Christopher Eibel

From radio telemetry to ultra-low-power sensor networks: tracking bats in the wild

Sensor networks have successfully been used for wildlife monitoring and tracking of different species. When it comes to small animals such as smaller birds, mammals, or even insects, the current approach is to use extremely lightweight RF tags located using radio telemetry. A new quantum leap in technology is needed to overcome this limitation and enable new ways to observe larger numbers of small animals. In an interdisciplinary team, we are working on the different aspects of such a new technology. In particular, we report on our findings on a sensor- network-based tracking solution for bats. Our system is based on integrated localization and wireless communication protocols for ultra-low-power systems. This requires coding techniques for improved reliability as well as ranging solutions for tracking hunting bats. We address the technological and methodical problems related to system design, software support, and protocol design. First field experiments have been conducted that showcase the capabilities of our system.

SEEP: exploiting symbolic execution for energy-aware programming

In recent years, there has been a rapid evolution of energy-aware computing systems (e.g., mobile devices, wireless sensor nodes), as still rising system complexity and increasing user demands make energy a permanently scarce resource. While static and dynamic optimizations for energy-aware execution have been massively explored, writing energy-efficient programs in the first place has only received limited attention.n This paper proposes SEEP, a framework which exploits symbolic execution and platform-specific energy profiles to provide the basis for energy-aware programming. More specifically, the framework provides developers with information about the energy demand of their code at hand, even for the invocation of library functions and in settings with multiple possibly strongly heterogeneous target platforms. This equips developers with the necessary knowledge to take energy demand into account during the task of writing programs.

Monitoring Bats in the Wild: On Using Erasure Codes for Energy-Efficient Wireless Sensor Networks

We explore the advantages of using Erasure Codes (ECs) in a very challenging sensor networking scenario, namely, monitoring and tracking bats in the wild. The mobile bat nodes collect contact information that needs to be transmitted to stationary base stations whenever they are in communication range. We are particularly interested in improving the overall communication reliability of the wireless communication. The mobile nodes are capable of storing a few 100kB of data and to exchange contact information in aggregated form. Due to the continuous flight of the bats and the forest environment, the wireless channel quality varies quickly and, thus, the communication is in general assumed to be highly unreliable. Given the very strict energy constraints of the mobile node and the inherently asymmetric channels, conventional techniques such as full data replication or Automatic Repeat Request to improve the communication reliability are prohibitive. In this work, we investigate the tradeoff between reliability achieved and the cost in form of additional transmissions, that is, the additional energy costs. Our energy measurements on a real platform combined with larger-scale simulation of the wireless communication clearly indicate the advantages of using ECs in our scenario. The results are also applicable in other configurations when unreliable communication channels meet tight energy budgets.

Towards Energy-Proportional State-Machine Replication

The energy consumption of state-of-the-art systems applying state-machine replication in general is not proportional to the performance they provide. This is mainly due to the fact that current implementations rely on static replica configurations, for example with regard to the number of threads to be used, which prevent them from adjusting their resource footprints to changing load levels. In this paper, we address this problem by presenting a mechanism that allows a replica to adapt its energy consumption by switching between configurations at runtime. Furthermore, we study the effectiveness of different energy-saving techniques and their impact on peak performance. Our evaluation results for a Byzantine fault-tolerant coordination service show that utilizing such knowledge in combination with our mechanism, it is possible to build energy-proportional replicated systems.

How to Make Profit: Exploiting Fluctuating Electricity Prices with Albatross, A Runtime System for Heterogeneous HPC Clusters

The ongoing evolution of the power grid towards a highly dynamic supply system poses challenges as renewables induce new grid characteristics. The volatility of electricity sources leads to a fluctuating electricity price, which even becomes negative when excess supply occurs. Operators of high-performance--computing (HPC) clusters therefore can consider the highly dynamic variations of electricity prices to provide an energy-efficient and economic operation. This paper presents Albatross, a runtime system for heterogeneous HPC clusters. To ensure an energy-efficient and economic processing of HPC workloads, our system exploits heterogeneity at the hardware level and considers dynamic electricity prices. We have implemented Albatross and evaluate it on a heterogeneous HPC cluster in our lab to show how the power demand of the cluster decreases when electricity prices are high (i.e., excess demand at the grid). When electricity prices are low or negative (i.e., excess supply to the grid), Albatross purposefully increases the workload and, thus, power demand of the HPC cluster---to make profit.

Playing Hare and Tortoise: The FigarOS Kernel for Fine-Grained System-Level Energy Optimizations

Energy has emerged to be the most important resource for computing systems. Despite the exceptional importance of energy, reducing its demand at application and system level remains a challenging task for programmers and engineers. This is aggravated by the fact that traditional energy-saving approaches are not only error-prone but even lead to adverse consequences (i.e. increased energy consumption). To address this concern, we present the FigarOS operating system for fine-grained system-level energy optimizations. The evaluation of our FigarOS implementation shows that the operating system lowers the energy consumption of processes by up to 2.9 x.

Making Profit with ALBATROSS: A Runtime System for Heterogeneous High-Performance-Computing Clusters

1 MOTIVATION AND INTRODUCTION The ongoing evolution of the power grid towards a highly dynamic supply and demand system poses challenges [1] to its operators and subscribers. The dependence on renewable electricity (e.g., wind, solar, and water) induces new grid characteristics: the volatility of electricity sources leads to an interplay of excess supply and demand, which results in fluctuating electricity prices. Thus, the operation of high-performance–computing (HPC) clusters canwork with the fluctuating electricity price to ensure cost effectiveness [2]. This poster abstract presents Albatross [3], a runtime system for heterogeneous HPC clusters. To ensure an energy-efficient and economic processing of HPC workloads, our system exploits heterogeneity at the hardware level and considers dynamic electricity prices. Early results of our Albatross prototype running on a heterogeneous HPC cluster in our lab show how the power demand of the cluster decreases when electricity prices are high (i.e., excess demand at the grid), and how our system purposefully increases the workload and, thus, power demand when electricity prices are low or even negative (i.e., excess supply to the grid)—to make profit.

Strome: Energy-Aware Data-Stream Processing

Handling workloads generated by a large number of users, data-stream–processing systems also require large amounts of energy. To reduce their energy footprint, such systems typically rely on the operating systems of their servers to adjust processor speeds depending on the current workload by performing dynamic voltage and frequency scaling (DVFS). In this paper, we show that, although effective, this approach still leaves room for significant energy savings due to DVFS making conservative assumptions regarding its impact on application performance. To leverage the unused potential we present Strome, an energy-aware technique to minimize energy demand in data-stream–processing systems by dynamically adapting upper limits for the power demand of hardware components. In contrast to DVFS, Strome exploits information on application performance and is therefore able to achieve energy savings while minimizing its effects on throughput and latency. Our evaluation shows that Strome is particularly effective in the face of varying workloads, reducing power demand by up to 25 % compared with the state-of-the-art data-stream–processing system Heron relying on DVFS.

Energy Claims at Scale: Decreasing the Energy Demand of HPC Workloads at OS Level

The ever-increasing performance and power demand of HPC systems requires sophisticated approaches that improve energy-efficient job execution. Targeted goals such as the 20-MW limit for an exascale system, set by the Department of Energy (DoE), are not achievable with advances at hardware level only. Instead, it is inevitable to establish new concepts at system-software level. We propose a system software in which the operating system acquires a key position in the energy-reduction process. Our approach advocates heterogeneous hardware components - especially those that currently emerge from the embedded-system domain - to achieve both high performance and high energy efficiency.