Wyniki wyszukiwania - BazTech

1

Multi-AUV distributed task allocation based on the differential evolution quantum bee colony optimization algorithm

Li J., Zhang R.

Polish Maritime Research

|

2017

|

S 3

65--71

EN

The multi-autonomous underwater vehicle (AUV) distributed task allocation model of a contract net, which introduces an equilibrium coefficient, has been established to solve the multi-AUV distributed task allocation problem. A differential evolution quantum artificial bee colony (DEQABC) optimization algorithm is proposed to solve the multi-AUV optimal task allocation scheme. The algorithm is based on the quantum artificial bee colony algorithm, and it takes advantage of the characteristics of the differential evolution algorithm. This algorithm can remember the individual optimal solution in the population evolution and internal information sharing in groups and obtain the optimal solution through competition and cooperation among individuals in a population. Finally, a simulation experiment was performed to evaluate the distributed task allocation performance of the differential evolution quantum bee colony optimization algorithm. The simulation results demonstrate that the DEQABC algorithm converges faster than the QABC and ABC algorithms in terms of both iterations and running time. The DEQABC algorithm can effectively improve AUV distributed multi-tasking performance.

2

Mobile devices and computing cloud resources allocation for interactive applications

Krawczyk H., Nykiel M.

Archives of Control Sciences

|

2017

|

Vol. 27, no. 2

293--307

EN

Using mobile devices such as smartphones or iPads for various interactive applications is currently very common. In the case of complex applications, e.g. chess games, the capabilities of these devices are insufficient to run the application in real time. One of the solutions is to use cloud computing. However, there is an optimization problem of mobile device and cloud resources allocation. An iterative heuristic algorithm for application distribution is proposed. The algorithm minimizes the energy cost of application execution with constrained execution time.

3

Zjawiska dławień intensywności zadań do serwerów - eksperymenty symulacyjne

Oniszczuk W.

Symulacja w Badaniach i Rozwoju

|

2014

|

Vol. 5, nr 3

181--189

PL

W pracy przedstawiono wyniki eksperymentów symulacyjnych ukierunkowanych na badania zjawisk dławień intensywności strumieni zadań napływających do bloku serwerów. Badana była konfiguracja sieci z blokadami i dynamiczną manipulacją progami w buforach. Te ograniczające mechanizmy zrealizowano poprzez specjalny moduł kontroli napływu nowych zadań (dwóch priorytetowych klas) do wspólnych węzłów obsługi. Taki moduł kontroli zawiera w sobie adaptacyjne algorytmy manipulowania progami w buforach, reagujących na bieżące zmiany ruchu teleinformatycznego w sieci. Wyniki eksperymentów pokazują, jak ważnym czynnikiem są mechanizmy blokad i dynamicznych progów w sieciach z ograniczonymi buforami.

EN

This paper presents the series of experiments with simulation of stifling job intensities in some computer systems/networks with flexible buffer management and blocking. These constrains are treated as some control schemes for two priority job classes models in congested computer systems. The proposed scheme incorporates adaptive thresholds, which dynamically adjust according to computer system traffic behavior changes. The results of experiments confirm importance of a special treatment for the models with blocking, and threshold policy, in finite capacity buffers, which justifies this research.

4

GLBAI: Global Load Balancing Using Agents Identifiers in Grid Environment

Jamali S., Razzaghzadeh S.

Przegląd Elektrotechniczny

|

2012

|

R. 88, nr 12a

280-283

EN

In a grid environment the resource management, task scheduling and also load balancing are essential functionalities provided by software infrastructure. Recently, intelligent agent technology has provided an adaptive and scalable framework for management and scheduling of dynamic resources in the grid environment. In this approach an agent is a representative of a grid resource that is supported by a software system. This paper presents a new agent-based method, called GLBAI, for the improvement of global load balancing. While previous works assume that all existing agents in the environment have identical capabilities, this paper considers different capabilities for different agents. It proposes an agent identifier that indicates the agents capabilities. The agents cooperate with each other to balance workload using a service advertisement and discovery mechanism in which agents capability information are passed in the form of the identifier. Simulation results show that GLBAI reduces application execution time, maximizes resource utilization and offers more efficient load balancing service.

PL

W artykule przedstawiono nową metodę agentową o nazwie GLBAI, do zarządzania zasobami energii w sieci. Metoda ma na celu ulepszenie zbalansowania globalnego obciążenia sieci, poprzez uszeregowanie różnych agentów pod względem ich możliwości zasobowych i nadanie odpowiedniego identyfikatora. Agenci współpracują między sobą w celu zbalansowania obciążenia oraz wykorzystania informacji zawartych w identyfikatorach. Badania symulacyjne wskazują, że system GLBAI redukuje czas wykonania programu, maksymalizuje wykorzystanie zasobów oraz oferuje lepszy zbalansowanie obciążenia.

5

Worst-case relative regret algorithm for task allocation in complex operation system

Józefczyk J.

Systems Science

|

2005

|

Vol. 31, no 2

57-66

EN

The uncertain version of a task allocation problem in a complex of independent operations is considered. The parameters in models of the operations are assumed to belong to given intervals. The objective is to find a time-optimal robust solution in terms of the worst-case relative regret function. The optimal worst-case relative regret task allocation algorithm is presented. It consists in reducing the problem with uncertain input data to a number of deterministic problems whose solution algorithms are known. Special cases and a simple example for the polynomial models of the operations illustrate the solution algorithm.

6

Task allocation algorithms for maximizing reliability of heterogeneous distributed computing systems

Mahmood A.

Control and Cybernetics

|

2001

|

Vol. 30, no 1

115-130

EN

The rapid progress of microprocessor and communication technologies has made the distributed computing system economically attractive for many computer applications. One of the first problems encountered in the operation of a distributed system is the problem of allocating the tasks among the processing nodes. The task allocation problem is known to be computationally intractable for large task sets. In this paper, we consider the task allocation problem with the goal of maximizing reliability of heterogeneous distributed systems. After presenting a quantitative task allocation model, we present a least-cost branch-and-bound algorithm to find optimal task allocations. We also present two heuristic algorithms to obtain suboptimal allocations for realistic size large problems in a reasonable amount of computational time. Simulation was used to study the performance of the proposed algorithms for a large number of problems. Also, performance of the proposed algorithms has been compared with a well-known heuristics available in the literature.