https://beloglazov.info/papers/2011-energy-aware-fgcs.pdf

Energy-aware resource allocation heuristics for efficient management of data centers for Cloud computing

Network virtualization is recognized as an enabling technology for the future Internet. It aims to overcome the resistance of the current Internet to architectural change. Application of this technology relies on algorithms that can instantiate virtualized networks on a substrate infrastructure, optimizing the layout for service-relevant metrics. This class of algorithms is commonly known as "Virtual Network Embedding (VNE)" algorithms. This paper presents a survey of current research in the VNE area. Based upon a novel classification scheme for VNE algorithms a taxonomy of current approaches to the VNE problem is provided and opportunities for further research are discussed.

Virtual Network Embedding: A Survey

Networks are a shared resource connecting critical IT infrastructure, and the general practice is to always leave them on. Yet, meaningful energy savings can result from improving a network's ability to scale up and down, as traffic demands ebb and flow. We present ElasticTree, a network-wide power1 manager, which dynamically adjusts the set of active network elements -- links and switches--to satisfy changing data center traffic loads.We first compare multiple strategies for finding minimum-power network subsets across a range of traffic patterns. We implement and analyze ElasticTree on a prototype testbed built with production OpenFlow switches from three network vendors. Further, we examine the trade-offs between energy efficiency, performance and robustness, with real traces from a production e-commerce website. Our results demonstrate that for data center workloads, ElasticTree can save up to 50% of network energy, while maintaining the ability to handle traffic surges. Our fast heuristic for computing network subsets enables ElasticTree to scale to data centers containing thousands of nodes. We finish by showing how a network admin might configure ElasticTree to satisfy their needs for performance and fault tolerance, while minimizing their network power bill.

/pdf/elastictree-saving-energy-in-data-center-networks-2w53iv2yv5.pdf

ElasticTree: saving energy in data center networks

Energy expenses are becoming an increasingly important fraction of data center operating costs. At the same time, the energy expense per unit of computation can vary significantly between two different locations. In this paper, we characterize the variation due to fluctuating electricity prices and argue that existing distributed systems should be able to exploit this variation for significant economic gains. Electricity prices exhibit both temporal and geographic variation, due to regional demand differences, transmission inefficiencies, and generation diversity. Starting with historical electricity prices, for twenty nine locations in the US, and network traffic data collected on Akamai's CDN, we use simulation to quantify the possible economic gains for a realistic workload. Our results imply that existing systems may be able to save millions of dollars a year in electricity costs, by being cognizant of locational computation cost differences.

/pdf/cutting-the-electric-bill-for-internet-scale-systems-4awcltuqwb.pdf

Cutting the electric bill for internet-scale systems

We present the design and evaluation of two forms of power management schemes that reduce the energy consumption of networks. The first is based on putting network components to sleep during idle times, reducing energy consumed in the absence of packets. The second is based on adapting the rate of network operation to the offered workload, reducing the energy consumed when actively processing packets.

For real-world traffic workloads and topologies and using power constants drawn from existing network equipment, we show that even simple schemes for sleeping or rate-adaptation can offer substantial savings. For instance, our practical algorithms stand to halve energy consumption for lightly utilized networks (10-20%). We show that these savings approach the maximum achievable by any algorithms using the same power management primitives. Moreover this energy can be saved without noticeably increasing loss and with a small and controlled increase in latency (<10ms). Finally, we show that both sleeping and rate adaptation are valuable depending (primarily) on the power profile of network equipment and the utilization of the network itself.

/pdf/reducing-network-energy-consumption-via-sleeping-and-rate-40siwae9b4.pdf

Reducing network energy consumption via sleeping and rate-adaptation

Exponential bandwidth scaling has been a fundamental driver of the growth and popularity of the Internet. However, increases in bandwidth have been accompanied by increases in power consumption, and despite sustained system design efforts to address power demand, significant technological challenges remain that threaten to slow future bandwidth growth. In this paper we describe the power and associated heat management challenges in today's routers. We advocate a broad approach to addressing this problem that includes making power-awareness a primary objective in the design and configuration of networks, and in the design and implementation of network protocols. We support our arguments by providing a case study of power demands of two standard router platforms that enables us to create a generic model for router power consumption. We apply this model in a set of target network configurations and use mixed integer optimization techniques to investigate power consumption, performance and robustness in static network design and in dynamic routing. Our results indicate the potential for significant power savings in operational networks by including power-awareness.

/pdf/power-awareness-in-network-design-and-routing-17zkt9k3ta.pdf

Power Awareness in Network Design and Routing

DNS names assigned to interfaces of network devices along an end-to-end path are an important source of information for both operations and research. Our study focuses on the interface DNS names that encode detailed information about the device e.g., interface type, bandwidth, manufacturer. In this paper we describe a methodology for discovering and characterizing the structure of diverse interface DNS names. We extract, organize and assess the details of the encoding used in different networks. The results of our analysis show that many different encodings are used, and that meaningful encodings are common in the core of the Internet. To enable interface DNS name decoding to be used in practice, we incorporate our information extraction library into a new version of traceroute that we call PathAudit.

/pdf/what-s-in-a-name-decoding-router-interface-names-33uc5bts6l.pdf

What's in a name?: decoding router interface names

The escalation in power consumption of networking and communications equipment is of concern to technologists and environmentalists alike. Understanding how and when networking devices consume power is complicated by their lack of instrumentation. Furthermore, standard networking devices are not typically flexible enough to support experiments with new techniques for reducing power consumption. In this paper, we describe a set of extensions for Linux-based commodity switches that enable a wide range of power-aware experiments in laboratory testbeds. The extensions are based on the requirements for high fidelity in power measurement and in modulation of key subsystems. Our implementation includes two key capabilities: a flexible power consumption model and a traffic shaper that enable emulation of wide range of power-aware hardware and protocols. To validate our power-awareness extension and demonstrate their capabilities and utility, we built a testbed composed of simple, Linux-based switches. First, we show that the most simple configuration of our emulation extensions report power consumption consistent with what can be measured with an external power meter. Next, we conduct a series of experiments on power consumption when bandwidth is scaled directly to performance demands. Our results confirm our hypothesis that a finer grained approach yields more power savings when the transition cost is low and traffic varies.

/pdf/power-awareness-extensions-for-network-testbeds-1npe53t6g9.pdf

Power-Awareness Extensions for Network Testbeds

Understanding the details of power consumption in networks is a precursor to being able to make effective power management decisions. However, measuring the power consumption is often fraught with difficulty due in part to large and dispersed deployment of heterogeneous equipment. In this paper we present a tool suite called EnergyAudit that is designed for network operators to audit the power consumption in their infrastructure. The tool suite has three components, (i) an API that links to existing management infrastructures and enables devices to be queried, (ii) a database of benchmark measurements of networking equipment that maps device configurations and operating status to power consumption, (iii) an auditing tool that queries the community database. The API simplifies deployment of EnergyAudit. The database enables community and manufacturer contribution of power consumption estimates. The auditing tool can infer missing data and reports both the estimated power consumption for devices in the network and the fidelity of the measurements from which the device-to-power mapping was reported. We describe the details of the tool suite and demonstrate its use in three different network environments with diverse systems.

/pdf/energy-audit-monitoring-power-consumption-in-diverse-network-1h4o963dfl.pdf

Joseph Chabarek

Papers

Power Awareness in Network Design and Routing

What's in a name?: decoding router interface names

Power-Awareness Extensions for Network Testbeds

Energy Audit: Monitoring power consumption in diverse network environments