In the Fog Computer (FC), the process of data is prone to problems such as low data similarity and poor data tolerance. This paper proposes a hierarchical data job scheduling strategy Based on Intelligent Sensor-Cloud in Fog Computer (HDJS). HDJS dynamically adjusts the priority of the job to avoid job starvation and maximize the use of resources, uses the key frame to the resource occupied information, distributes the frame sequence to the unit, and then combines the intra frame distribution strategy to balance the load between the nodes. The experimental results show our proposed strategy may be possible to avoid the operation of hunger and resource fragmentation problems, make full use of the advantages of multi-core and multi-thread, improve system resource utilization, and shorten the execution time and response time.

When the nodes in the network are deployed in the target area with an appropriate density, the effective aggregation and transmission of the data gathered in the monitoring area remain to be solved. The existing Compressed Sensing (CS) based on data aggregation schemes are accomplished in a centralized manner and the Sink node achieves the task of data aggregation. However, these existing schemes may suffer from load imbalance and coverage void issues. In order to address these problems, we propose a Compressed Sensing based on Fault-tolerant Correcting Data Aggregation (CS-FCDA) scheme to accurately reconstruct the compressed data. Therefore, the network communication overhead can be greatly reduced while maintaining the quality of the reconstructed data. Meanwhile, we adopt the node clustering mechanism to optimize and balance the network load. It is shown via simulation results, compared with other data aggregation schemes, that the proposed scheme shows obvious improvement in terms of the Fault-tolerant correcting capability and the network energy efficiency of the data reconstruction.