| 000 | 03477nam a2200265 a 4500 | ||
|---|---|---|---|
| 001 | vtls000078839 | ||
| 003 | KUKTEM | ||
| 005 | 20251114204458.0 | ||
| 008 | 140528t2013 my da f m 000 0 eng d | ||
| 020 | _aTHE0001733(Local) | ||
| 039 | 9 |
_a201905131214 _byusri _c201710041242 _daishah _y201405280947 _zFida |
|
| 040 | _aUMP | ||
| 090 | _aQA76.63 .E47 2013 rs Bc. | ||
| 100 | 0 | _aElrasheed Ismail Sultan | |
| 245 | 1 | 0 |
_aQuantum particle swarm optimization technique for load balancing in cloud computing / _cElrasheed Ismail Sultan |
| 260 |
_aKuantan, Pahang : _bUMP, _c2013 |
||
| 300 |
_axvi, 148 p. : _bill. (some col.) ; _c30 cm. + _e1 CD-ROM |
||
| 502 | _aThesis (Doctor of Philosophy in Computer Science) -- Universiti Malaysia Pahang - 2013 | ||
| 504 | _aBibliography : p. 137-148 | ||
| 520 | 3 | _aCloud Computing systems are widely applied in many fields such as communication data management, web application, network monitoring, financial management and so on. The distributed Cloud Computing technology has been produced as the development of the computer network and distributed computing technology. Researches on data Cloud Computing become the necessary trend in the distributed Cloud Computing system domain since the sources and application of the data are distributed and the scale of the applications enlarges quickly. Load management is the focus of research in both of the area in distributed Cloud Computing systems and centralized Cloud Computing systems. Although researches on the load management in the cloud systems is similar to that of traditional parallel and distributed systems in many aspects, essential differences exist between them. The choice of a scheduling strategy has significant impact on the runtime Central Processing Unit, memory consumption as well as the storage systems. Load balancing optimization techniques such as Ant Colony Optimization (ACO), First Come First Served (FCFS), Round Robin (RR) and Particle Swarm Optimization (PSO) are popular techniques being used for scheduling and load balancing. However, these techniques have its weaknesses in terms of minimizing makespan, computation cost and communication cost. In this study, load balancing technique in Cloud Computing called Quantum Particle Swarm Optimization (QPSO) technique proposed by considering only minimization of makespan, computation cost and communication cost. Performance of the QPSO technique based on many heuristic algorithms it is comprised the following steps. Firstly, tasks are assigned averagely to the machines according to a special initialization policy. Then the optimal criterion for exchanging tasks between two machines is proposed and exploited to speed up the improving process towards load balance. Secondly, this thesis proposes job-combination based static algorithm for load balancing where all jobs should organized into the standard job combinations, each task of which consists of one to four jobs. Then they are assigned to the machines according to the assignment algorithm for job combinations, which is a special integer partition algorithm. Finally, the result of experiment shows that QPSO can achieve at least three times cost saving as compared with ACO, FCFS, RR and PSO. | |
| 650 | 0 | _aLogic programming | |
| 650 | 0 | _aSwarm intelligence | |
| 856 | 4 | 0 |
_uhttp://ecollib.ump.edu.my/2361/ _zLibrary access only |
| 999 |
_aVIRTUA40 _c2744 _d2750 |
||
| 999 | _aVTLSSORT0080*0200*0400*0900*1000*2450*2600*3000*5020*5040*5200*6500*6501*8560*9992 | ||