Search

In recent decades, the rapid advances in information technology have promoted a widespread deployment of medical cyber-physical systems (MCPS), especially in the area of digital healthcare. In digital healthcare, medical edge devices empowered by CPU-GPU (Graphics Processing Unit) cooperative multiprocessor system-on-chips (MPSoCs) have a great potential in processing and managing the massive amounts of health-related data. However, most of the existing works on CPU-GPU cooperative MPSoCs cannot maintain a high-precision workload estimation since they simply leverage the worst-case execution cycles to pessimistically predict the workload of digital healthcare applications. Besides, they neglect the personalized requirements of individual healthcare applications and the lifetime reliability demands of heterogeneous CPU-GPU cores. As a result, the normal functions of medical edge devices and the quality-of-services (QoS) of digital healthcare applications are likely to suffer from underlying failures and degradation. In this paper, we explore CPU-GPU cooperative QoS optimization of personalized digital healthcare applications running on reliability guaranteed edge devices with the help of machine learning and swarm intelligence techniques. We first develop two novel predictors: one is a machine learning based predictor for application workload estimation, and the other is a feature-driven predictor for application QoS estimation. We then incorporate the two predictors into a swarm intelligent application scheduling scheme upon the cooperative dual-population evolutionary algorithm (c-DPEA) to find optimal application mapping and partitioning settings. Experimental results show that our solution not only augments the average QoS of whole digital healthcare applications by 15.7%, but also balances the QoS of individual digital healthcare applications by 64.3%.

Cloud computing has attracted wide attention from both academia and industry, since it can provide flexible and on-demand hardware and software resources as services. Energy consumption of cloud servers is the main concern of cloud service providers since reducing energy consumption can bring them a lower operation cost (and hence a higher profit) and alleviate carbon footprints to the environment. Typically, the common power management techniques for enhancing energy efficiency would make cloud servers more vulnerable to soft errors and hence adversely impact the quality of services. Thus, reliability cannot be ignored in the design of methodologies for improving the energy efficiency of cloud servers. In this article, we aim to minimize the energy consumption of cloud servers under the soft-error reliability constraint by configuring the size and speed of servers. Specifically, we first derive the expected reliability based energy consumption of cloud servers to formulate the reliability-constrained energy minimization problem. We then leverage the reinforcement learning technique to obtain an optimal server configuration solution that maximizes system energy efficiency while maintaining the system reliability constraint. Finally, we perform extensive simulation experiments to analyze the relationship between system energy consumption and server configuration under varying arrival rates and execution requirements of service requests. Comparative experiments are also performed to validate the efficacy of the proposed learning-based server configuration scheme. Results show that compared to a benchmark method, the energy saved by the proposed scheme can reach up to 31.5%.

The execution of deep neural network (DNN) algorithms suffers from significant bottlenecks due to the separation of the processing and memory units in traditional computer systems. Emerging memristive computing systems introduce an in situ approach that overcomes this bottleneck. The nonvolatility of memristive devices, however, may expose the DNN weights stored in memristive crossbars to potential theft attacks. Therefore, this article proposes a 2-D permutation-based protection (TDPP) method that thwarts such attacks. We first introduce the underlying concept that motivates the TDPP method: permuting both the rows and columns of the DNN weight matrices. This contrasts with previous methods, which focused solely on permuting a single dimension of the weight matrices, either the rows or columns. While it is possible for an adversary to access the matrix values, the original arrangement of rows and columns in the matrices remains concealed. As a result, the extracted DNN model from the accessed matrix values would fail to operate correctly. We consider two different memristive computing systems (designed for layer-by-layer and layer-parallel processing, respectively), and demonstrate the design of the TDPP method that could be embedded into the two systems. Finally, we present a security analysis. Our experiments demonstrate that TDPP can achieve comparable effectiveness to prior approaches, with a high level of security when appropriately parameterized. In addition, TDPP is more scalable than previous methods and results in reduced area and power overheads. The area and power are reduced by, respectively, $1218\times $ and $2815\times $ for the layer-by-layer system and by $178\times $ and $203\times $ for the layer-parallel system compared to prior works.