Temperature-Power Consumption Relationship and Hot-Spot Migration for FPGA-Based Systems

Heat emission and temperature control in an electronic device are highly correlated with power consumption as well as to equipment’s reliability. Within this context, this chapter discusses a possible solution to restrict the processing component’s heat emission in FPGA-based systems (e.g., Cognitive Radio [CR] equipment). It also describes the implementation, on reconfigurable FPGA based circuit, of a digital thermal sensor, analyzes the applicability of local heat estimations, and empirically describes the temperature-power consumption relationship in a dynamically reconfigurable FPGA platform. Finally, discussions are conducted on the decision making issues related to the use of such sensors to enable “hot-spot” migration in CR equipment.

Power Consumption Aware Cluster Resource Management

In 2007, the Green500 list was introduced, which compares supercomputers by performance-per-watt. Since supercomputers consist of thousands of nodes, energy-saving is a growing demand. Compute clusters are often managed by a so-called Resource Management Systems (RMS), which have load information about the whole system. For clusters with changing compute demands, this can be used to switch on/off nodes according to the current load situation and save energy this way. Here, the authors present energy-saving techniques that work on the management level and measurements that show that speed scaling is not a good means for energy saving. Further, they give an overview of some important standards and specifications related to energy saving, like ACPI and IPMI. Finally, the authors present their energy-saving daemon called CHERUB. Due to its modular design, it can operate with different Resource Management Systems. Their experimental results show that CHERUB’s scheduling algorithm works well, i.e. it will save energy, if possible, and avoids state flapping.

Energy-Aware Switch Design

The use of virtualization technology has been increasing in the IT industry to consolidate servers and reduce power consumption significantly. Virtualized commodity servers are scaled out in the data center and increase the demand for bandwidth between servers. Therefore, a high performance switch is required. The shared-memory switch is the best performance/cost switch architecture, but it is challenging to satisfy the requirements on the memory bandwidth in a high speed network. In addition, it is challenging to handle variable-length frames in Ethernet. This chapter describes the main challenges in Ethernet switch designs and then energy-aware switch designs, including switch architecture and high speed IO interface. As implementation examples, this chapter also describes a single-chip switch Large Scale Integration (LSI) embedded with high-speed IO interfaces and 10-Gigabit Ethernet (10GbE) switch blade equipped with the switch LSI. The switch blade delivers 100% more performance per watt than other 10GbE switch blades in the industry.

Energy Optimizations in Broadband Access Networks

The second part of this chapter focuses on deployment practices and describes how different access network architectures can improve the energy consumption, when considering both the telecom equipment and its supporting functions. The authors show that introducing an access network architecture that distributes more functions in the outside plant does not negatively impact energy consumption of the access network. A use case for the Benelux is worked out and a related innovation in the Swisscom access network shows that also in the more centralized architectures further optimizations are possible.1

Intelligent Systems for Energy Management in Wireless Sensor-Based Smart Environments

The purpose of this chapter is to explore and address the issues that are applicable to Smart Environments by encouraging and providing new insights towards the “Sustainable Green Computing” initiatives for “energy aware” applicable solutions. The topics covered in this chapter provide an introduction to future wireless sensor-based smart environments for energy management systems. Introduction to the topic, motivation, and objective are covered in Section 1. A review of the state-of-the-art technological achievements, theory, and applications, related to the energy management systems (wireless sensors and intelligent systems) are covered in Section 2. Whilst, Section 3 covers in detail the authors’ proposed methodological approach and main ideas leading towards the “Intelligent Systems for Energy Management in Wireless Sensor-Based Smart Environments.” Case studies of real-world applications, following the principles of “Green Computing” in intelligent systems are introduced. The authors present the simulation results of an “energy conservation perspective” in smart homes, demonstrating the potential improvements with respect to energy conservation. Moreover, they present examples of large Wireless Sensor Networks (WSN) simulations (impact of topology control in network survivability) and hybrid intelligent techniques for energy efficient solutions, i.e. finding optimal solution in a predefined interval. The conclusions and future research directions are provided in Sections 4 and 5, respectively.

Green Communications

The exponential growth of wireless systems makes their carbon footprint hard to ignore. This chapter presents statistics related to the energy consumption of cellular networks’ infrastructure in order to motivate the need for more efficient and environmentally friendly communications. A definition of the term “Green Communications” is provided along with different metrics that can be used to quantify energy efficiency for the various aspects of wireless infrastructure. In addition to topics related to cellular infrastructure, the chapter presents a brief review of key techniques that can be potentially used for improving energy efficiency. Furthermore, since improving energy efficiency is not by itself sufficient for low-carbon systems, possible ways of using and managing energy harvested from renewable sources such as solar and ambient RF signals are discussed. Moreover, the concept of Wireless Distributed Computing is introduced to illustrate how a group of wireless devices can share their resources for achieving a set of common goals. Finally, resource allocation is examined for managing the trade-offs involved when simultaneously minimizing the carbon footprint and performing the necessary communication and computation tasks in mobile devices.

Data-Stream-Driven Computers are Power and Energy Efficient

It is believed that data-stream-driven computing is power and energy efficient as compared to its counterpart, instruction-stream-driven computing. This latter requires memory access and memory control overheads while the processor is fetching task instructions from the memory. The programmer describes all the tasks as instructions in the program memory. On the other hand data-stream-driven computer is already configured or hardwired for a specific computing operation, no memory is required apart from data storage. In some contexts we refer to data-stream-driven computers as accelerators or single-purpose processors. This chapter discusses the benefit of data-stream-driven computing for better power and energy efficiency. We took matrix multiplication as an example application to compare the power and energy dissipations between load/store and non-instruction fetch-based architectures. We witnessed that single-purpose processor reduces almost 100% of the dynamic power when replacing the general-purpose processor. With the current mainstream transistor technology, morphware platforms that allow massive parallelism are the potential key for data-stream-driven computer implementations to saving energy in battery-powered embedded systems and to solve the dissipated power dilemma, as the heat becomes the bottleneck of traditional high frequency processors. If the same strategy is applied to mainstream computers and data center servers, we will not only reduce electricity bills but we will also contribute to greener computing by lowering the IT sector’s CO2 emissions.

Energy Efficient Association Method for Wireless Sensor Networks

This chapter describes an energy efficient association method for Wireless Sensor Networks (WSNs). The described method can be used to implement an association procedure by which an improved processing rate can be achieved by using a Beacon Only Period (BOP). The performance of mobile nodes is enhanced by using information on depth, traffic, and Received Signal Strength Indicator (RSSI). By using the Energy Efficient Association (EEA) method, trusted data can be transferred, and traffic overloads that occur at specific nodes can be prevented. In order to research the performance of the described method, the obtained information, such as depth, traffic rate, and RRSI from the relay nodes, is investigated and analyzed. Simulation results show that the EEA method can be used to obtain an efficient network configuration according to the mobility of nodes in WSNs.

Energy Efficient Transmission in Cellular Networks

A cellular network is a kind of dedicated distributed network with wireless radio access, and nowadays, it is widely used in people’s lives. The statistics shows that currently there are 4 billion mobile subscribers in the world, and unquestionably, the cellular network has been playing the main role of energy consumption in ICT (Information and Communications Technology). This chapter discloses the status of energy consumption in the cellular network and introduces energy efficient transmission strategies for accessing a network of cellular networks, especially in cell selection and power control scopes. For future research perspectives, this chapter also introduces the roadmap of smart radio resource management for energy efficient transmission.

Improving Energy-Efficiency of Scientific Computing Clusters

The authors applied operations management principles on scheduling and allocation to scientific computing clusters to decrease energy consumption and to increase throughput. They challenged the traditional one job per one processor core scheduling method commonly used in scientific computing with parallel processing and bottleneck management. The authors tested the effect of increased parallelism by using different test applications related to high-energy physics computing. The test results showed that at best their methods both decreased energy consumption down to 40% and increased throughput up to 100%, compared to the standard one task per CPU core method. The trade-off is that processing times of individual tasks get longer, but in scientific computing, the overall throughput and energy-efficiency are often more important.