Load balancing scheduling method based on maximum entropy principle

Abstract

The invention discloses a load balancing scheduling method based on a maximum entropy principle. The concept of thermodynamic entropy is introduced into load balancing. The internal relation between entropy and load balance is studied. The resource balance distribution is taken as a target. A balanced scheduling problem of the load is equivalent to a maximum entropy problem for solving the system.Meanwhile, a theoretical model and basic properties of the system entropy are given, the entropy is used as a measurement index of the system load balance degree, scheduling and migration are carriedout on the system load according to the entropy change, the system can reach the load balance target faster and better, the response time is shortened, the throughput rate is increased, and thereforethe performance of the cluster system is improved.

Description

technical field [0001] The invention relates to the technical field of computer load balancing, in particular to a load balancing scheduling method based on the principle of maximum entropy. Background technique [0002] With the rapid development of Internet information technology and terminal technology, the demand of the information industry is increasingly moving towards the direction of high service end and low terminal. The ensuing mass data integration and computing requirements have become the bottleneck of server-side cluster technology at this stage. The service capability of a single server is far from meeting the growing demand, so the cluster system with good scalability and high cost performance became the main choice. How to allocate tasks reasonably in the cluster system, so that the tasks are evenly allocated, so that one server is not allocated too much, while other servers are allocated too little and cannot fully play their role, has become a focus and d...

AI Technical Summary

Problems solved by technology

Liu Zhanghui et al [Liu Zhanghui, Wang Xiaoli. Load balancing algorithm with genetic algorithm in cloud computing virtual machine clusters [J]. Journal of Fuzhou University (Natural Science Edition), 2012,40(4): 453-458.] proposed The load balancing algorithm with genetic algorithm applies artificial intelligence technology to solve the load balancing problem. However, this algorithm is only suitable for the experimental environment and can only be executed in an ideal environment, and cannot meet the complex and changing needs of actual application scenarios.

Balasubramaniam M et al[CHAUU S C,ADA W C F.Load balancing between computing clusters[C].In Proceedings of the 4th International Conference on Parallel and Distributed Computing,A applications and Technologies.CA:IEEE,2003,548-551.] proposed a cluster Computing dynamic load balancing library, however, the library is built on heterogeneous clusters and cannot meet the needs of homogeneous clusters

[0005] Through the above analysis, it is found that in the existing research work, the static allocation strategy cannot meet the dynamic change requirements of the resource load; most of the dynamic allocation strategies only consider a certain attribute of the resource, and cannot well reflect the real-time load of the resource and The difference of resources; the introduction of artificial intelligence technology and control theory into the solution process of load balancing makes the calculation process too complicated and increases the burden on the system

Images