Field Programmable Gate Array (FPGA) has become an efficient accelerator for convolutional neural network (CNN) inference due to its high performance and flexibility. To further improve the performance of CNN inference on FPGAs, an Intellectual Property core (IP core) called Deep Learning Processor Unit (DPU) is released by Xilinx. Unlike previous FPGA-based hardware designs focusing on specific functions or CNNs, the DPU IP supports ample basic functions of deep learning, and the developers can take advantage of DPUs to accelerate CNN inference conveniently. In DPU-based CNN acceleration platform, an encapsulated scheduler plays a crucial role in task scheduling between heterogeneous ARM and multiple DPUs. However, the current scheduler is unsatisfactory because its low schedule efficiency. This paper thus presents a high performance task assignment framework built upon Xilinx hybrid CPU-FPGA MPSoC devices. We first evaluate the main causes of low schedule efficiency problem. Then, we explore the scheduler rules and improve shedule efficiency through purposeful observations and analysis. Finally, we integrate our optimizations, and propose an efficient task assignment framework to maximize performance on DPU-based CNN acceleration platform. Experimental results on Xilinx Zynq UltraScale+ MPSoC zcu104 show that our efficient task assignment framework significantly boosts schedule efficiency for small-scale CNNs (from 36% to 70%), medium-scale CNNs (from 65% to 95%), and large-scale CNNs (from 77% to 99%) compared with original schedule strategy.

With the development of multi-access edge computing (MEC), the cloudlet at the edge of the network can provide nearby high-performance computing services, thus reducing the computational consumption of user equipments (UEs). To provide more real-time computing services to UEs, service providers face the challenge of optimizing the assignment of requests and the allocation of cloudlets’ computing resources to achieve low latency while dealing with the large number of offloaded requests from UEs. Therefore, in this paper, we study the problem of minimizing the total latency to complete the requests in the MEC network by jointly optimizing request assignment and computing resource allocation. The problem is formulated as a mixed integer nonlinear programming (MINLP) problem which is NP-hard. To solve the problem, we decompose the problem into two subproblems which respectively optimize the request assignment and the computing resource allocation. We first deal with the computing resource allocation problem by utilizing the Lagrangian multiplier method, and the resulting solution is applied for the request assignment problem. Then a novel primal-dual based approximation algorithm is devised to address the request assignment problem. Finally, to verify the efficiency of the proposed algorithm, we provide an upper bound on the approximation ratio. The experiment results show that the proposed algorithm outperforms baseline algorithms in terms of total latency, loading balancing, and computational speed.

Multi-Access Edge Computing (MEC) is a promising paradigm that providing cloud-like service for handling the high-complexity and latency-sensitive applications on user equipment (UE) via computation offloading. However, the execution reliability is rarely considered in current MEC studies, which is an important factor to guarantee the quality of service (QoS). For that, this paper considers an energy-saving offloading to satisfy the reliability and latency requirements of the application. Specifically, we formulate an optimization problem to minimize the UE’s energy consumption with reliability and latency constraints. To tackle this NP-hard problem, we first divide the entire application into multiple directed-acyclic-graph-(DAG)-based subtasks, where the subtask can be executed on the UE locally or MEC server remotely. Then, we decompose the overall reliability and latency requirements into multiple constraints for each subtask. Finally, we propose a fast heuristic algorithm to find a solution satisfying the constraints. Simulation results demonstrate the proposed algorithm obtains lower energy consumption compared with the local execution and random assignment and costs less runtime compared with the greedy algorithm.

The large number of mobile-sensing vehicles traveling in cities offer a novel solution to the collection of vast amounts of multimedia data packets. When a vehicle passes through the data center (DC), the collected multimedia data packets will be transmitted to the DC. Due to the mobile characteristic of vehicular sensor networks, the main challenge lies in how to improve the multimedia data delivery ratio and balance the data packet collections. In this paper, in consideration of delay and delivery factors, a novel routing method is proposed to optimize multimedia data collections in mobile sensing vehicles (DDSVs). This method targets at balancing multimedia data collections, improving the delivery ratio of the multimedia data, and reducing the delay ratio in Internet of Things (IoT) networks. In the DDSV scheme, two rules are designed for improving the collection of multimedia data in the IoT. These rules pertain to: 1) data and 2) vehicular priorities. First, different regions hold different priorities of data packet transmission, which can improve the delivery ratio in the suburban areas and reduce the delay ratio. Meanwhile, this scheme is capable of guaranteeing the balance of multimedia data collection. Second, the vehicular priority is proportional to the probability of a vehicle reaching a DC. Therefore, the data should be forwarded to vehicles with higher priorities, that is, the vehicles which are more likely to pass by the DC. By using these two rules, the DDSV scheme can improve the performances of the multimedia data delivery ratio, compared with the conventional optimal vehicular data forwarding scheme. In the simulation experiments, the DDSV scheme utilizes multidatasets of Beijing city, where the average delay for data collection can be decreased by 17.3% in general, and by 41.8% in the suburban areas; the average data delivery ratio can be improved by 16.9% in comparison to the previous studies.

Time-series data is crucial for the development of mobile crowdsensing (MCS). Participant's privacy is one of the major concerns because MCS data often contain sensitive individual information. Existing privacy-preserving mechanisms for time-series data do not preserve salient patterns of the time series and take into account that the perturbed data may fall outside the valid data interval, leading to data distortion. To overcome these deficiencies, we first perform dynamic feature extraction and incorporate an adaptive sampling scheme that is sensitive to the distinction of short-term patterns and stable patterns. Then a Bounded Laplace (BLP) mechanism is adopted with a theoretical guarantee on the data perturbation range so as to address the issue of data going beyond the valid range. We establish theoretically that the proposed Adaptive Sampling and Randomized perturbation mechanism based on dynamic Temporal patterns (ASRT) satisfies the metric-based $w$ -event $\epsilon$ -LDP for privacy protection. Empirical results of extensive experiments on realworld datasets demonstrate that our proposed method is superior to existing protection mechanisms and the efficacy of our ASRT in enhancing data utility without introducing outliers.

Cloud service centers (CSCs) can purchase edge computation resources to improve service quality in mobile cloud-edge computing networks. However, edge servers (ESs) are owned by different entities, and dishonest entities may launch computational forgery attacks, i.e., the ES falsely reports its idle computation resources to win more tasks for increased revenue. Most existing approaches ignore the threat of dishonest ESs. To address the challenges, we design a Trust-based Computation Offloading (TCO) framework. Firstly, we construct the problem for minimizing the difference between the CSC's cost and the expected revenue (DCER), which is a mixed- integer nonlinear programming problem. Secondly, we develop a trust-based computation offloading method that quickly finds a good solution by decomposing the problem. Finally, a two-tier trust evaluation method was proposed to obtain accurate trust values. Experimental results indicate that TCO's comprehensive performance surpasses the benchmarks and significantly enhances computation offloading reliability with a lower performance loss. Notably, tasks are preferentially offloaded to honest ESs to ensure their revenue and promote ESs' honesty under the TCO framework. Additionally, compared with no trust mechanisms, TCO reduces the service timeout count in an interval by 34.37% - 73.80% with a performance loss of only 1.42% - 4.10%.