEEE Transactions on Software Engineering
Design principles of operating systems for large scale multicomputers
Proceedings of the International Workshop on Experiences with Distributed Systems
SHAYOG: a test bed for evaluation dynamic load-sharing policies
Software—Practice & Experience
Analysis of the Effects of Delays on Load Sharing
IEEE Transactions on Computers
The Probability of Load Balancing Success in a Homogeneous Network
IEEE Transactions on Software Engineering
Load-balancing heuristics and process behavior
SIGMETRICS '86/PERFORMANCE '86 Proceedings of the 1986 ACM SIGMETRICS joint international conference on Computer performance modelling, measurement and evaluation
A comparison of receiver-initiated and sender-initiated adaptive load sharing (extended abstract)
SIGMETRICS '85 Proceedings of the 1985 ACM SIGMETRICS conference on Measurement and modeling of computer systems
A taxonomy of scheduling in general-purpose distributed computing systems
IEEE Transactions on Software Engineering
Development of Veda, a Prototyping Tool for Distributed Algorithms
IEEE Transactions on Software Engineering
Case study: Evaluation of loadsharing algorithms for heterogeneous distributed systems
Computer Communications
| Hi-index | 0.00 |
This paper presents a new load balancing algorithm called Periodic Symmetrically-Initiated (PSI). It is symmetrically initiated and uses periodic polling of a single random node to acquire information about the system state. Its performance on a distributed system is compared to the following algorithms: Random, Sender, Receiver, and Symetric. These algorithms have been evaluated in [15] where the terms Sender and Receiver are referred to as Forward and Reverse respectively. The algorithms performance under different variants to the system model is also studied to assess the sensitivity of the PSI algorithm to changes in the system attributes. This includes the communication bandwidth, the system size, the file system structure, and the workload model. The results of the study show that the PSI algorithm out performs the existing algorithms and is robust over a range of system attributes.