Distributed optimization in sensor networks

Wireless sensor networks are capable of collecting an enormous amount of data over space and time. Often, the ultimate objective is to derive an estimate of a parameter or function from these data. This paper investigates a general class of distributed algorithms for "in-network" data processing, eliminating the need to transmit raw data to a central point. This can provide significant reductions in the amount of communication and energy required to obtain an accurate estimate. The estimation problems we consider are expressed as the optimization of a cost function involving data from all sensor nodes. The distributed algorithms are based on an incremental optimization process. A parameter estimate is circulated through the network, and along the way each node makes a small adjustment to the estimate based on its local data. Applying results from the theory of incremental subgradient optimization, we show that for a broad class of estimation problems the distributed algorithms converge to within an ε-ball around the globally optimal value. Furthermore, bounds on the number incremental steps required for a particular level of accuracy provide insight into the trade-off between estimation performance and communication overhead. In many realistic scenarios, the distributed algorithms are much more efficient, in terms of energy and communications, than centralized estimation schemes. The theory is verified through simulated applications in robust estimation, source localization, cluster analysis and density estimation.