A computational model to support in-network data analysis in federated ecosystems

Software-defined networks (SDNs) have proven to be an efficacious tool for undertaking complex data analysis and manipulation within data intensive applications. SDN technology allows us to separate the data path from the control path, enabling in-network processing capabilities to be supported as data is migrated across the network. We propose to leverage software-defined networking (SDN) to gain control over the data transport service with the purpose of dynamically establishing data routes such that we can opportunistically exploit the latent computational capabilities located along the network path. This strategy allows us to minimize waiting times at the destination data center and to cope with spikes in demand for computational capability. We validate our approach using a smart building application in a multi-cloud infrastructure. Results show how the in-transit processing strategy increases the computational capabilities of the infrastructure and influences the percentage of job completion without significantly impacting costs and overheads. We present a model that leverages software-defined networks to opportunistically exploit the latent computational capabilities located along the data path.Our model is able to use alternative methods of computation when our primary method cannot be used due to SLA constraints. In this paper we use a neuronal network approximation model as alternative to EnergyPlus.The description of two algorithms that introduces how the neuronal network model is trained and how neuronal network jobs are deployed across in-transit resources.A new set of experiments to validate and evaluate the effect that our new strategy has in the energy optimization of smart buildings.