Gayan Abeysundara - Complex Adaptive Systems Group

More documents

Recommendations

Info

Dynamic Cellular Channel Allocation using Intelligent Agents April 2005COMP 4905 Honours Projectobtained using fixed ants. We could conclude that the random hotspots produced a high demandfor ants that resulted in higher ant populations, bu did not result in better call rates simply becausethe network is too stressed and could not be relieved by extra channel shuffling. When the antpopulation was able dynamically adjust, the call blockage was reduced by an average of 62%.4.3 Observations and AnalysisUpon examining all the above simulation results, we can confidently conclude that adding agentsto the cellular network produced better call rates under all conditions. All simulations leveled offto a plateau when more agents were added. Agents proved to work very well and self-organize todramatically reduce the percentage of calls blocked. Considering all call models, agents were ableto reduce the number of calls blocked by 55% - 82%. Agents in the Centre Hotspot call modelreduced the call blockage by an average of 77%. While agents in the Downtown and RandomHotspot model reduced the calls blocked by an average of 70% and 68%, respectively. The higherperformance results in the Centre Hotspot call model can be attributed to the less random networkconditions, allowing agents to adapt more easily to the centre-oriented network demand. Overall,the agent-based solution decreased the number of calls blocked by a remarkable 72%, consideringall simulated network scenarios. In contrary to previous simulations done by Lawlor, the callgeneration rate had no effect on the results. With high call rate such as nine or ten, when oneassumes the network may be too overloaded to have any affect, the addition of agents alwaysimproved network performance. Another interesting fact was when the simulation results attainedthe minimum call blockage rate, the addition of more agents did not overload the system butcontinued to produce the same performance results. Although the Random Hotspot modelgenerated more fluctuations in the graphs, the results were excellent. Agents were able to adaptefficiently to the continuous flow of random network hotspots.The results of the Dynamic Ant Adjustment feature were outstanding. The number of antsadapted very well to network conditions, producing call rates that were good as any of the fixedant methods. The system managed to adapt to an optimal minimal number of ants under everysituation, with the exception of the Random Hotspot. With higher call rates in the RandomHotspot model, more ants were spawned then required. But even with the higher ant populations,call rate results were not affected. An average 68% reduction in call blockage was achieved usingthe feature, considering all call models and call rates.31
Dynamic Cellular Channel Allocation using Intelligent Agents April 2005COMP 4905 Honours Project5. Conclusion5.1 Similar Work Done in FieldThere has been a great deal of work in the field of intelligent agents used for network control andmanagement. Considerable interest in this field arises from the decentralized nature of agenttechnology and the ability to adapt real-time to network conditions. One researcher by the nameKhaldoun Al agha had done similar work to this project by using intelligent agents associatedwith wireless networks to achieve adaptive resource allocation [Al agha, 2000].Al agha proposes a multi-agent solution for intelligent base stations in wireless networks. Agentsare able to combine knowledge and experience with neighboring agents to make the bestdecisions. This is achieved by agents cooperating, communicating, reasoning, and perceiving.Agents corresponding with a base station are capable of communicating its state to neighbors andlearning from past events in the environment to optimize the utilization of resources.The agent solution is used in conjunction with a resource allocation scheme known as ChannelSegregation (CS). Channel Segregation differs from traditional dynamic allocation schemesbecause it has a simple form of self-learning. It involves segregating physical channels from acommon pool by each base station to form a preferred list of channels. Base stations attempt toallocate channels at the top of their priority list. The learning aspect of CS is achieved though themethod priority lists are formed, resulting in differing lists across the network cells – andstabilizing over time. Simulation results have shown that the integration of intelligent agents withchannel segregation had improved call rates by decreasing the number of calls blocked.An overview of research done in the field of both Communication Networks (CN) andDistributed Artificial Intelligence (DAI) can be found in [Willmott and Calisti, 2000]. Willmottand Calisti identify current trends in agent-based network control and management. They discussareas that would most benefit from agent technologies and deployment strategies for agent basedsolutions. For a thorough summary of mobile agents in networks, the reader may refer to[Sriraman, 2002].32
Page 1 and 2: School of Computer ScienceCarleton
Page 3 and 4: Dynamic Cellular Channel Allocation

Gayan Abeysundara - Complex Adaptive Systems Group

You also want an ePaper? Increase the reach of your titles

Delete template?

Save as template?