SOC dynamic power management using artificial neural network

Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level power management policies. We proposed two PM policies-Back propagation Power Management (BPPM) and Radial Basis Function Power Management (RBFPM) which are based on Artificial Neural Networks (ANN). Our experiments show that the two power management policies greatly lowered the system-level power consumption and have higher performance than traditional Power Management(PM) techniques-BPPM is 1.09-competitive and RBFPM is 1.08-competitive vs. 1.79, 1.45, 1.18-competitive separately for traditional timeout PM, adaptive predictive PM and stochastic PM.

Dynamic power management approaches based on neural network

Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system. by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level policies. We proposed two PAY policies-Back propagation Power Management (BPPM) and Radial Basis Function Power management (RBFPM) which are based on Artificial Neural Networks (ANN). Our experiments show that the two power management policies greatly lowered the system-level power consumption and have higher performance than traditional Power Management(PM) techniques-BPPM is 1.09-competitive and RBFPM is 1.08-competitive vs. 1.79,145,1.18-competitive separately for traditional timeout PM, adaptive predictive PM and stochastic PM.

SOC dynamic power management using artificial neural network

Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level power management policies. We proposed two PM policies-Back propagation Power Management (BPPM) and Radial Basis Function Power Management (RBFPM) which are based on Artificial Neural Networks (ANN). Our experiments show that the two power management policies greatly lowered the system-level power consumption and have higher performance than traditional Power Management(PM) techniques-BPPM is 1.09-competitive and RBFPM is 1.08-competitive vs. 1.79 . 1.45 . 1.18-competitive separately for traditional timeout PM . adaptive predictive PM and stochastic PM.

Dynamic power management: from portable devices to high performance computing

Electronic applications are nowadays converging under the umbrella of the cloud computing vision. The future ecosystem of information and communication technology is going to integrate clouds of portable clients and embedded devices exchanging information, through the internet layer, with processing clusters of servers, data-centers and high performance computing systems. Even thus the whole society is waiting to embrace this revolution, there is a backside of the story. Portable devices require battery to work far from the power plugs and their storage capacity does not scale as the increasing power requirement does. At the other end processing clusters, such as data-centers and server farms, are build upon the integration of thousands multiprocessors. For each of them during the last decade the technology scaling has produced a dramatic increase in power density with significant spatial and temporal variability. This leads to power and temperature hot-spots, which may cause non-uniform ageing and accelerated chip failure. Nonetheless all the heat removed from the silicon translates in high cooling costs. Moreover trend in ICT carbon footprint shows that run-time power consumption of the all spectrum of devices accounts for a significant slice of entire world carbon emissions. This thesis work embrace the full ICT ecosystem and dynamic power consumption concerns by describing a set of new and promising system levels resource management techniques to reduce the power consumption and related issues for two corner cases: Mobile Devices and High Performance Computing.

Channel Adaptive MAC Protocol with Traffic-Aware Distributed Power Management in Wireless Sensor Networks-Some Performance Issues

In Wireless Sensor Networks (WSN), neglecting the effects of varying channel quality can lead to an unnecessary wastage of precious battery resources and in turn can result in the rapid depletion of sensor energy and the partitioning of the network. Fairness is a critical issue when accessing a shared wireless channel and fair scheduling must be employed to provide the proper flow of information in a WSN. In this paper, we develop a channel adaptive MAC protocol with a traffic-aware dynamic power management algorithm for efficient packet scheduling and queuing in a sensor network, with time varying characteristics of the wireless channel also taken into consideration. The proposed protocol calculates a combined weight value based on the channel state and link quality. Then transmission is allowed only for those nodes with weights greater than a minimum quality threshold and nodes attempting to access the wireless medium with a low weight will be allowed to transmit only when their weight becomes high. This results in many poor quality nodes being deprived of transmission for a considerable amount of time. To avoid the buffer overflow and to achieve fairness for the poor quality nodes, we design a Load prediction algorithm. We also design a traffic aware dynamic power management scheme to minimize the energy consumption by continuously turning off the radio interface of all the unnecessary nodes that are not included in the routing path. By Simulation results, we show that our proposed protocol achieves a higher throughput and fairness besides reducing the delay

Ultra-low power WSNs: distributed signal processing and dynamic resource management

This thesis presents several data processing and compression techniques capable of addressing the strict requirements of wireless sensor networks. After introducing a general overview of sensor networks, the energy problem is introduced, dividing the different energy reduction approaches according to the different subsystem they try to optimize. To manage the complexity brought by these techniques, a quick overview of the most common middlewares for WSNs is given, describing in detail SPINE2, a framework for data processing in the node environment. The focus is then shifted on the in-network aggregation techniques, used to reduce data sent by the network nodes trying to prolong the network lifetime as long as possible. Among the several techniques, the most promising approach is the Compressive Sensing (CS). To investigate this technique, a practical implementation of the algorithm is compared against a simpler aggregation scheme, deriving a mixed algorithm able to successfully reduce the power consumption. The analysis moves from compression implemented on single nodes to CS for signal ensembles, trying to exploit the correlations among sensors and nodes to improve compression and reconstruction quality. The two main techniques for signal ensembles, Distributed CS (DCS) and Kronecker CS (KCS), are introduced and compared against a common set of data gathered by real deployments. The best trade-off between reconstruction quality and power consumption is then investigated. The usage of CS is also addressed when the signal of interest is sampled at a Sub-Nyquist rate, evaluating the reconstruction performance. Finally the group sparsity CS (GS-CS) is compared to another well-known technique for reconstruction of signals from an highly sub-sampled version. These two frameworks are compared again against a real data-set and an insightful analysis of the trade-off between reconstruction quality and lifetime is given.

Energy-aware dynamic route management for THAWS

In this research we focus on the Tyndall 25mm and 10mm nodes energy-aware topology management to extend sensor network lifespan and optimise node power consumption. The two tiered Tyndall Heterogeneous Automated Wireless Sensors (THAWS) tool is used to quickly create and configure application-specific sensor networks. To this end, we propose to implement a distributed route discovery algorithm and a practical energy-aware reaction model on the 25mm nodes. Triggered by the energy-warning events, the miniaturised Tyndall 10mm data collector nodes adaptively and periodically change their association to 25mm base station nodes, while 25mm nodes also change the inter-connections between themselves, which results in reconfiguration of the 25mm nodes tier topology. The distributed routing protocol uses combined weight functions to balance the sensor network traffic. A system level simulation is used to quantify the benefit of the route management framework when compared to other state of the art approaches in terms of the system power-saving.

Dynamic load management in a smart home to participate in demand response events

In future power systems, in the smart grid and microgrids operation paradigms, consumers can be seen as an energy resource with decentralized and autonomous decisions in the energy management. It is expected that each consumer will manage not only the loads, but also small generation units, heating systems, storage systems, and electric vehicles. Each consumer can participate in different demand response events promoted by system operators or aggregation entities. This paper proposes an innovative method to manage the appliances on a house during a demand response event. The main contribution of this work is to include time constraints in resources management, and the context evaluation in order to ensure the required comfort levels. The dynamic resources management methodology allows a better resources’ management in a demand response event, mainly the ones of long duration, by changing the priorities of loads during the event. A case study with two scenarios is presented considering a demand response with 30 min duration, and another with 240 min (4 h). In both simulations, the demand response event proposes the power consumption reduction during the event. A total of 18 loads are used, including real and virtual ones, controlled by the presented house management system.

Power Management Controls

In an office building in the US the office equipment uses about 7% of the total electricity use. Eventhough this is a low number, there is still a reason to save more energy, especially since one third of theenergy savings are lost when power management is not enabled.The core in the project ”Power Management Controls” is to develop a voluntary standard, The UserInterface Standard, that manufacturers of office equipment can use as a reference when they developnew equipment and design new interfaces. The interface is an important part of the use of powermanagement and doing this should increase the use of power management and save more energy. Theinterfaces are ofter hidden or inconsistent and confusing, which makes it harder for the user tounderstand power management. A more consistent interface makes it easier for the user to understandthe meaning of an interface and power management itselfThe standard consists of six different parts, which describe what can be done to achieve a consistentinterface. The standard also describes the part of the project called Dynamic Behavior. This part isconcentrating on the interfaces and the behavior of the device over time, which is important for the userto understand.The purpose of this degree project is to study and participate in the project ”Power ManagementControls”, and to understand what is being done to save more energy.

Power management techniques in an FPGA-Based WSN node for high performance application

In this work, the power management techniques implemented in a high-performance node for Wireless Sensor Networks (WSN) based on a RAM-based FPGA are presented. This new node custom architecture is intended for high-end WSN applications that include complex sensor management like video cameras, high compute demanding tasks such as image encoding or robust encryption, and/or higher data bandwidth needs. In the case of these complex processing tasks, yet maintaining low power design requirements, it can be shown that the combination of different techniques such as extensive HW algorithm mapping, smart management of power islands to selectively switch on and off components, smart and low-energy partial reconfiguration, an adequate set of save energy modes and wake up options, all combined, may yield energy results that may compete and improve energy usage of typical low power microcontrollers used in many WSN node architectures. Actually, results show that higher complexity tasks are in favor of HW based platforms, while the flexibility achieved by dynamic and partial reconfiguration techniques could be comparable to SW based solutions.

Practical dynamic thermal management on Intel desktop computer

Fueled by increasing human appetite for high computing performance, semiconductor technology has now marched into the deep sub-micron era. As transistor size keeps shrinking, more and more transistors are integrated into a single chip. This has increased tremendously the power consumption and heat generation of IC chips. The rapidly growing heat dissipation greatly increases the packaging/cooling costs, and adversely affects the performance and reliability of a computing system. In addition, it also reduces the processor's life span and may even crash the entire computing system. Therefore, dynamic thermal management (DTM) is becoming a critical problem in modern computer system design. Extensive theoretical research has been conducted to study the DTM problem. However, most of them are based on theoretically idealized assumptions or simplified models. While these models and assumptions help to greatly simplify a complex problem and make it theoretically manageable, practical computer systems and applications must deal with many practical factors and details beyond these models or assumptions. The goal of our research was to develop a test platform that can be used to validate theoretical results on DTM under well-controlled conditions, to identify the limitations of existing theoretical results, and also to develop new and practical DTM techniques. This dissertation details the background and our research efforts in this endeavor. Specifically, in our research, we first developed a customized test platform based on an Intel desktop. We then tested a number of related theoretical works and examined their limitations under the practical hardware environment. With these limitations in mind, we developed a new reactive thermal management algorithm for single-core computing systems to optimize the throughput under a peak temperature constraint. We further extended our research to a multicore platform and developed an effective proactive DTM technique for throughput maximization on multicore processor based on task migration and dynamic voltage frequency scaling technique. The significance of our research lies in the fact that our research complements the current extensive theoretical research in dealing with increasingly critical thermal problems and enabling the continuous evolution of high performance computing systems.

Power management and power flow control with back-to-back converters in a utility connected microgrid

This paper proposes a method for power flow control between utility and microgrid through back-to-back converters, which facilitates desired real and reactive power flow between utility and microgrid. In the proposed control strategy, the system can run in two different modes depending on the power requirement in the microgrid. In mode-1, specified amount of real and reactive power are shared between the utility and the microgrid through the back-to-back converters. Mode-2 is invoked when the power that can be supplied by the DGs in the microgrid reaches its maximum limit. In such a case, the rest of the power demand of the microgrid has to be supplied by the utility. An arrangement between DGs in the microgrid is proposed to achieve load sharing in both grid connected and islanded modes. The back-to-back converters also provide total frequency isolation between the utility and the microgrid. It is shown that the voltage or frequency fluctuation in the utility side has no impact on voltage or power in microgrid side. Proper relay-breaker operation coordination is proposed during fault along with the blocking of the back-to-back converters for seamless resynchronization. Both impedance and motor type loads are considered to verify the system stability. The impact of dc side voltage fluctuation of the DGs and DG tripping on power sharing is also investigated. The efficacy of the proposed control ar-rangement has been validated through simulation for various operating conditions. The model of the microgrid power system is simulated in PSCAD.

Process variability-aware statistical hybrid modeling of dynamic power dissipation in 65 nm CMOS designs

A generalized technique is proposed for modeling the effects of process variations on dynamic power by directly relating the variations in process parameters to variations in dynamic power of a digital circuit. The dynamic power of a 2-input NAND gate is characterized by mixed-mode simulations, to be used as a library element for 65mn gate length technology. The proposed methodology is demonstrated with a multiplier circuit built using the NAND gate library, by characterizing its dynamic power through Monte Carlo analysis. The statistical technique of Response. Surface Methodology (RSM) using Design of Experiments (DOE) and Least Squares Method (LSM), are employed to generate a "hybrid model" for gate power to account for simultaneous variations in multiple process parameters. We demonstrate that our hybrid model based statistical design approach results in considerable savings in the power budget of low power CMOS designs with an error of less than 1%, with significant reductions in uncertainty by atleast 6X on a normalized basis, against worst case design.

Power Management and Data Rate Maximization in Wireless Energy Harvesting Sensors

This paper considers the problem of power management and throughput maximization for energy neutral operation when using Energy Harvesting Sensors (EHS) to send data over wireless links. It is assumed that the EHS are designed to transmit data at a constant rate (using a fixed modulation and coding scheme) but are power-controlled. A framework under which the system designer can optimize the performance of EHS when the channel is Rayleigh fading is developed. For example, the highest average data rate that can be supported over a Rayleigh fading channel given the energy harvesting capability, the battery power storage efficiency and the maximum allowed transmit energy per slot is derived. Furthermore, the optimum transmission scheme that guarantees a particular data throughput is derived. The usefulness of the framework developed is illustrated through simulation results for specific examples.

Dual-Stage Power Management Algorithms for Energy Harvesting Sensors

In this paper, we propose power management algorithms for maximizing the utility of energy harvesting sensors (EHS) that operate purely on the basis of energy harvested from the environment. In particular, we consider communication (i.e., transmission and reception) power management issues for EHS under an energy neutrality constraint. We also consider the fixed power loss effects of the circuitry, the battery inefficiency and its storage capacity, in the design of the algorithms. We propose a two-stage structure that exploits the inherent difference in the timescales at which the energy harvesting and channel fading processes evolve, without loss of optimality of the resulting solution. The outer stage schedules the power that can be used by an inner stage algorithm, so as to maximize the long term average utility and at the same time maintain energy neutrality. The inner stage optimizes the communication parameters to achieve maximum utility in the short-term, subject to the power constraint imposed by the outer stage. We optimize the algorithms for different transmission schemes such as the truncated channel inversion and retransmission strategies. The performance of the algorithms is illustrated via simulations using solar irradiance data, and for the case of Rayleigh fading channels. The results demonstrate the significant performance benefits that can be obtained using the proposed power management algorithms compared to the energy efficient (optimum when there is no storage) and the uniform power consumption (optimum when the battery has infinite capacity and is perfectly efficient) approaches.