Four Multi-agent Architectures for Intelligent Network Load Management

Johansson, Stefan J.; Davidsson, Paul; Kristell, Martin

doi:10.1007/3-540-36086-7_22

Cited by 6 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…framework abstraction no framework agents based [22](*), [42], [39], [35] [16], [38](*), [24], [19] without agents [3], [2] [17], [45], [25], [34], [31] [46], [43], [44](*), [33] The above table gives another type of classification according to the criterion whether an approach uses agents or not ([11] identifies essentials of different multi-agent architectural styles (MAS) and shows how MAS can be characterized and evaluated), as well as whether an approach introduces a general framework (taking in the consideration both structured P2P and unstructured P2P net-works as well as grid). Those papers that use a very specific LB algorithm are marked with "(*)".…”

Section: Classification Of Lb Algorithmsmentioning

confidence: 99%

A Space-Based Generic Pattern for Self-Initiative Load Balancing Agents

Kühn

Šešum-Čavić

2009

Engineering Societies in the Agents World X

View full text Add to dashboard Cite

Load-Balancing is a significant problem in heterogeneous distributed systems. There exist many load balancing algorithms, however, most approaches are very problem specific oriented and a comparison is therefore complex. This paper proposes a generic architectural pattern for a load balancing framework that allows for the plugging of different load balancing algorithms, reaching from unintelligent to intelligent ones, to ease the selection of the best algorithm for a certain problem scenario. As in complex network environments there is no "one-fits-all solution", also the integration of several different algorithms shall be supported. The presented pattern assumes autonomous agents and decentralized control. It can be composed towards arbitrary network topologies, foresees exchangeable policies for load-balancing, and uses a black-board based communication mechanism to achieve high software architecture agility. The pattern has been implemented and first instantiations of it with three algorithms have been benchmarked.

show abstract

Section: Classification Of Lb Algorithmsmentioning

confidence: 99%

A Space-Based Generic Pattern for Self-Initiative Load Balancing Agents

Kühn

Šešum-Čavić

2009

Engineering Societies in the Agents World X

View full text Add to dashboard Cite

show abstract

“…This phenomenon degrades performance when self-similar traffic passes through network nodes [8]. Self-similar models can exhibit the property of long-term dependence, which means the manifestation of dependence between events at sufficiently large intervals [3]. An informally self-similar process is defined as a random process whose statistical characteristics exhibit scaling properties.…”

Section: Introductionmentioning

confidence: 99%

Quality Assurance of Data Transmission in Queuing Networks

Komarova,

Saiko,

Nakonechnyi

et al. 2019

IJEAT

View full text Add to dashboard Cite

With the development of high-speed communication networks, the so-called property of self-similarity of flows has an increasing impact on the quality of service. From a practical point of view, this can be explained by the high variability of traffic intensity and, as a consequence, the high receipt of packets to the network node at a high data rate, which leads, due to the limitation of the buffer, to packet losses. For a long time, it was believed that the traffic of the local network is described by the classical Poisson distribution. Telephone networks were originally built on the principle of channel switching, and computer networks are usually based on the principle of packet switching, but the calculation methods have remained virtually the same. Packets at high speed of their movement on a network arrive on a node not separately, and the whole pack. Traffic in such networks has ripples, which increases the likelihood of congestion in the network nodes, which lead to buffer overflows and cause losses and / or delays. Pulsations lead to differences in the speed of information flows, in which the ratio of the maximum value to the minimum speed is tens of times. At the same time, it turned out that in multiservice networks, the number of events in a given time interval depends on previous, very distant events. This means that at large scales of a multiservice network, traffic has the property of self-similarity, i.e. it looks qualitatively the same at any sufficiently large scales of the time axis

show abstract

Characterization and Evaluation of Multi-agent System Architectural Styles

Davidsson

Johansson

Svahnberg

2006

Software Engineering for Multi-Agent Systems IV

Self Cite

View full text Add to dashboard Cite

We argue that it is useful to study classes of Multi-Agent System (MAS) architectures, corresponding to architectural styles in addition to particular architectures. In this work we focus on a particular abstraction level where MAS architectural styles are characterized according to properties, such as, the type of control used (from fully centralized to fully distributed), and the type of coordination used. Different architectural styles support different quality attributes to different extent. When choosing architectural style for a given application domain, we argue that it is important to evaluate the them according to the quality attributes relevant to that application. The architectural style that provides the most appropriate balance between these attributes should then be selected. As a case study we investigate the problem of dynamic and distributed resource allocation and compare six MAS architectural styles that can be used to handle this task. We also illustrate the use of the Analytic Hierarchy Process, which is a basic approach to select the most suitable alternative from a number of alternatives evaluated with respect to several criteria, for selecting the architectural style that balance the trade-off between the relevant quality attributes in the best way.

show abstract

Four Multi-agent Architectures for Intelligent Network Load Management

Cited by 6 publications

References 6 publications

A Space-Based Generic Pattern for Self-Initiative Load Balancing Agents

A Space-Based Generic Pattern for Self-Initiative Load Balancing Agents

Quality Assurance of Data Transmission in Queuing Networks

Characterization and Evaluation of Multi-agent System Architectural Styles

Contact Info

Product

Resources

About