Seokho Son

A Price- and-Time-Slot-Negotiation Mechanism for Cloud Service Reservations

When making reservations for Cloud services, consumers and providers need to establish service-level agreements through negotiation. Whereas it is essential for both a consumer and a provider to reach an agreement on the price of a service and when to use the service, to date, there is little or no negotiation support for both price and time-slot negotiations (PTNs) for Cloud service reservations. This paper presents a multi-issue negotiation mechanism to facilitate the following: 1) PTNs between Cloud agents and 2) tradeoff between price and time-slot utilities. Unlike many existing negotiation mechanisms in which a negotiation agent can only make one proposal at a time, agents in this work are designed to concurrently make multiple proposals in a negotiation round that generate the same aggregated utility, differing only in terms of individual price and time-slot utilities. Another novelty of this work is formulating a novel time-slot utility function that characterizes preferences for different time slots. These ideas are implemented in an agent-based Cloud testbed. Using the testbed, experiments were carried out to compare this work with related approaches. Empirical results show that PTN agents reach faster agreements and achieve higher utilities than other related approaches. A case study was carried out to demonstrate the application of the PTN mechanism for pricing Cloud resources.

Negotiation-Based Flexible SLA Establishment with SLA-driven Resource Allocation in Cloud Computing

As various consumers tend to use personalized Cloud services, Service Level Agreements (SLAs) emerge as a key aspect in Cloud and Utility computing. The objectives of this doctoral research are 1) to support a flexible establishment of SLAs that enhances the utility of SLAs for both providers and consumers, and 2) to manage Cloud resources to prevent SLA violations. Because consumers and providers may be independent bodies, some mechanisms are necessary to resolve different preferences when they establish a SLA. Thus, we designed a Cloud SLA negotiation mechanism for interactive and flexible SLA establishment. The novelty of this SLA negotiation mechanism is that it can support advanced multi-issue negotiation that includes time slot and price negotiations. In addition, to prevent SLA violations, we provided a SLA-driven resource allocation scheme that selects a proper data center among globally distributed centers operated by a provider. Empirical results showed that the proposed SLA negotiation mechanism supports faster agreements and achieves higher utilities. Also, the proposed SLA-driven resource allocation scheme performs better in terms of SLA violations and the providers profits.

Adaptive and similarity-based tradeoff algorithms in a price-timeslot-QoS negotiation system to establish cloud SLAs

Since participants in a Cloud may be independent bodies, some mechanisms are necessary for resolving the different preferences to establish a service-level agreement (SLA) for Cloud service reservations. Whereas there are some mechanisms for supporting SLA negotiation, there is little or no negotiation support involving price, time slot, and QoS issues concurrently for a Cloud service reservation. For the concurrent price, timeslot, and QoS negotiation, a tradeoff algorithm to generate and evaluate a proposal which consists of price, timeslot, and QoS proposals is necessary. The contribution of this work is designing a multi-issue negotiation mechanism to facilitate 1) concurrent price, time slot, and QoS negotiations including the design of QoS utility functions and 2) adaptive and similarity-based trade-off proposals for price, time slots, and level of QoS issues. The tradeoff algorithm referred to as “adaptive burst mode” is especially designed to increase negotiation speed, total utility, and to reduce computational load for evaluating proposals by adaptively generating concurrent set of proposals. The empirical results obtained from simulations carried out using an agent-based testbed suggest that using the negotiation mechanism, (i) a consumer and a provider agent have a mutually satisfying agreement on price, time slot, and QoS issues in terms of the aggregated utility and (ii) the fastest negotiation speed with (iii) comparatively lower number of evaluated proposals in a negotiation.

An Adaptive Tradeoff Algorithm for Multi-issue SLA Negotiation

Since participants in a Cloud may be independent bodies, mechanisms are necessary for resolving different preferences in leasing Cloud services. Whereas there are currently mechanisms that support service-level agreement negotiation, there is little or no negotiation support for concurrent price and timeslot for Cloud service reservations. For the concurrent price and timeslot negotiation, a tradeoff algorithm to generate and evaluate a proposal which consists of price and timeslot proposal is necessary. The contribution of this work is thus to design an adaptive tradeoff algorithm for multi-issue negotiation mechanism. The tradeoff algorithm referred to as “adaptive burst mode” is especially designed to increase negotiation speed and total utility and to reduce computational load by adaptively generating concurrent set of proposals. The empirical results obtained from simulations carried out using a testbed suggest that due to the concurrent price and timeslot negotiation mechanism with adaptive tradeoff algorithm: 1) both agents achieve the best performance in terms of negotiation speed and utility; 2) the number of evaluations of each proposal is comparatively lower than previous scheme (burst-N).

A delay compensation scheme based on prediction for networked haptic collaboration system

Network delay in haptic-based CVEs (collaborative virtual environments) severely deteriorates the haptic interaction quality (e.g., larger force feedback than real). In order to compensate this delay effect, existing studies dynamically change spring and damper coefficients according to the network delay. However, it is difficult to choose proper coefficients to offset the delay effect by precisely reflecting virtual object characteristics. In this paper, a new delay-compensation scheme based on the force feedback prediction is proposed to improve the force feedback experience. By predicting the virtual object movements and force feedback, the proposed scheme in client side provides timely force feedback to a user. Then, it gradually converges to real (but delayed) information from the server in order to maintain the consistency of virtual environment. According to the experiment results, the proposed scheme can improve the haptic interaction quality by providing more realistic force feedback similar to that of no network delay.

A Negotiation Mechanism that Facilitates the Price-Timeslot-QoS Negotiation for Establishing SLAs of Cloud Service Reservation

A negotiation mechanism is essential to establish a service level agreement between Cloud participants who need to resolve different preferences of a Cloud service. Whereas there are some mechanisms for supporting service level agreement negotiation, there is little or no negotiation support of price, time slot, and QoS issues concurrently for a Cloud service reservation. The contribution of this work is designing a multi-issue negotiation mechanism to facilitate 1) concurrent price, time slot, and QoS negotiations between agents representing Cloud participants and 2) trade-off proposals for price, time slots, and level of QoS issues. The ideas of the negotiation mechanism are implemented in an agent-based Cloud testbed, and the empirical results obtained from simulations carried out using the testbed suggest that using the concurrent negotiation mechanism, (i) a consumer and a provider agent have a mutually satisfying agreement on price, time slot, and QoS issues in terms of the aggregated utility, and (ii) both agents achieved the highest negotiation speed among related approaches.

Relaxed Time Slot Negotiation for Grid Resource Allocation

Since participants in a computational grid may be independent bodies, some mechanisms are necessary for resolving the differences in their preferences for price and desirable time slots for utilizing/leasing computing resources. Whereas there are mechanisms for supporting price negotiation for grid resource allocation, there is little or no negotiation support for allocating mutually acceptable time slots for grid participants. The contribution of this work is designing a negotiation mechanism for facilitating time slot negotiations between grid participants. In particular, this work adopts a relaxed time slot negotiation protocol designed to enhance the success rate and resource utilization level by allowing some flexibility for making slight adjustments following a tentative agreement for a mutually acceptable time slot. The ideas of the relaxed time slot negotiation are implemented in an agent-based grid testbed, and empirical results of the relaxed time slot negotiation mechanism carried out, (i) a consumer and a provider agent have a mutually satisfying agreement on time slot and price, (ii) consumer agents achieved higher success rates in negotiation, and (iii) provider agents achieved higher utility and resource utilization of overall grid.

Cost-effective haptic-based networked virtual environments with high-resolution tiled display

In this paper, a haptic-based NVE (networked virtual environment) supporting high-resolution tiled display is proposed with a resource management scheme for future home applications such as a haptic-based networked game. Although NVEs with haptic interaction and immersive display have been developed in previous studies, they usually require expensive system configurations. In order to implement a cost-effective system, our proposed design includes a tiled display supporting high-resolution with several low-cost LCDs. The display nodes of the tiled display also have low processing and storage resource requirements because they only need to handle display-ready pixels received from the application node. The proposed resource management scheme, called as an object-based display scheme, reduces the resource requirements of the application node that would otherwise require significant resources to manage all the display nodes and to provide a user with haptic feedback. The proposed scheme segments graphic scenes into several pixelated virtual objects and assigns different frame rates to each object according to the interest of user. Experimental results confirm that the proposed scheme reduces the required network bandwidth and appropriately assigns the limited processing resources to graphic and haptic renderings for a high-level visual and haptic quality.

Interactive Scientific Visualization of High-resolution Brain Imagery Over Networked Tiled Display

In this paper, we discuss our on-going efforts for an interactive scientific visualization of high-resolution brain imagery over networked tiled display. It targets to visualize a brain in both 2D and 3D. It also supports multiple highresolution displays of brain images by integrating networked tiled display while providing interactive control of display resolution and view direction. In order to construct an appropriate visualization system for brain imaging researches, we study and compare existing visualization systems using a networked tiled display. Based on this comparison, we integrate visualization features on our brain visualization system. Finally, to verify the usefulness of the proposed approach, an initial implementation of EIT brain image visualization is being made.

Networked Haptic Virtual Environments Supporting Ultra High Resolution Display

With HPC (high performance computing) and scientific computing, it has been possible to produce a large amount of data. To easily analyze those data and collaborate on it, visualization in terms of ultra high resolution is desired. However, in order to combine a HPC system with a high resolution display system, high system resource is required. This paper shows an example of a system combining both a haptic system requiring high speed computing and a ultra high resolution display system. Thus, in this paper, we realize a networked haptic virtual environment system over ultra high resolution tiled display. With a networked haptic virtual environment supporting ultra high resolution display, users can feel sense of touch with haptic device and see visuals in ultra high resolution manner with network tiled display when users collaborate in shared virtual environment together. In addition, in this paper, a frame rate control scheme, making the networked haptic virtual environment system over ultra high resolution display stable, is proposed.