York Tüchelmann

A Trust Model Considering the Aspects of Time

Today, many trust models do exist which are based on bayesian systems, discrete values or the probability theory. Some of them are generic while others are specifically designed for certain applications such as p2p or ecommerce. What all these models have in common is the intention to map the human understanding of trust in a computational model. Some aspects of trust such as the direct trust towards another member or the reputation of said member have already been considered by fellow researchers while aspects such as sympathy or gut feeling will probably never be sufficiently integrated. The aspect, that experiences may age or be forgotten are currently incorporated in only few models. However, to our understanding the current approaches to aging are not satisfactory. We will point out the weak spot of the current aging approaches and present a refined version including the not yet discussed aspect of inactivity. Our proposed trust model incorporates this new approach, including methods on how to handle temporarily inactive members as well as the context-dependent computation of trust and reputation resulting in the valuation of a members trustworthiness. Due to the generic approach, our proposed trust model can both be used for centralized and decentralized applications.

Context-Aware QoS Control for Wireless Mesh Networks of UAVs

Unmanned Aerial Vehicles (UAVs) can be used in a wide application range. For example, UAVs are utilized to observe critical areas in disaster situations without jeopardizing individuals or to extend the transmission range of communication networks. Connecting a set of UAVs with each other within a Wireless Mesh Network helps to increase the coverage of the observable area. Due to their limited performance and energy resources and, thereby, restricted communication capabilities, a tailored QoS management scheme has to be used to optimize occurring data flows in these networks. We present a QoS control scheme that works on the basis of process-patterns, each describing the context-dependent behavior of UAVs according to the execution order of services for different situations. Furthermore, the logical communication path is optimized within the mesh network based on each nodes areal position using a dynamic hierarchical communication structure. Thereby, performance and fairness within a network of UAVs can be increased demand-actuated.

A business process aware semantic QoS provisioning scheme

The execution of business processes is supported by running many applications within a corporate network. Each business process includes several tasks which have different priorities expressing each tasks relevance in helping to achieve the related business objectives. The provisioning of a certain level of QoS according to the requirements of an entire business process can hardly be accomplished using existing QoS provisioning schemes because these do not account for the dynamic requirements introduced by business processes. The definition of a certain level of QoS using the existing models is just driven by technical aspects of the running applications. In this paper we present a novel business process aware semantic QoS provisioning scheme that accounts for the dynamic requirements and permits application-independent usage. In the business world the priority of a task depends on the current context it is executed in. So equal tasks may need different conditions of QoS in different situations, which can be characterized by the tasks that ran before or run in parallel. Therefore, the semantic behavior is based on the entire business processes as input for the QoS provisioning process. With the proposed QoS provisioning scheme a fair application conditioning can be achieved that is much closer to the business requirements on QoS. For the validation of the scheme, it has been implemented as a QoS-driver in different operating systems.

A survey of security issues in trust and reputation systems for E-commerce

Trust and reputation systems are always subject to attacks if an adversary can gain a benefit in doing so. The list of different attacks against them is extensive. Attacks like bad mouthing, newcomer, sybil, collusion and many more are subject to current research. Some of them present methods that allow to detect adversarial behaviour, hence providing protection against attacks. However, smart adversaries will adapt their behaviour strategies to the existing protection mechanisms and bypass some of the security methods. In this paper, we discuss the options available to adversaries for achieving their goal: Gaining a benefit. For this, we analyse the wellknown attacks and propose security methods which provide resistance or immunity against them at any time, hence independently from the cleverness or strategy of adversaries. Our second focus is to elaborate on the problem of reliably identifying an adversary amongst transacting participants and its influence on possible security methods.

Trust-based resource allocation and evaluation of workflows in distributed computing environments

An optimal resource allocation is desired to increase the efficiency of systems processing business or scientific workflows. These systems include the processing of workflows in distributed computing environments such as grid or cloud computing. Current approaches used in this systems consider QoS-requirements as quality, speed or costs in the resource allocation process and just select the resources that satisfy these requirements. However, the selection of a resource should not be based solely on whether a resource meets the QoS-requirements or not, because it does not imply that a task is processed satisfactory by the selected resource according to its content. To evaluate resources regarding this aspect, trust models can be used. But current trust models are not specifically designed to model trust in distributed computing environments, hence handling the dynamics of business or scientific workflows that constantly change their requirements and conditions. In this paper, we present approaches which improve current trust models according to the problems mentioned. Thereby, the degree of automation in the trust evaluation process will be increased as well. Finally, in combination with an adjusted trust level workflow, the presented approach allows an optimal resource allocation for grid or cloud computing service providers.

A distributed fair congestion avoidance protocol

Congestion is a particular problem in computer networks because all nodes compete with each other for the available resources. If congestion occurs, packets cannot be delivered anymore and the achieved data rate decreases significantly for all nodes. Different approaches for congestion avoidance and control exist. Nevertheless, a new proactive approach that works independent of the congestion control or avoidance capabilities of Transport Layer protocols and the available resources may be superior. In this paper, we present DiFCAP, a proactive Distributed Fair Congestion Avoidance Protocol that works independent of the congestion handling capabilities of Transport Layer protocols and the available resources. DiFCAP uses a transmission notification mechanism that leads to fair throttling of outgoing transmissions of all nodes within a predefined group. Thereby, congestion can be partially avoided and the packet drop rate can be reduced. The performance improvements that can be achieved using DiFCAP are shown through simulations.

I-DWRR — An insolvency enabled scheduling scheme extending Deficit Weighted Round Robin

The allocation of network resources to flows within a computer network is performed using scheduling algorithms with the aim of enabling every flow to receive the required resources to perform well. One of several algorithms proposed in the last decades is the well-known Deficit (Weighted) Round Robin (D(W)RR) scheduling algorithm proposed by Shreedhar and Varghese [1]. It has a low complexity, but at the same time allows fair and weighted sharing of limited resources. Nevertheless, DWRR does not work deadline compliant and active handling of nearly over-delayed packets is not considered. In this paper, we present a novel insolvency enabled extension of the DWRR scheduling algorithm called I-DWRR. It reduces the number of deadline violations by preventing them using an innovative mechanism called Queue Insolvency (QI). The proposed extension provides a lower packet-loss rate for multi-queue scenarios in comparison to DWRR while keeping the occurring latency equal to DWRR. The algorithm and its benefits have been validated through a broad simulation study.

On the performance of host-based business process aware QoS management

In general, network traffic is classified and marked at the edge- or ingress-routers of a transit network to permit different levels of QoS when using the DiffServ architecture. Thus, the core-nodes of a network are able to handle the traffic accordingly. Problems in the process of identification of traffic flows and their associated applications, for example because of encryption, avoid the classification of network traffic. This can be improved by relocating the functions of classifying and marking towards the network traffic generating hosts. The great benefit of the relocation is that applications can be identified in any case. In addition, pre-shaping of network traffic becomes possible. Unfortunately, the set of rules for classification and marking on hosts is always static in its behavior so that it would not be possible to map dynamics, for example, of business processes to the set of rules or its interpreter. Therefore, it has to be possible that the marking of packets depends on their temporal execution context and, thereby, on the business processes. In this paper, we present an efficient solution that considers business processes in host-based QoS management systems. The applied QoS management system considers the dynamic requirements of business processes and works application-independent. The performance of the system, introduced by its efficient design, is analyzed and its benefits are discussed.

Improving the Distributed Fair Congestion Avoidance Protocol for Home Area Networks with Internet Access Links

If network congestion occurs, packets cannot be delivered timely, the data rate decreases significantly and the required level of QoS cannot be achieved for all nodes. Especially in Home Area Networks (HANs) with limited uplink bandwidth for internet access, congestion is a major problem. Different approaches for congestion aware link sharing and QoS provisioning exist. Also the Distributed Fair Congestion Avoidance Protocol has been proposed for this purpose, but has to be modified to work efficient in HANs. In this paper, we present an enhanced version of the former proposed DiFCAP protocol which works proactive and independent of the congestion handling capabilities of Transport Layer protocols.

Understanding the advantage of business-driven QoS provisioning on the performance of networks

Converged networks carry different types of media using one transmission medium. Fair and target-oriented sharing of a mediums limited resources among applications using a converged network is still a challenge. Quality-of-Service (QoS) architectures try to overcome this problem by classifying applications and permitting differentiated amounts of available resources to each of them. Our novel approach presented in former work considers the dynamics of applications based on business processes. Instead of working edge-based, this approach works host-based because the identification of applications is more precise on hosts. In this paper, we present the results of a performance analysis. Thereby, the advantage of the business-driven approach on the performance of networks is shown. Instead of just simulating the behavior of our approach, a real testbed is used in which several measurements considering the occurrence of cross-traffic are performed. It is shown that our approach performs well in realistic network environments and does not affect the network in a negative way, but improves the performance according to business processes.