Fog Computing Based Optimized Compressive Data Collection for Big Sensory Data

According to efficient performance requirement of big sensory data compression and collection, this paper proposes a fog computing based optimized compressive data collection scheme to enhance recovery quality of original data. In this scheme, mutual correlations of big sensory data are exploited fully owing to the designed data collection architecture. The data processing of fog node urges the computation capability of edge device can be utilized effectively, and which reduces the amount of data transmission significantly. At the same time the constructed encoding and decoding methods among sensory, fog and cloud nodes guarantee successful performing of conventional compressed sensing (CS) reconstruction algorithm with overwhelming probability. In addition, since recovery error is proportional to the mutual coherence among measurement matrix, network coding (NC) transformation matrix and sparsifying basis, a measurement matrix optimization algorithm is constructed to minimize the mutual coherence for stabilizing and enhancing data recovery quality. The desired solution of mutual coherence can be achieved by integrating the alternating minimization and low-pass filtering methods. Simulation results illustrate that the constructed optimization algorithm can obtain the optimal value of mutual coherence, and reconstruction quality of our developed scheme is higher as compared with other compressive data collection schemes.