A time-efficient data offloading method with privacy preservation for intelligent sensors in edge computing

Abstract

Over the past years, with the development of hardware and software, the intelligent sensors, which are deployed in the wearable devices, smart phones, and etc., are leveraged to collect the data around us. The data collected by the sensors is analyzed, and the corresponding measures will be implemented. However, due to the limited computing resources of the sensors, the overload resource usage may occur. In order to satisfy the requirements for strong computing power, edge computing, which emerges as a novel paradigm, provides computing resources at the edge of networks. In edge computing, the computing tasks could be offloaded from the sensors to the other sensors for processing. Despite the advantages of edge computing, during the offloading process of computing tasks between sensors, private data, including identity information and address, may be leaked, which threatens personal security. Hence, it is important to avoid privacy leakage in edge computing. In addition, the time consumption of offloading computing tasks affects the using experience of customers, and low time consumption makes contributions to the development of applications which are strict with time. To satisfy the above requirements, a time-efficient offloading method (TEO) with privacy preservation for intelligent sensors in edge computing is proposed. Technically, the time consumption and the offloading of privacy data are analyzed in a formalized way. Then, an improved of Strength Pareto Evolutionary Algorithm (SPEA2) is leveraged to optimize the average time consumption and average privacy entropy jointly. At last, abundant experimental evaluations are conducted to verify efficiency and reliability of our method.

Task offloading in Edge and Cloud Computing: A survey on mathematical, artificial intelligence and control theory solutions

“…Apparently, this type of device mobility is considered trivial when it comes to studying the task offloading problem, as it does not impose any type of dynamicity to the network conditions. In certain cases, purely non-mobile devices like stationary IoT sensors are engaged in task offloading at the Edge, [110], [111]. Other works apply this assumption on mobile devices, to reduce the complexity of their proposed offloading solutions; for example, the authors in [112] assume that the statistics of the utilized wireless links remain unchanged during the processing of the users' tasks, reflecting a relatively static or low-mobility scenario.…”

Computing resource allocation strategy considering privacy protection mechanism in edge computing environment

“…Moreover, these three methods almost all show linear growth, the security of data distribution and transmission can be enhanced by increasing the number of tasks. When the number of computing tasks is 5, 10, 15, 20 and 25, the privacy entropy of this method is 14.17, 49.78, 59.32, 68.02 and 83.33 respectively, which is better than the methods based on [26] and [27]. When the number of tasks is the same, although the privacy entropy of method in literature [27] is similar to the calculated value of proposed method, the proposed method performs better in terms of time consumption.…”

A Proactive Management Scheme for Data Synopses at the Edge

“…Game theory also provides a technique to support migration, e.g., the authors of [43] discuss a coalitional game based pricing scheme to reason on the offloading relationship between data and processing nodes. In [42], smart sensors are assumed to be the recording devices and privacy preservation is considered to be the outcome of the proposed approach. A Pareto evolutionary algorithm is proposed to optimize the average time consumption and average privacy entropy jointly.…”