Resource location based on precomputed partial random walks in dynamic networks

TL;DR

This paper extends precomputed partial random walk strategies for resource location to dynamic networks, demonstrating significant reductions in search lengths and efficient overhead management through simulation validation.

Contribution

It adapts static network resource location mechanisms to dynamic environments, providing analytical models and validating their robustness and efficiency in volatile networks.

Findings

Significant reduction in average search lengths in dynamic networks.

Analytical expressions accurately predict search performance.

Proposed mechanisms are efficient and robust under high network volatility.

Abstract

The problem of finding a resource residing in a network node (the \emph{resource location problem}) is a challenge in complex networks due to aspects as network size, unknown network topology, and network dynamics. The problem is especially difficult if no requirements on the resource placement strategy or the network structure are to be imposed, assuming of course that keeping centralized resource information is not feasible or appropriate. Under these conditions, random algorithms are useful to search the network. A possible strategy for static networks, proposed in previous work, uses short random walks precomputed at each network node as partial walks to construct longer random walks with associated resource information. In this work, we adapt the previous mechanisms to dynamic networks, where resource instances may appear in, and disappear from, network nodes, and the nodes themselves may leave and join the network, resembling realistic scenarios. We analyze the resulting resource location mechanisms, providing expressions that accurately predict average search lengths, which are validated using simulation experiments. Reduction of average search lengths compared to simple random walk searches are found to be very large, even in the face of high network volatility. We also study the cost of the mechanisms, focusing on the overhead implied by the periodic recomputation of partial walks to refresh the information on resources, concluding that the proposed mechanisms behave efficiently and robustly in dynamic networks.