Distributed Online Algorithms for the Agent Migration Problem in WSNs

  • Authors:

  • Nikos Tziritas;Spyros Lalis;Samee Ullah Khan;Thanasis Loukopoulos;Cheng-Zhong Xu;Petros Lampsas

  • Affiliations:

  • Chinese Academy of Sciences, Beijing, China;University of Thessaly & IRETETH/CERTH, Thessaly, Greece;Chinese Academy of Sciences, Beijing, China and North Dakota State University, Fargo, USA;Technological Educational Institute of Lamia, Lamia, Greece;Chinese Academy of Sciences, Beijing, China and Wayne State University, Detroit, USA;Technological Educational Institute of Lamia, Lamia, Greece

  • Venue:
  • Mobile Networks and Applications
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

The mobile agent paradigm has been adopted by several systems in the area of wireless sensor networks as it enables a flexible distribution and placement of application components on nodes, at runtime. Most agent placement and migration algorithms proposed in the literature, assume that the communication rates between agents remain stable for a sufficiently long time to amortize the migration costs. Then, the problem is that frequent changes in the application-level communication may lead to several non-beneficial agent migrations, which may actually increase the total network cost, instead of decreasing it. To tackle this problem, we propose two distributed algorithms that take migration decisions in an online fashion, trying to deal with fluctuations in agent communication. The first algorithm is more of theoretical value, as it assumes infinite storage to keep information about the message exchange history of agents, while the second algorithm is a refined version that works with finite storage and limited information. We describe these algorithms in detail, and provide proofs for their competitive ratio vs. an optimal oracle. In addition, we evaluate the performance of the proposed algorithms for different parameter settings through a series of simulated experiments, also comparing their results with those achieved by an optimal static placement that is computed with full (a posteriori) knowledge of the execution scenarios. Our theoretical and experimental results are a strong indication for the robustness and effectiveness of the proposed algorithms.