CONDENSE: A Reconfigurable Knowledge Acquisition Architecture for Future 5G IoT

摘要

In forthcoming years, the Internet of Things (IoT) will connect billions ofsmart devices generating and uploading a deluge of data to the cloud. Ifsuccessfully extracted, the knowledge buried in the data can significantlyimprove the quality of life and foster economic growth. However, a criticalbottleneck for realising the efficient IoT is the pressure it puts on theexisting communication infrastructures, requiring transfer of enormous datavolumes. Aiming at addressing this problem, we propose a novel architecturedubbed Condense, which integrates the IoT-communication infrastructure intodata analysis. This is achieved via the generic concept of network functioncomputation: Instead of merely transferring data from the IoT sources to thecloud, the communication infrastructure should actively participate in the dataanalysis by carefully designed en-route processing. We define the Condensearchitecture, its basic layers, and the interactions among its constituentmodules. Further, from the implementation side, we describe how Condense can beintegrated into the 3rd Generation Partnership Project (3GPP) Machine TypeCommunications (MTC) architecture, as well as the prospects of making it apractically viable technology in a short time frame, relying on NetworkFunction Virtualization (NFV) and Software Defined Networking (SDN). Finally,from the theoretical side, we survey the relevant literature on computing"atomic" functions in both analog and digital domains, as well as on functiondecomposition over networks, highlighting challenges, insights, and futuredirections for exploiting these techniques within practical 3GPP MTCarchitecture.