Decentralised Cooperative Agent-Based Clustering in Intelligent Traffic Clouds
Contemporary traffic management systems will become more intelligent with advent of future Internet technologies. The systems are expected to become more simple, effective and comfortable for users, but this transformation will require the development of both new system architectures as well as enhanced processing and mining algorithms for large volumes of cloud data. In this study, we consider a conceptual architecture of a cloud-based traffic management system that applied to a multi-modal journey planning scenario. For this purpose, it is necessary to process large amounts of travel-time information. Information is collected by cloud service providers and processed for future route planning. In this paper, we focus on the data clustering step in the data mining process. The data collection and processing require an appropriate clustering algorithm to aggregate similar data. In particular, we support a process where a particular service provider can request additional information from others to be used in the clustering function, requiring a decentralised clustering algorithm. We present a cloud-based architecture for this scenario, develop a decentralised cooperative kernel-density based clustering algorithm, and evaluate the efficiency of the proposed approach using real-world traffic data from Hanover, Germany.
KeywordsCloud computing architecture decentralised data processing and mining multi-agent systems kernel density estimation clustering
Unable to display preview. Download preview PDF.
- 2.Bazzan, A.L.C., Klügla, F.: A review on agent-based technology for traffic and transportation. The Knowledge Engineering Review FirstView, 1–29 (2013)Google Scholar
- 3.Ben-Hur, A., Elisseeff, A., Guyon, I.: A stability based method for discovering structure in clustered data. In: Pacific Sym. on Biocomputing, vol. 7, pp. 6–17 (2002)Google Scholar
- 5.Fiosina, J., Fiosins, M.: Chapter 1: Cooperative regression-based forecasting in distributed traffic networks. In: Memon, Q.A. (ed.) Distributed Network Intelligence, Security and Applications, pp. 3–37. CRC Press, Taylor and Francis Group (2013)Google Scholar
- 6.Fiosina, J., Fiosins, M., Müller, J.P.: Mining the traffic cloud: Data analysis and optimization strategies for cloud-based cooperative mobility management. In: Casillas, J., Martínez-López, F.J., Vicari, R., De la Prieta, F. (eds.) Management Intelligent Systems. AISC, vol. 220, pp. 25–32. Springer, Heidelberg (2013)CrossRefGoogle Scholar
- 7.Fiosins, M., Fiosina, J., Müller, J.P., Görmer, J.: Reconciling strategic and tactical decision making in agent-oriented simulation of vehicles in urban traffic. In: ICST Conf. on Simulation Tools and Techniques, SimuTools 2011 (2011)Google Scholar
- 11.Lee, J.G., Han, J., Whang, K.Y.: Trajectory clustering: A partition-and-group framework. In: ACM SIGMOD Int. Conf. on Management of Data (SIGMOD 2007), Beijing, pp. 593–604 (2007)Google Scholar
- 13.Ogston, E., Overeinder, B., van Steen, M., Brazier, F.: A method for decentralized clustering in large multi-agent systems. In: Proc. of 2nd Int. Conf. on Autonomous Agents and Multiagent Systems, pp. 789–796 (2003)Google Scholar
- 14.Talia, D.: Cloud computing and software agents: Towards cloud intelligent services. In: Proc. of the 12th Workshop on Objects and Agents, vol. 741, pp. 2–6 (2011)Google Scholar
- 15.Weijermars, W., van Berkum, E.: Analyzing highway flow patterns using cluster analysis. In: Proc. of the 8th Int. IEEE Conf. on ITS, Vienna, pp. 831–836 (2005)Google Scholar