In this paper, we study secure computing migration scenarios in uncertain environments with the presence of multiple malicious eavesdroppers (MEs). Specifically, when edge servers (ESs) execute tasks delivered by smar...
详细信息
In this paper, we study secure computing migration scenarios in uncertain environments with the presence of multiple malicious eavesdroppers (MEs). Specifically, when edge servers (ESs) execute tasks delivered by smart devices (SDs), SDs may move beyond the coverage of ESs, and computing migration (CM) of unfinished tasks is required to ensure service continuity. There is a risk of privacy leakage during task migration, and MEs use colluding eavesdropping to eavesdrop on the migrated tasks, and we consider eavesdropping on the associated tasks through data sharing among MEs to improve the eavesdropping efficiency. For eavesdropping in MEs, we achieve eavesdropping strikes using cooperative interference by jammers, which benefit by providing jamming services. In addition, uncertain computational scenarios directly affect the efficiency of task execution, and we consider the uncertainty factor in the malicious eavesdropping environment. To this end, this paper proposes the secure computational migration of associative privacy in uncertain environments (SCMAPUE) model, which transforms uncertainties into interval parameters, and optimizes the five objectives of migration delay, maximum completion time, energy consumption, load balancing and migration reliability to achieve efficient task execution and reliable migration. Aiming at the model characteristics, this paper designs an interval many-objective evolutionary algorithm for reliable migration (IMaOEA-RM), which employs a condition-based interval confidence strategy and a multi-access secure migration selection strategy to improve the convergence of the algorithm, and utilizes a dual-migration crossover strategy in order to adjust the jammer partners and improve the population diversity. Simulation results show that our proposed IMaOEA-RM algorithm can provide a more reliable and efficient migration scheme than existing algorithms.
In the context of intelligent manufacturing, machinery and equipment in the industrial manufacturing process form the "industrial Internet of Things." In this process of interlocking production, the requirem...
详细信息
In the context of intelligent manufacturing, machinery and equipment in the industrial manufacturing process form the "industrial Internet of Things." In this process of interlocking production, the requirements for sensor data delay typically reach the millisecond level. Once the data is delayed, the equipment will be shut down, which will make the production difficult or dangerous. In the context of intelligent manufacturing, local computers have been unable to complete calculations and decisions quickly and on time for the huge computing demands. Therefore, the cloud computing migration mode needs to be introduced, but cloud computing migration will cause additional delays. Based on the above problems, this paper designs a cloud cooperative migration strategy based on the information exchange structure of the industrial Internet of Things and the delay mechanism caused by the migration. The feasibility of selecting the optimal migration strategy based on task partitioning is verified by simulation.
Edge intelligence (EI) is a promising paradigm where end devices collaborate with edge servers to provide artificial intelligence services to users. In most realistic scenarios, end devices often move unconsciously, r...
详细信息
Edge intelligence (EI) is a promising paradigm where end devices collaborate with edge servers to provide artificial intelligence services to users. In most realistic scenarios, end devices often move unconsciously, resulting in frequent computing migrations. Moreover, a surge in computing tasks offloaded to edge servers significantly prolongs queuing latency. These two issues obstruct the timely completion of computing tasks in EI-assisted systems. In this paper, we formulate an optimization problem aiming to maximize computing task completion under latency constraints. To address this issue, we first categorize computing tasks into new computing tasks (NCTs) and partially completed computing tasks (PCTs). Subsequently, based on model partitioning, we design a new computing task saving scheme (NSS) to optimize early exit points for NCTs and computing tasks in the queuing queue. Furthermore, we propose a partially completed computing task saving scheme (PSS) to set early exit points for PCTs during computing migrations. Numerous experiments show that computing saving schemes can achieve at least 90% computing task completion rate and up to 61.81% latency reduction compared to other methods.
Edge computing involves shifting computational and storage capabilities from centralized cloud computing centers to the edge of the network, allowing edge servers deployed at the edge to respond to user requests. This...
详细信息
ISBN:
(纸本)9798350328356;9798350328349
Edge computing involves shifting computational and storage capabilities from centralized cloud computing centers to the edge of the network, allowing edge servers deployed at the edge to respond to user requests. This approach eliminates the need for users to traverse the uplink from the edge network to the cloud computing center when initiating a business request, as well as the downlink from the cloud computing center when returning the computed results, significantly reducing transmission time. However, as latency requirements continue to increase, meeting higher latency demands will inevitably lead to the deployment of a large number of edge servers. The consequent energy consumption problem has become a pressing issue for service providers today. Studies have shown that user business requests are unevenly distributed over time, with periods of high and low demand. To cope with the uncertainty of user business requests and respond quickly, many edge servers remain idle or operate at low business volume, leading to significant energy consumption even when idle. This paper proposes a centralized server-controlled edge device hibernation strategy based on upper and lower thresholds, aiming to minimize the overall energy consumption of all edge servers in the system while meeting user latency requirements. By dividing time slots under upper and lower threshold monitoring, the paper analyzes the load conditions of each edge server in the system during each time slot and assigns computing task migration through the central server to reduce the number of idle and low-business volume edge servers, ultimately achieving the minimization of overall system energy consumption.
暂无评论