Peter Hillmann

Simulation and optimization of content delivery networks considering user profiles and preferences of internet service providers

A Content Delivery Network (CDN) is a dynamic and complex service system. It causes a huge amount of traffic on the network infrastructure of Internet Service Providers (ISPs). Oftentimes, CDN providers and ISPs struggle to find an efficient and appropriate way to cooperate for mutual benefits. This challenge is key to push the quality of service (QoS) for the end-user. We model, simulate, and optimize the behavior of a CDN to provide cooperative solutions and to improve the QoS. Therefor, we determine reasonable server locations, balance the amount of servers and improve the user assignments to the servers. These aspects influence run time effects like caching at the server, response time and network load at specific links. Especially, user request history and profiles are considered to improve the overall performance. Since we consider multiple objectives, we aim to provide a diverse set of pareto optimal solutions using simulation based optimization.

A novel approach to solve K-center problems with geographical placement

The facility location problem is a well-known challenge in logistics that is proven to be NP-hard. In this paper we specifically simulate the geographical placement of facilities to provide adequate service to customers. Determining reasonable center locations is an important challenge for a management since it directly effects future service costs. Generally, the objective is to place the central nodes such that all customers have convenient access to them. We analyze the problem and compare different placement strategies and evaluate the number of required centers. We use several existing approaches and propose a new heuristic for the problem. For our experiments we consider various scenarios and employ simulation to evaluate the performance of the optimization algorithms. Our new optimization approach shows a significant improvement. The presented results are generally applicable to many domains, e.g., the placement of military bases, the planning of content delivery networks, or the placement of warehouses.

Dragoon: Advanced modelling of IP geolocation by use of latency measurements

IP Geolocation is a key enabler for many areas of application like determination of an attack origin, targeted advertisement, and Content Delivery Networks. Although IP Geolocation is an ongoing field of research for over one decade, it is still a challenging task, whereas good results are only achieved by the use of active latency measurements. Nevertheless, an increased accuracy is needed to improve service quality. This paper presents an novel approach to find optimized Landmark positions which are used for active probing. Since a reasonable Landmark selection is important for a highly accurate localization service, the goal is to find Landmarks close to the target with respect to the infrastructure and hop count. Furthermore, we introduce a new approach of an adaptable and more accurate mathematical modelling of an improved geographical location estimation process. Current techniques provide less information about solving the Landmark problem as well as are using imprecise models. We demonstrate the usability of our approach in a real-world environment and analyse Geolocation for the first time in Europe. The combination of an optimized Landmark selection and advanced modulation results in an improved accuracy of IP Geolocation.

An efficient solution for K-center problems

The facility location problem is a well-known challenge in logistics that is proven to be NP-hard. In this paper we specifically simulate the geographical placement of facilities to provide adequate service to customers. We analyze the problem and compare different placement strategies and evaluate the number of required centers. We simulate several existing approaches and propose a new heuristic for the problem.

Tracemax: A novel single packet IP traceback strategy for data-flow analysis

The identification of the exact path that packets are routed on in the network is quite a challenge. This paper presents a novel, efficient traceback strategy named Tracemax in context of a defense system against distributed denial of service (DDoS) attacks. A single packet can be directly traced over many more hops than the current existing techniques allow. In combination with a defense system it differentiates between multiple connections. It aims to letting non-malicious connections pass while bad ones get thwarted. The novel concept allows detailed analyses of the traffic and the transmission path through the network. The strategy can effectively reduce the effect of common bandwidth and resource consumption attacks, foster early warning and prevention as well as higher the availability of the network services for the wanted customers.

Modelling of IP geolocation by use of latency measurements

IP Geolocation is a key enabler for many areas of application like Content Delivery Networks, targeted advertisement and law enforcement. Therefore, an increased accuracy is needed to improve service quality. Although IP Geolocation is an ongoing field of research for over one decade, it is still a challenging task, whereas good results are only achieved by the use of active latency measurements. This paper presents an novel approach to find optimized Landmarks positions which are used for active probing and introduce an improved location estimation. Since a reasonable Landmark selection is important for a highly accurate localization service, the goal is to find Landmarks close to the target with respect to the infrastructure and hop count. Current techniques provide less information about solving this problem as well as are using imprecise models. We demonstrate the usability of our approach in a real-world environment. The combination of an optimized Landmark selection and advanced modulation results in an improved accuracy of IP Geolocation.

YANG2UML: Bijective transformation and simplification of YANG to UML

Specifically designed to exchange configuration information from a management platform to network components, the XML-based NETCONF protocol has become widely used. In combination with NETCONF, YANG is the corresponding protocol that defines the associated data structures, supporting virtually all network configuration protocols. YANG itself is a semantically rich language, which - in order to facilitate familiarization with the relevant subject - is often visualized using UML to involve other experts or developers and to support them by their daily work (writing applications which make use of YANG/NETCONF). To support this process, this paper presents an novel approach to optimize and simplify YANG data models, as current solutions tend to produce very complex UML diagrams. Therefore, we have (i) defined a bidirectional mapping of YANG to UML, (ii) developed a strategy to reduce the numbers of objects, and (iii) created a tool that renders the created UML diagrams, closing the gap between technically improved data models and their human readability.

Optimized travel to meetings on a common location of geographical distributed participants

Members of international organizations often meet in person at a common location for discussions. There is frequently disagreement over the place and time of the meeting due to the different travel efforts of the members. They usually travel by plane and their travel expenses depend on the flight connections. This paper presents an approach to calculate the optimized location and time, where and when distributed partners should meet. The presented system considers the requirements and specifications of each individual member. It respects earliest starting time of an event and non night flights. The optimized result is evaluated with regard to multiple objectives. We focus on the minimization of costs and travel time. Our search algorithm identifies individual travel data for all members for a potential event. The output provides recommendations for the global best appointments and offers further information for the partners. Our system saves expenses and time for all members and allows adjustment as well as compensation.

Evaluation of the general applicability of Dragoon for the k -center problem

The k-center problem is a fundamental problem we often face when considering complex service systems. Typical challenges include the placement of warehouses in logistics or positioning of servers for content delivery networks. We previously have proposed Dragoon as an effective algorithm to approach the k-center problem. This paper evaluates Dragoon with a focus on potential worst case behavior in comparison to other techniques. We use an evolutionary algorithm to generate instances of the k-center problem that are especially challenging for Dragoon. Ultimately, our experiments confirm the previous good results of Dragoon, however, we also can reliably find scenarios where it is clearly outperformed by other approaches.

Modeling the Location Selection of Mirror Servers in Content Delivery Networks

For a provider of a Content Delivery Network (CDN), the location selection of mirror servers is a complex optimization problem. Generally, the objective is to place the nodes centralized such that all customers have convenient access to the service according to their demands. It is an instance of the k-center problem, which is proven to be NP-hard. Determining reasonable server locations directly influences run time effects and future service costs. We model, simulate, and optimize the properties of a content delivery network. Specifically, considering the server locations in a network infrastructure with prioritized customers and weighted connections. A simulation model for the servers is necessary to analyze the caching behavior in accordance to the targeted customer requests. We analyze the problem and compare different optimization strategies. For our simulation, we employ various realistic scenarios and evaluate several performance indicators. Our new optimization approach shows a significant improvement. The presented results are generally applicable to other domains with k-center problems, e.g., the placement of military bases, the planning and placement of facility locations, or data mining.