Research On Fog-Assisted Privacy Preserving Data Collection And Smart Computation Offloading

With the continuous and high-speed development of urban intelligence,a large number of wireless sensor devices are deployed,which makes the sensing data grow explosively.At the same time,due to the complex deployment environment of Io T(Internet of Things),the data collection scheme still faces security threats.The traditional Io T cannot meet the requirements of massive data processing and management.Therefore,for the delay sensitive and compute intensive tasks,how to effectively collect data and achieve the goal of efficient data collection and computing task processing under the premise of ensuring data security has become a research hotspot.In view of the outstanding problems existing in the current data collection scheme in exploring spatio-temporal correlation,optimization of measurement matrix,data privacy protection and computation offloading,the main innovative contributions include the following three aspects:1)Fog Computing Assisted Efficient Privacy Preserving Data Collection for Big Sensory Data: The designed layer-aware fog computing architecture provides effective support for exploring the spatio-temporal correlations and avoids long-distance communication with cloud center for utilizing the computation capabilities of local devices.Meanwhile,the proposed sampling perturbation encryption method protects the data privacy against eavesdropper and active attackers without sacrificing the data correlation,and it facilitates the simultaneous executing of decrypting and decompressing operations for encrypted sampling data.Furthermore,the formulated optimization model for measurement matrix ensures the high precision of data reconstruction.Finally,the simulation reveal that the proposed scheme is an efficient data collection with a strong privacy preservation property.2)Efficient Privacy Preserving Data Collection and Computation Offloading for Fog-Assisted Io T: in the traditional fog computing assistant model,the limited computing resources of a single fog node cannot meet the needs of large-scale task computing.A completion time minimization problem is formulated for fog computation offloading,and an efficient offloading decision algorithm is developed to find the minimum completion time by determining the optimal offloading proportion with joint optimal allocation of local CPU,external CPU and channel bandwidth resources.Finally,the illustrative results reveal that the proposed scheme is an efficient data collection and computation offloading scheme with a strong privacy preservation property.3)Energy and Delay Co-aware Computation Offloading with Deep Learning in Fog Computing Networks: the traditional methods of computing migration need to acquire real-time channel and computing information data,but in reality,such data is often difficult to obtain.An energy and delay co-aware fog computation offloading mechanism is proposed in this dissertation.Specifically,we formulate a weighted sum minimization problem of task completion time and energy consumption at the local fog for achieving efficient task computation.Furthermore,a deep learning based joint offloading decision and resource allocation(Deep learning-based joint offloading decision and resource allocation algorithm,DL-JODRA)algorithm is developed to address such problem.Finally,the extensive simulation results demonstrate that the proposed DL-JODRA can achieve optimal offloading decision rapidly with low computation resource requirement and gain significant reduction on network costs(i.e.,delay and energy)as compared with benchmark methods.