|
Symbiotic Service Composition in Distributed Sensor NetworksDOI: 10.1155/2013/684563 Abstract: To cope with the evergrowing number of colocated networks and the density they exhibit, we introduce symbiotic networks—networks that intelligently share resources and autonomously adapt to the dynamicity thereof. By allowing the software services provided in such networks to operate in an equally symbiotic manner, new opportunities for the so-called service compositions arise, which take advantage of the multitude of services and combine them to achieve goals set out by the individual networks. To accommodate services in large-scale symbiotic networks, including wireless sensor networks, we propose a software platform which autonomously constructs and orchestrates such compositions. Furthermore, upon changes in the infrastructure, the platform responds by adapting compositions to reflect the changed context. To enable the interaction between services offered by arbitrary partners, the platform deploys ontologies to achieve a common vocabulary and semantic rules to express the policies imposed by the networks involved. By applying the platform to typical scenarios from the field of sensor-augmented cargo transportation and logistics, we illustrate its applicability and, through performance evaluation, show a significant increase in process efficiency. Additionally, by means of a generic problem generator, we quantify the scalability of our platform and show the importance of an appropriate priority function, one of the core constituents of our service composition approach. 1. Introduction Over the past few years, network environments have seen a vast increase in density. Now more than ever, wired and wireless networks have become truly colocated infrastructures. Today’s home and office users have grown to depend on Wi-Fi hotspots as well as 3G and 4G cellular networks and also increasingly rely on wireless sensor networks—based on ZigBee, for instance—and interconnected home automation systems. Despite this explosion in both the number of available network technologies and the number of colocated infrastructures, relatively little progress has been made regarding optimized allocation of resources. Interconnected devices usually contend for the same limited amount of bandwidth rather than efficiently sharing it, leading to all too well-known issues such as network latency and congestion. Figure 1 shows a typical office environment, in which several wireless networks coexist with a wired network as well as a public cellular network. Despite the scarcity of their resources, the networks make no effort to cooperate. Consequently, typical issues such as
|