A general cloud firewall framework with dynamic resource allocation

Cloud is becoming a dominant computing platform. However, we see few work on how to protect cloud data centers. As a cloud usually hosts many different type of applications, the traditional packet level firewall mechanism is not suitable for cloud platforms in case of complex attacks. It is necessary to perform anomaly detection at the event level. Moreover, protecting objects are more diverse than the traditional firewall. Motivated by this, we propose a general framework of cloud firewall, which features event level detection chain with dynamic resource allocation. We establish a mathematical model for the proposed framework. Moreover, a linear resource investment function is proposed for economical dynamical resource allocation for cloud firewalls. A few conclusions have been extracted for the reference of cloud service providers and designers.

Role of index bonds in an optimal dynamic asset allocation model with real subsistence consumption

We investigate the role of index bonds in a dynamic consumption and asset allocation model where the rate of real consumption at any given time cannot fall below a fixed level. An explicit form of the optimal consumption and portfolio rule for a class of Constant Relative Risk Aversion (CRRA) utility functions is derived. Consumption increases above the subsistence level only when wealth exceeds a threshold value. Risky investments in equity and nominal bonds are initially proportional to the excess of wealth over a lower bound, and then increase nonlinearly with wealth. The desirability of investing in the risky assets are related to the agent’s risk preference, the equity premium, and the inflation risk premium. The demand for index bonds is also obtained. The results should be useful for the management of defined benefit pension funds, university endowments, and other portfolios which have a withdrawal pre-commitment in real terms.

A profiling based task scheduling approach for multicore network processors

 Multicore network processors have been playing an increasingly important role in computational processes, which emphasize on scalability and parallelism of the systems, in distributed environments especially in Internet-based delay-sensitive applications. It is an important but unsolved issue, however, to efficiently schedule tasks in network processors with multicore and multithread for improving the system throughput as much as possible. Profiling can gather runtime environment information and guide the compiler to optimize programs through scheduling tasks based on the runtime context. This paper proposes a profiling-based task scheduling approach, targeting on improving the throughput of multicore network processor (Intel IXP) systems in the balanced pipeline way. In this work, we investigate a profiling-based task scheduling framework, a task scheduling algorithm, and a set of performance models. Our task allocation scheme maps tasks onto the pipeline architecture and multiple threads of network processors in parallel, which incorporates the profiling context and global thread refinement. We evaluate our task scheduling algorithm by implementing representative network applications on the Intel IXP network processor. Experimental results demonstrate that our algorithm is able to schedule tasks in a balanced pipeline fashion and achieve the high throughput and data transmission rate. Copyright © 2012 John Wiley & Sons, Ltd.

A reinforcement learning approach for robot control in an unknown environment

In this paper, a control approach based on reinforcement learning is present for a robot to complete a dynamic task in an unknown environment. First, a temporal difference-based reinforcement learning algorithm and its evaluation function are used to make the robot learn with its trials and errors as well as experiences. Second, the simulation are carried out to adjust the parameters of the learning algorithm and determine an optimal policy by using the models of a robot. Last, the effectiveness of the present approach is demonstrated by balancing an inverse pendulum in the unknown environment.

A winner determination algorithm for multi-unit combinatorial auctions with reserve prices

Combinatorial auction mechanisms have been used in many applications such as resource and task allocation, planning and time scheduling in multi-agent systems, in which the items to be allocated are complementary or substitutable. The winner determination in combinatorial auction itself is a NP-complete problem, and has attracted many attentions of researchers world wide. Some outstanding achievements have been made including CPLEX and CABOB algorithms on this topic. To our knowledge, the research into multi-unit combinatorial auctions with reserve prices considered is more or less ignored. To this end, we present a new algorithm for multi-unit combinatorial auctions with reserve prices, which is based on Sandholm's work. An efficient heuristic function is developed for the new algorithm. Experiments have been conducted. The experimental results show that auctioneer agent can find the optimal solution efficiently for a reasonable problem scale with our algorithm.

Can we beat DDoS attacks in clouds?

Cloud is becoming a dominant computing platform. Naturally, a question that arises is whether we can beat notorious DDoS attacks in a cloud environment. Researchers have demonstrated that the essential issue of DDoS attack and defense is resource competition between defenders and attackers. A cloud usually possesses profound resources and has full control and dynamic allocation capability of its resources. Therefore, cloud offers us the potential to overcome DDoS attacks. However, individual cloud hosted servers are still vulnerable to DDoS attacks if they still run in the traditional way. In this paper, we propose a dynamic resource allocation strategy to counter DDoS attacks against individual cloud customers. When a DDoS attack occurs, we employ the idle resources of the cloud to clone sufficient intrusion prevention servers for the victim in order to quickly filter out attack packets and guarantee the quality of the service for benign users simultaneously. We establish a mathematical model to approximate the needs of our resource investment based on queueing theory. Through careful system analysis and real-world data set experiments, we conclude that we can defeat DDoS attacks in a cloud environment. © 2013 IEEE.

Interactive effects of GPI stimulation and levodopa on postural control in Parkinson's disease.

INTRODUCTION: Postural instability is a major source of disability in idiopathic Parkinson's disease (IPD). Deep brain stimulation of the globus pallidus internus (GPI-DBS) improves clinician-rated balance control but there have been few quantitative studies of its interactive effects with levodopa (L-DOPA). The purpose of this study was to compare the short-term and interactive effects of GPI-DBS and L-DOPA on objective measures of postural stability in patients with longstanding IPD. METHODS: Static and dynamic posturography during a whole-body leaning task were performed in 10 IPD patients with bilateral GPI stimulators under the following conditions: untreated (OFF); L-DOPA alone; DBS alone; DBS+L-DOPA, and in 9 healthy Control subjects. Clinical status was assessed using the UPDRS and AIMS Dyskinesia Scale. RESULTS: Static sway was greater in IPD patients in the OFF state compared to the Control subjects and was further increased by L-DOPA and reduced by GPI-DBS. In the dynamic task, L-DOPA had a greater effect than GPI-DBS on improving Start Time, but reduced the spatial accuracy and directional control of the task. When the two therapies were combined, GPI-DBS prevented the L-DOPA induced increase in static sway and improved the accuracy of the dynamic task. CONCLUSION: The findings demonstrate GPI-DBS and L-DOPA have differential effects on temporal and spatial aspects of postural control in IPD and that GPI-DBS counteracts some of the adverse effects of L-DOPA. Further studies on larger numbers of patients with GPI stimulators are required to confirm these findings and to clarify the contribution of dyskinesias to impaired dynamic postural control.

Robot coordination for energy-balanced matching and sequence dispatch of robots to events

Given a set of events and a set of robots, the dispatch problem is to allocate one robot for each event to visit it. In a single round, each robot may be allowed to visit only one event (matching dispatch), or several events in a sequence (sequence dispatch). In a distributed setting, each event is discovered by a sensor and reported to a robot. Here, we present novel algorithms aimed at overcoming the shortcomings of several existing solutions. We propose pairwise distance based matching algorithm (PDM) to eliminate long edges by pairwise exchanges between matching pairs. Our sequence dispatch algorithm (SQD) iteratively finds the closest event-robot pair, includes the event in dispatch schedule of the selected robot and updates its position accordingly. When event-robot distances are multiplied by robot resistance (inverse of the remaining energy), the corresponding energy-balanced variants are obtained. We also present generalizations which handle multiple visits and timing constraints. Our localized algorithm MAD is based on information mesh infrastructure and local auctions within the robot network for obtaining the optimal dispatch schedule for each robot. The simulations conducted confirm the advantages of our algorithms over other existing solutions in terms of average robot-event distance and lifetime.

A novel time computation model based on algorithm complexity for data intensive scientific workflow design and scheduling

Scientific workflow offers a framework for cooperation between remote and shared resources on a grid computing environment (GCE) for scientific discovery. One major function of scientific workflow is to schedule a collection of computational subtasks in well-defined orders for efficient outputs by estimating task duration at runtime. In this paper, we propose a novel time computation model based on algorithm complexity (termed as TCMAC model) for high-level data intensive scientific workflow design. The proposed model schedules the subtasks based on their durations and the complexities of participant algorithms. Characterized by utilization of task duration computation function for time efficiency, the TCMAC model has three features for a full-aspect scientific workflow including both dataflow and control-flow: (1) provides flexible and reusable task duration functions in GCE;(2) facilitates better parallelism in iteration structures for providing more precise task durations;and (3) accommodates dynamic task durations for rescheduling in selective structures of control flow. We will also present theories and examples in scientific workflows to show the efficiency of the TCMAC model, especially for control-flow. Copyright©2009 John Wiley & Sons, Ltd.

Dynamic control of skilled and unskilled labour task assignments

Efficient allocation of skilled and non-skilled workers allow a company to improve productivity and usually requires an understanding of personnel capability, operating conditions and resource availability. This paper examines a labour control strategy that optimises labour skill level, utilisation, task execution time and processing error. The proposed controller manages different labour groups in a multiple work cell environment, providing real-time job assignment, as well as guiding and navigation features. These features can be used to enhance the performance of existing MRP-based or Just-In-Time production systems. A discrete event simulation-based manufacturing model has been developed to assess the performance of the labour controller. Experiments conducted for the selected production scenarios have demonstrated a productivity improvement when using the proposed control. A second experiment has shown that when a skilled labour uses the labour controller to guide them through the job, their utilisation also increases. The proposed controller also has potential application in other domains, such as minimising the shopping time at a supermarket

Energy minimization in multi-task software-defined sensor networks

Abstract—
After a decade of extensive research on application-specific wireless sensor networks (WSNs), the recent development of information and communication technologies makes it practical to realize the software-defined sensor networks (SDSNs), which are able to adapt to various application requirements and to fully explore the resources of WSNs. A sensor node in SDSN is able to conduct multiple tasks with different sensing targets simultaneously. A given sensing task usually involves multiple sensors to achieve a certain quality-of-sensing, e.g., coverage ratio. It is significant to design an energy-efficient sensor scheduling and management strategy with guaranteed quality-of-sensing for all tasks. To this end, three issues are investigated in this paper: 1) the subset of sensor nodes that shall be activated, i.e., sensor activation, 2) the task that each sensor node shall be assigned, i.e., task mapping, and 3) the sampling rate on a sensor for a target, i.e., sensing scheduling. They are jointly considered and formulated as a mixed-integer with quadratic constraints programming (MIQP) problem, which is then reformulated into a mixed-integer linear programming (MILP) formulation with low computation complexity via linearization. To deal with dynamic events such as sensor node participation and departure, during SDSN operations, an efficient online algorithm using local optimization is developed. Simulation results show that our proposed online algorithm approaches the globally optimized network energy efficiency with much lower rescheduling time and control overhead.

A dynamic pricing reverse auction-based resource allocation mechanism in cloud workflow systems

Market-oriented reverse auction is an efficient and cost-effective method for resource allocation in cloud workflow systems since it can dynamically allocate resources depending on the supply-demand relationship of the cloud market. However, during the auction the price of cloud resource is usually fixed, and the current resource allocation mechanisms cannot adapt to the changeable market properly which results in the low efficiency of resource utilization. To address such a problem, a dynamic pricing reverse auction-based resource allocation mechanism is proposed. During the auction, resource providers can change prices according to the trading situation so that our novel mechanism can increase the chances of making a deal and improve efficiency of resource utilization. In addition, resource providers can improve their competitiveness in the market by lowering prices, and thus users can obtain cheaper resources in shorter time which would decrease monetary cost and completion time for workflow execution. Experiments with different situations and problem sizes are conducted for dynamic pricing-based allocation mechanism (DPAM) on resource utilization and the measurement of Time∗Cost (TC). The results show that our DPAM can outperform its representative in resource utilization, monetary cost, and completion time and also obtain the optimal price reduction rates.

The metabolic and cognitive energy costs of stabilising a high-energy interlimb coordination task

Kinematic (relative phase error), metabolic (oxygen consumption, heart rate) and attentional (baseline and cycling reaction times) variables were measured while participants practised a high energy-demanding, intrinsically unstable 90° relative phase coordination pattern on independent bicycle ergometers. The variables were found to be strongly inter-correlated, suggesting a link between emerging performance stability with practice and minimal metabolic and attentional cost. The effects of practice of 90° relative phase coordination on the performance of in-phase (0°-phase) and antiphase (180°-phase) coordination were investigated by measuring the relative phase attractor layouts and recording the metabolic and attentional cost of the three coordination patterns before and after practice. The attentional variables did not differ significantly between coordination patterns and did not change with practice. Before practice, the coordination performance was most accurate and stable for in-phase cycling, with antiphase next and 90°-phase the poorest. However, metabolic cost was lower for antiphase than either in-phase or 90°-phase cycling, and the pre-practice attractor layout deviated from that predicted on the basis of dynamic stability as an attractor state, revealing an attraction to antiphase cycling. After practice of 90°-phase cycling, in-phase cycling remained the most accurate and stable, with 90°-phase next and antiphase the poorest, but antiphase retained the lowest metabolic energy cost. The attractor layout had changed, with new attractors formed at the practised 90°-phase pattern and its symmetrical partner of 270°-phase. Considering both the pre- and post-practice results, attractors were formed at either a low metabolic energy cost but less stable (antiphase) pattern or at a more stable but higher metabolic energy cost (90°-phase) pattern, but in neither case at the most stable and accurate (in-phase) pattern. The results suggest that energetic factors affect coordination dynamics and that coordination modes lower in metabolic energy expenditure may compete with dynamically stable modes.

A platform for dynamic organization of agents in agent-based systems

In most agent-based systems, different middle agents are employed to increase their flexibility. However, there are still three issues remain unsolved. In centralized architecture with single middle agent, the middle agent itself is a bottleneck and suffers from single point failure; middle agents in distributed architecture lack capability of dynamic organization of agents; The reliability is not strong because of the single point failure and lack of effective architecture. We introduce a platform with ring architectural model to solve all above problems. In the platform, multiple middle agents are dynamically supported for solving the first problem. For solving the second problem, middle agents dynamically manage the registration and cancellation of service provider agents and application teams, each of which includes a set of closely interacting requester agents to complete an independent task. Redundancy middle agent technique is proposed for solving the third problem. All middle agents are of the feature of proliferation and self-cancellation according to the sensory inputs from their environment. For organizing the middle agents effectively, a ring architectural model is proposed. We demonstrate the applicability of the platform by its application and present experimental evidence that the platform is flexible and robust.

Comparison of corticomotor excitability during visuomotor dynamic and static tasks

The human central nervous system (CNS) has the ability to modulate its activity during the performance of different movements. Recent evidence, however, suggests that the CNS can also modulate its activity in the same movement but with increased precision during a visuomotor static task. This study aimed to extend on these findings by using transcranial magnetic stimulation (TMS) to measure the CNS during the performance of two visuomotor dynamic tasks. Twelve volunteers participated in this study, performing two separate motor tasks. Study I (“Position Tracking”) involved participants to perform a visuomotor tracking task using a dial potentiometer and matching their response icon to the computer generated tracking icon whilst holding a pincer grip. Study II (“Force Tracking”) involved participants to perform a similar visuomotor tracking task by applying or releasing pressure against a fixed force transducer. Tasks were conducted at two speeds (“slow” being one tracking cycle in 10 s; and “fast” being two tracking cycles in 10 s) and compared to a visuomotor static task at a similar muscle contraction level. Results showed corticospinal changes with significant increases (p = 0.002) in excitability demonstrated during Study I (42.3 ± 16.8%) and Study II (56.3 ± 34.2%) slow speed tasks. Moreover, significant reduction in corticospinal inhibition was also observed during both tracking tasks at slow (59.3 ± 13.7%; p = 0.001) and fast speeds (31.9 ± 12.3%; p = 0.001). The findings may provide information on the underlying physiology during the early stages of motor skill acquisition.