Narrow Results

We study the worst-case performance of approximation algorithms for the problem of multiprocessor task scheduling on m identical processors with resource augmentation, whose objective is to minimize the makespan. In this case, the approximation algorithms are given k (k ≥ 0) extra processors than the optimal off-line algorithm. For on-line algorithms, the Greedy algorithm and shelf algorithms are studied. For off-line algorithm, we consider the LPT (longest processing time) algorithm. Particularly, we prove that the schedule produced by the LPT algorithm is no longer than the optimal off-line algorithm if and only if k ≥ m - 2.

Modern computing is a path of violations and transformations coming from an intrinsically concurrent application domain into a sequence of instructions and then back to concurrency with OpenMP, MPI and CUDA/OpenCL. Why we create so many difficulties? Sleptsov Net Computing (SNC) maps a task into an appropriate computing structure implemented as a re-configurable multidimensional sparse matrix of computing memory. It has entirely graphical mass parallel language for concurrent programming and a framework of techniques for concurrent program verification to develop reliable software. Estimated efficiency of SNC is higher than 50% compared to actual less that 1% efficiency of the most powerful supercomputers. It yields hyper-performance capable of efficient control of hyper-sonic objects, colliders, thermonuclear reaction. This paper presents an open source prototype VM and IDE for SNC with a view on upcoming hardware implementation of the corresponding computer.

Cloud is a pay-per use infra-structed which has invited huge clients to cloud, in order to get reliable services without extra maintenance or infrastructure cost. Growing cloud services and migration of small business to cloud have led to high load on cloud service providers, which leads to the need of better optimization algorithm in order to manage the machine better performance and meet better quality of services to the client. Cloud broker or agent plays an important role to achieve this using intelligent task scheduling algorithm to manage the task in such a way to optimize the performance of the cloud services and data center. Currently various optimization algorithms are proposed but most of them take execution time into consideration but not the network delay between the client and the data center. Hence, to overcome this, an optimization algorithm is proposed in this work using execution time and network delay as the optimization parameters. The nature inspired grasshopper optimization is proposed which is compared with the exiting PSO and ACO models to study the performance. The results show that the proposed algorithm out performs the existing models with execution time, total time and network delay as performance metrics. It demonstrates how the suggested, naturally inspired GOA algorithm beats the existing ACO and PSO algorithms for task scheduling in the cloud with scaling loads requiring 5 virtual machines and 2 data centers. More objective functions, such as power and cost-effective algorithms, can be added to the work to further expand it. This study compares the efficacy of several algorithms based on the predetermined criteria while also examining related algorithms. To determine the best algorithm possible, it is intended to offer each approach individually, analyze the results, and plot the resulting graphs.

Dynamic languages are becoming widely used in software engineering due to the flexibility needs of specific software systems. Different example scenarios are the development of dynamic aspect oriented software, Web applications, adaptable and adaptive software or application frameworks. One important lack of these languages is compile-time error detection offered by static languages. However, runtime performance is the most serious limitation to use them in commercial software development. Although JIT optimizing compilation is a widely used technique to speed up intermediate code execution, this has not been successfully applied to dynamically adaptive platforms yet.

We present an approach to improve the structural reflective primitives offered by dynamic languages. Looking for a language-neutral platform with a good JIT-based runtime performance, we have used the Microsoft shared source implementation of the CLI. Its model has been extended with semantics of prototype-based object-oriented models, much more suitable than the class-based one for reflective environments. This augmented semantics together with JIT generation of native code has produced significantly better runtime performance than the existing implementations.

One of the most powerful tools in the hacker's reverse engineering arsenal is the virtual machine. These systems provide a simple mechanism for executing code in an environment in which the program can be carefully monitored and controlled, allowing attackers to subvert copy protection and access trade secrets. One of the challenges for anti-reverse engineering tools is how to protect software within such an untrustworthy environment. From the perspective of a running program, detecting an emulated environment is not trivial: the attacker can emulate the result of different operations with arbitrarily high fidelity. This paper demonstrates a mechanism that is able to detect even carefully constructed virtual environments by focusing on the stochastic variation of system call timings. A statistical technique for detecting emulated environments is presented, which uses a model of normal system call behavior to successfully identify two commonly used virtual environments under realistic conditions.

In geo-distributed cloud systems, a key challenge faced by cloud providers is to optimally tune and configure the underlying cloud infrastructure. An important problem in this context, deals with finding an optimal virtual machine (VM) placement, minimizing costs, while at the same time, ensuring good system performance. Moreover, due to the fluctuations of demand and traffic patterns, it is crucial to dynamically adjust the VM placement scheme over time. It should be noted that most of the existing studies, however, dealt with this problem either by ignoring its dynamic aspect or by proposing solutions that are not suitable for a geographically distributed cloud infrastructure. In this paper, exact as well as heuristic solutions based on Integer Linear programming (ILP) formulations are proposed. Our work focuses also on the problem of scheduling the VM migration by finding the best migration sequence of intercommunicating VMs that minimizes the resulting traffic on the backbone network. The proposed algorithms execute within a reasonable time frame to readjust VM placement scheme according to the perceived demand. Our aim is to use VM migration as a tool for dynamically adjusting the VM placement scheme while minimizing the network traffic generated by VM communication and migration. Finally, we demonstrate the effectiveness of our proposed algorithms by performing extensive experiments and simulation.

Selecting and utilizing proper virtual machines in a virtualized cloud platform to achieve high availability, throughput, reliability, as well as low cost and makespan is very important. The importance lies in the adaptive resource provisioning to satisfy variant of workloads. An Adaptive Accessing Aware Algorithm (A5) is proposed in this paper to deal with this conflicting objective optimization problem. The main strategy of A5 is selecting adaptive upper/lower bound of service capacity to decide the time for scheduling redundant virtual machines and a Pareto-front-based multi-objective optimization method to decide the number of scheduling virtual machines. We carried out experiments in simulation, which show that A5 can achieve much higher performance improvements in four different workload testing environments, compared with other three commonly used methods.

Cyber-physical systems (CPS) tightly integrate cyber and physical components and transcend discrete and continuous domains. It is greatly desired that the synergy between cyber and physical components of CPS is explored even before the complete system is put together. Virtualization has potential to play a significant role in exploring such synergy. In this paper, we propose a CPS virtualization approach based on the integration of virtual machine and physical component emulator. It enables real software, virtual hardware, and virtual physical components to execute in a holistic virtual execution environment. We have implemented this approach using QEMU as the virtual machine and Matlab/Simulink as the physical component emulator, respectively. To achieve high-fidelity between the real system and its virtualization, we have developed a strategy for synchronizing the virtual machine and the physical component emulator. To evaluate our approach, we have successfully applied it to real-world control systems. Experiments results have shown that our approach achieves high-fidelity in capturing dynamic behaviors of the entire system. This approach is promising in enabling early development of cyber components of CPS and early exploration of the synergy of cyber and physical components.

Cloud computing is the distributed computing paradigm continually exposed to different attacks and threats of various origins. The data stored in the cloud framework is easier for external and internal intruders, as access to the cloud framework is done through internet services. Various intrusion detection (ID) methods are developed to detect network intruders in the cloud, but these methods are not primarily effective in generating accurate detection results. Hence, an effective intrusion detection system (IDS) is designed to solve the security issues that unfavorably influence the sustainable development of the cloud and enhance the protection of the cloud from malicious attacks. The IDS is modeled using the proposed Feedback Deer Hunting Optimization (FDHO)-based Deep Residual network to detect network intrusions. However, the proposed FDHO algorithm is designed by integrating Feedback Artificial Tree (FAT) with Deer Hunting Optimization (DHOA), respectively. Moreover, the detection of malicious attacks is carried out using a Deep Residual network that significantly increases the training speed, reduces the computational complexity, and generates effective detection results. The performance of the proposed method is comparatively analyzed with the existing techniques, such as Stacked Contractive Auto-Encoder and Support Vector Machine (SCAE+SVM), Artificial Neural Network with ant bee colony optimization algorithm+fuzzy clustering (ANN+ABC+fuzzy clustering), Improved dynamic immune algorithm (IDIA), and Normalized K-means (NK) clustering algorithm with RNN named, (NK-RNN), FAT-based Deep Residual network, and DHOA-based Deep Residual network using the BoT-IoT dataset and KDD cup-99 dataset. The proposed method achieved outstanding performance by considering the metrics, like specificity, accuracy, and sensitivity, with the values of 0.9526, 0.9498, and 0.9214 using the BoT-IoT dataset.

Previous work [Chrisley & Sloman, 2016, 2017] has argued that a capacity for certain kinds of meta-knowledge is central to modeling consciousness, especially the recalcitrant aspects of qualia, in computational architectures. After a quick review of that work, this paper presents a novel objection to Frank Jackson’s Knowledge Argument (KA) against physicalism, an objection in which such meta-knowledge also plays a central role. It is first shown that the KA’s supposition of a person, Mary, who is physically omniscient, and yet who has not experienced seeing red, is logically inconsistent, due to the existence of epistemic blindspots for Mary. It is then shown that even if one makes the KA consistent by supposing a more limited physical omniscience for Mary, this revised argument is invalid. This demonstration is achieved via the construction of a physical fact (a recursive conditional epistemic blindspot) that Mary cannot know before she experiences seeing red for the first time, but which she can know afterward. After considering and refuting some counter-arguments, the paper closes with a discussion of the implications of this argument for machine consciousness, and vice versa.