Edge computing has recently emerged as an extension to cloud computing for quality of service (QoS) provisioning particularly delay guarantee for delay-sensitive applications. By offloading the computationally intensive workloads to edge servers, the quality of computation experience, e.g., network transmission delay and transmission energy consumption, could be greatly improved. However, the computation resource of an edge server is so scarce that it cannot response quickly to the bursting computation requirements. Accordingly, queueing delay is un-negligible in a computationally intensive environment, e.g., a computing environment consists of Internet of Thing (IoT) applications. In addition, the computation energy consumption in edge servers may be higher than that in clouds when the workload is heavy. To provide QoS for end users while achieving green computing for computing systems, the cooperation between edge servers and the cloud is significantly important. In this paper, the energy-efficient and delay-guaranteed workload allocation problem in an IoT-edge-cloud computing system is investigated. We formulate a delay-based workload allocation problem which suggests the optimal workload allocations among local edge server, neighbor edge servers and cloud toward the minimal energy consumption as well as the delay guarantee. The problem is then tackled using a delay-base workload allocation (DBWA) algorithm based on Lyapunov drift-plus-penalty theory. The theoretical analysis and simulation results have been conducted to demonstrate the efficiency of the proposal for energy efficiency and delay guarantee in an IoT-edge-cloud system.

Fog computing has become the primary infrastructure on the Internet for improving the quality of service. We consider a fog queueing system with limited infrastructure resources to accommodate real-time tasks with heterogeneities in task types and execution deadlines. Owing to the uncertain execution duration, such a fog system should jointly consider fog resource allocation and task offloading to satisfy the deadline requirements. To consider the task heterogeneity, a parallel virtual queue model is applied to buffer each type of task in a separate queue. Subsequently, we use a framework including three parallel algorithms, namely offloading, buffering and resource allocation, to improve resource allocation balance, throughput and task completion ratio. Task offloading is decided according to the task urgencies in terms of the laxity times, which accounts for the deadline, estimated execution time and transmission delay to the cloud. The buffering process rearranges the arriving tasks based on their laxity time and the estimated task execution time at the fog tier. The resource allocation uses an adaptive queue weight based on the Lyapunov drift to avoid task starvation that may lead to a long queueing delay for tasks with long execution time. The simulation results indicate that our proposed policies can avoid task starvation and yields a tradeoff between a high throughput and a high task completion ratio.

This paper studies the delay-optimal virtual machine (VM) scheduling problem in cloud computing systems, which have a constant amount of infrastructure resources such as CPU, memory and storage in the resource pool. The cloud computing system provides VMs as services to users. Cloud users request various types of VMs randomly over time, and the requested VM-hosting durations vary vastly. We first adopt a queueing model for the heterogeneous and dynamic workloads. Then, we formulate the VM scheduling in such a queueing cloud computing system as a decision-making process, where the decision variable is the vector of VM configurations and the optimization objective is the delay performance in terms of average job completion time. A low-complexity online scheme that combines the shortest-job-first (SJF) buffering and min-min best fit (MMBF) scheduling algorithms, i.e., SJF-MMBF, is proposed to determine the solutions. Another scheme that combines the SJF buffering and reinforcement learning (RL)-based scheduling algorithms, i.e., SJF-RL, is further proposed to avoid the potential of job starvation in SJF-MMBF. The simulation results show that SJF-RL achieves its goal of delay-optimal scheduling of VMs by provisioning a low delay at various job arrival rates for various shapes of job length distributions. The simulation results also illustrate that although SJF-MMBF is sub-delay-optimal in a heavy-loaded and highly dynamic environment, it is efficient in throughput performance in terms of the average job hosting rate provisioning.

A two-level voltage source inverter (2L-VSI) when working under over-modulation regulation potentially has low performance, especially during large reference or load changes. To address this problem, a new calculation method is proposed in this work by determining a new reference vector from the boundary of linear modulation zone as a best vector. The reference vector is synthesized by one or two vectors on the boundary line. Therefore, this technique simplifies the calculations to obtain the duty cycles and uses these duty cycles to identify the overmodulation zones. The proposed method is applied to the Modulated Model Predictive Control (MMPC) and the Space Vector Modulation (SVM) respectively in a 2L-VSI. A comprehensive assessment mathematically proves that both methods are in consistent with each other. Simulations and experiments are carried out to show that the proposed methods can reduce the computational burden and implementation complexity and improve the performance of the 2L-VSI in terms of fast dynamic response and smooth transition between the linear-modulation zone and overmodulation zone.