Fog-based Optimized Kronecker-Supported Compression Design for Industrial IoT

Although current proposed compression schemes achieve better performance than traditional data compression schemes, they have not fully exploited the spatial and temporal correlations among the data, and the design of the projection (measurement) matrix cannot satisfy the requirement of real scenarios adaptively. Hence, well-designed clustering algorithm is needed to further explore strong spatial correlation, and an adaptive measurement matrix is also needed to ensure exact data recovery. In this paper, we propose a fog-based optimized Kronecker-supported compression scheme to address the above shortcomings and achieve better compression results in the industrial Internet of Things (IIoT). Our scheme first leverages a k-means-based clustering algorithm that explores the spatial correlation among sensory data, which can obtain better compression effects with less communication overhead. It then develops a novel Kronecker-supported two-dimensional data compression mechanism at the fog node, which can ensure the recovery of the original data from the compressed data with high precision; this mechanism can also reduce the communication overhead between fog and cloud nodes significantly. Next, a Kronecker concatenated measurement matrix optimization problem is formulated for meeting the requirement of real scenarios adaptively, and an efficient solution algorithm is developed to obtain the optimal value and ensure that the stringent precision requirements of industrial applications are satisfied. Finally, simulation results show that our proposed scheme is energy efficient and can achieve better clustering results and recovery performance for sensory data, for example, the energy consumption is reduced by 6.8 percent after clustering operation, and the relative reconstruction error of temperature data is improved by an average of 15.8 percent with the same energy saving effect.