TY - GEN AU - Roeske, Daniel ID - 361 TI - Simulating load-dependent operation of picocells ER - TY - CONF AB - In the near future many more compute resources will be available at different geographical locations. To minimize the response time of requests, application servers closer to the user can hence be used to shorten network round trip times. However, this advantage is neutralized if the used data centre is highly loaded as the processing time of re- quests is important as well. We model the request response time as the network round trip time plus the processing time at a data centre.We present a capacitated facility location problem formal- ization where the processing time is modelled as the sojourn time of a queueing model. We discuss the Pareto trade-off between the number of used data centres and the resulting response time. For example, using fewer data centres could cut expenses but results in high utilization, high response time, and smaller revenues.Previous work presented a non-linear cost function. We prove its convexity and exploit this property in two ways: First, we transform the convex model into a linear model while controlling the maximum approximation error. Sec- ond, we used a convex solver instead of a slower non-linear solver. Numerical results on network topologies exemplify our work. AU - Keller, Matthias AU - Karl, Holger ID - 372 T2 - Proceedings of the SIGCOMM workshop on Distributed cloud computing TI - Response Time-Optimized Distributed Cloud Resource Allocation ER - TY - THES AB - Radio access networks (RANs) have become one of the largest energy consumers of communication technology [LLH+13] and their energy consumption is predicted to increase [FFMB11]. To reduce the energy consumption of RANs different techniques have been proposed. One of the most promising techniques is the use of a low-power sleep mode. However, a sleep mode can also reduce the performance. In this dissertation, I quantify how much energy can be conserved with a sleep mode and which negative effects it has on the performance of RANs. Additionally, I analyze how a sleep mode can be enabled more often and how the performance can be kept high. First, I quantify the effect of power-cycle durations on energy consumption and latency in an abstract queuing system. This results in a trade-off between energy consumption and latency for a single base station (BS). Second, I show that considering a network as a whole (instead of each BS individually) allows the energy consumption to be reduced even further. After these analyses, which are not specific for RANs, I study RANs for the rest of the dissertation. RANs need to both detect and execute the requests of users. Because detection and execution of requests have different requirements, I analyze them independently. I quantify how the number of active BSs can be reduced if the detection ranges of BSs are increased by cooperative transmissions. Next, I analyze how more BSs can be deactivated if the remaining active BSs cooperate to transmit data to the users. However, in addition to increasing the range, cooperative transmissions also radiate more power. This results in higher interference for other users which slows their transmissions down and, thus, increases energy consumption. Therefore, I describe how the radiated power of cooperative transmissions can be reduced if instantaneous channel knowledge is available. Because the implementation in real hardware is impractical for demonstration purposes, I show the results of a simulation that incorporates all effects I studied analytically earlier. In conclusion, I show that a sleep mode can reduce the energy consumption of RANs if applied correctly. To apply a sleep mode correctly, it is necessary to consider power-cycle durations, power profiles, and the interaction of BSs. When this knowledge is combined the energy consumption of RANs can be reduced with only a slight loss of performance. Because this results in a trade-off between energy consumption and performance, each RAN operator has to decide which trade-off is preferred. AU - Herlich, Matthias ID - 376 TI - Reducing Energy Consumption of Radio Access Networks ER - TY - CONF AB - This paper explores how cloud provider competition influences instance pricing in an IaaS (Infrastructure-as-a-Service) market. When reserved instance pricing includes an on-demand price component in addition to a reservation fee (two-part tariffs), different providers might offer different price combinations, where the client’s choice depends on its load profile. We investigate a duopoly of providers and analyze stable market prices in two-part tariffs. Further, we study offers that allow a specified amount of included usage (three-part tariffs). Neither two-part nor three-part tariffs produce an equilibrium market outcome other than a service pricing that equals production cost, i.e., complex price structures do not significantly affect the results from ordinary Bertrand competition. AU - Künsemöller, Jörn AU - Brangewitz, Sonja AU - Karl, Holger AU - Haake, Claus-Jochen ID - 382 T2 - Proceedings of the 2014 IEEE International Conference on Services Computing (SCC) TI - Provider Competition in Infrastructure-as-a-Service ER - TY - CONF AU - Wette, Philip AU - Karl, Holger ID - 1801 SN - 9781479900565 T2 - 2013 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) TI - Incorporating feedback from application layer into routing and wavelength assignment algorithms ER - TY - GEN AU - Dreimann, Philipp ID - 458 TI - Anticipatory Power Cycling of Mobile Network Equipment for High-Demand Multimedia Traffic ER - TY - GEN AU - Dräxler, Sevil ID - 461 TI - Adaptive Placement of Programmable Virtual Network Function Chains ER - TY - JOUR AB - Financial benefits are an important factor when cloud infrastructure is considered to meet processing demand. The dynamics of on-demand pricing and service usage are investigated in a two-stage game model for a monopoly Infrastructure-as-a-Service (IaaS) market. The possibility of hybrid clouds (public clouds plus own infrastructure) turns out to be essential in order that not only the provider but also the clients have significant benefits from on-demand services. Even if the client meets all demand in the public cloud, the threat of building a hybrid cloud keeps the instance price low. This is not the case when reserved instances are offered as well. Parameters like load profiles and economies of scale have a huge effect on likely future pricing and on a cost-optimal split-up of client demand between either a client’s own data center and a public cloud service or between reserved and on-demand cloud instances. AU - Künsemöller, Jörn AU - Karl, Holger ID - 467 JF - Future Generation Computer Systems TI - A Game-Theoretic Approach to the Financial Benefits of Infrastructure-as-a-Service ER - TY - JOUR AU - Beister, Frederic AU - Dräxler, Martin AU - Aelken, J. AU - Karl, Holger ID - 753 JF - Computer Communications TI - Power model design for ICT systems -- A generic approach ER - TY - JOUR AU - Azeem M. Khan, Rana AU - Karl, Holger ID - 754 IS - 1 JF - IEEE Communications Surveys and Tutorials TI - MAC Protocols for Cooperative Diversity in Wireless LANs and Wireless Sensor Networks ER - TY - CONF AU - Dräxler, Martin AU - Dreimann, Philipp AU - Karl, Holger ID - 759 T2 - IEEE Online Conference on Green Communications, OnlineGreenComm 2014, November 12-14, 2014 TI - Anticipatory power cycling of mobile network equipment for high demand multimedia traffic ER - TY - CONF AU - Auroux, Sebastien AU - Karl, Holger ID - 760 T2 - 25th IEEE Annual International Symposium on Personal, Indoor, and Mobile Radio Communication, {PIMRC} 2014, Washington DC, USA, September 2-5, 2014 TI - Flow processing-aware controller placement in wireless DenseNets ER - TY - CONF AU - Schwabe, Arne AU - Karl, Holger ID - 762 T2 - Proceedings of the third workshop on Hot topics in software defined networking, HotSDN '14, Chicago, Illinois, USA, August 22, 2014 TI - Using MAC addresses as efficient routing labels in data centers ER - TY - CONF AU - Blanckenstein, Johannes AU - Karl, Holger ID - 763 T2 - 22nd International Conference on Software, Telecommunications and Computer Networks, SoftCOM 2014, Split, Croatia, September 17-19, 2014 TI - Energy-efficient clock synchronization using wake-up receivers ER - TY - CONF AU - Beister, Frederic AU - Karl, Holger ID - 765 T2 - IEEE 10th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2014, Larnaca, Cyprus, October 8-10, 2014 TI - Predicting mobile video inter-download times with Hidden Markov Models ER - TY - GEN AU - Mehraghdam, Sevil AU - Keller, Matthias AU - Karl, Holger ID - 766 T2 - CoRR TI - Specifying and Placing Chains of Virtual Network Functions ER - TY - GEN AU - Wette, Philip AU - Karl, Holger ID - 767 T2 - CoRR TI - DCT²Gen: A Versatile TCP Traffic Generator for Data Centers ER - TY - GEN AU - Schwabe, Arne AU - Karl, Holger ID - 768 T2 - CoRR TI - Adding Geographical Embedding to AS Topology Generation ER - TY - GEN AU - Dornseifer, Veit ID - 426 TI - Evaluation of a Hybrid Packet-/Circuit-Switched Data Center Network ER - TY - GEN AU - Bredenbals, Nico ID - 432 TI - Energy-Efficient Queuing with Delayed Deactivation ER -