Distributed computational model for shared processing on Cyber-Physical System environments

Cyber-Physical Systems typically consist of a combination of mobile devices, embedded systems and computers to monitor, sense, and actuate with the surrounding real world. These computing elements are usually wireless, interconnected to share data and interact with each other, with the server part and also with cloud computing services. In such a heterogeneous environment, new applications arise to meet ever-increasing needs and these are an important challenge to the processing capabilities of devices. For example, automatic driving systems, manufacturing environments, smart city management, etc. To meet the requirements of said application contexts, the system can create computing processes to distribute the workload over the network and/or a cloud computing server. Multiple options arise in relation to what network nodes should support the execution of the processes. This paper focuses on this problem by introducing a distributed computational model to dynamically share these tasks among the computing nodes and considering the inherent variability of the context in these environments. Our novel approach promotes the integration of the computing resources, with externally supplied cloud services, to fulfill modern application requirements. A prototype implementation for the proposed model has been built and an application example has been designed to validate the proposal in a real working environment.