Deployment automation with BLITZ

Many of the world's most critical systems are distributed real-time embedded (DRE) systems, with mission-critical quality of service (QoS) requirements. However, because of their nature - heterogeneous nodes and links, shared and constrained resources, and deployment in dynamic environments - providing QoS requires coordinated QoS management throughout the system of multiple end-to-end application streams competing for shared resources. It requires dynamic resource allocation to these end-to-end application streams based on potentially changing mission requirements and shaping application behaviors to effectively use the resources that are allocated. In this paper, we describe the issues involved with providing end-to-end QoS management in DRE systems, an architecture we have designed to support system-wide end-to-end QoS management, and a multi-UAV surveillance and target tracking application we are using to evaluate these technologies.

We present a scalable, hierarchical control system for the dynamic resource management of a distributed real-time embedded (DRE) system. This DRE is inspired by the DARPA adaptive and reflective middleware systems (ARMS) program. The goal of the control system is to simultaneously manage multiple resources and QoS concerns using a utility-driven approach for decision making and performance evaluation. At each level of the control hierarchy there are multiple local controllers which autonomously make decisions to optimize their local utility. The controllers in the hierarchy can use different, localized resource control algorithms and the system's user can tune the operations of the local controllers. We discuss how the selections of local control algorithms affect the behavior of the overall system. The control system is designed to be easily adaptable to other multi-tiered DRE systems.

New advances in software component and modeling standards promise to ease the burden of development complexity while improving flexibility and reliability. These solutions raise the level of abstraction from object-oriented classes to coarser components and support the creation and configuration of systems using modeling or other specification standards. This paper outlines the challenges inherent in the original Bold Stroke component model developed in the late 1990's and then discusses an evolved component model that leverages work being done in the Object Management Group (OMG) and in government funded research that addresses these issues in a distributed real-time embedded (DRE) application context.

On-site study was held to investigate the influences of load factor on power consumption and energy performance of water-cooled air conditioning (WCAC) system. A comprehensive measurement has been conducted to a WCAC plant of a supermall building located in West Java, Indonesia. Hourly and daily power consumption and performance characteristics of the WCAC system at varied load factors for a period of one year were evaluated. Regression analyses were developed to evaluate the influences of load factor on the WCAC power consumption and performance. The WCAC system was found to operate with varied load factor ranging from 70 percent to 100 percent. Power consumption of the system was strongly influenced by the load factor. Power consumption boosted when the power factor increased. The increase of load factor was also found to significantly improve the cooling capacity but reduce the coefficient of performance (COP). The best potential performance of the investigated WCAC system could be obtained at load factor between 70 percent and 85 percent.

Background. Energy awareness in the ICT has become an important issue: ICT is both a key player in energy efficiency, and a power drainer. Focusing on software, recent work suggested the existence of a relationship between power consumption, software configuration and usage patterns in computer systems. Aim. The aim of this work was collecting and analysing power consumption data of a general-purpose computer system, simulating common usage scenarios, in order to extract a power consumption profile for each scenario. Methods. We selected a desktop system running Windows XP as a test machine. Meanwhile, we developed 11 usage scenarios, classified by their functionality, and automated by a GUI testing tool. Then, we conducted several test runs of the scenarios, collecting power consumption data by means of a power meter. Results. Our analysis resulted in an estimation of a power consumption value for each scenario and software application used, obtaining that each single scenario introduced an overhead from 2 to 11 Watts, corresponding to an increase of about 12%. Conclusions. We determined that software and its usage patterns impacts consistently on the power consumption of computer systems. Further work will be devoted to evaluate how power consumption is affected by the usage of specific system resources, like processors, disks, memory etc.KeywordsGreen SoftwareEnergy AwareEnergy ProfilingPower Consumption

Massive Multiple-Input Multiple-Output (Massive MIMO) serves as a foundational enabling technology for 5G and future communication systems, markedly boosting spectral and energy efficiency through the deployment of large-scale antenna arrays. However, the scaling-up of antenna arrays has led to a substantial increase in system power consumption and hardware costs, with high-precision analog-to-digital converters (ADCs) emerging as the dominant power consumption bottleneck in the radio frequency chain. To alleviate system complexity and power consumption, low-resolution ADCs (13 bits) have attracted extensive research interest in recent years. Such schemes can substantially curtail hardware costs and energy consumption while retaining satisfactory system performance. Nevertheless, the introduction of severe nonlinear distortion due to low-precision quantization disrupts the linear Gaussian model assumption upon which traditional receiver algorithms rely, resulting in compromised channel estimation and signal detection performance. Quantization errors demonstrate non-Gaussian and input-dependent characteristics, leading to the degradation of amplitude information and thus constraining the applicability of technologies such as high-order modulation and high-precision sensing. This paper presents a systematic review of low-precision quantization techniques for Massive MIMO. It first investigates the impacts of low-bit quantization on system models and signal statistical properties. Subsequently, it elaborates on transceiver architectures and key design challenges pertaining to low-precision ADCs/DACs. The paper highlights signal processing and algorithmic strategies to overcome quantization distortion, including Bussgang decomposition linearization methods, statistical inference techniques such as approximate message passing (AMP), model-driven deep learning frameworks, and quantization architectures endowed with noise-shaping capabilities. Finally, it discusses the challenges and future directions of this technology in emerging scenarios, including terahertz communications, intelligent reflecting surfaces, and integrated sensing and communication. This paper seeks to provide researchers with a systematic technical overview, clarifying the intrinsic connections and trade-offs among different methods, and offering valuable insights for the realization of high-energy-efficiency and low-cost Massive MIMO systems.

Mobile devices can reduce their energy consumption through power-aware remote processing. Software components running on battery-operated wireless nodes are migrated to wall-power wired remote servers. To increase the efficiency of power-aware remote processing, we propose a novel integrated estimator for software components' power and energy consumption. This adaptive estimator is based on a software component interface. The interface provides power and timing information. The unit is one of the main components in our framework for power-aware remote processing, providing information for efficient internal decision making whether software components can profit by migration and remote execution or not. We present results from our framework evaluated in Java environment and standard wearable computing hardware, using sample software components for AES encryption and decryption.

Mobile devices can reduce their energy consumption through power-aware remote processing. Software components running on battery-operated wireless nodes are migrated to wall-power wired remote servers. To increase the efficiency of power-aware remote processing, we propose a novel integrated estimator for software components' power and energy consumption. This adaptive estimator is based on a software component interface. The interface provides power and timing information. The unit is one of the main components in our framework for power-aware remote processing, providing information for efficient internal decision making whether software components can profit by migration and remote execution or not. We present results from our framework evaluated in Java environment and standard wearable computing hardware, using sample software components for AES encryption and decryption.

With increasing design complexity of portable handheld devices, decreasing system power and energy consumption has become a key design metric. It is crucial for the designers to accurately evaluate the system power consumption in detail during the development process, especially for the power hungry digital system processing (DSP) system. This paper presents an automatic power estimation methodology, which can provide accurate dynamic power consumption distributions of DSP components implemented on Xilinx FPGAs. Additionally, the dependences of power consumption on system level parameters, including clock frequency, area utilization ratio and activity rate, are investigated from sensitivity metric. According to the experimental results, several power optimizations can be performed at the early stages of design flow.

Formal analysis of feature degradation in fault-tolerant automotive systems

Focus on the energy saving problem in cloud radio access network (C-RAN), this paper jointly optimizes the system power consumption and delay performance with the consideration of quality-of-service (QoS) and fronthaul capacity. First, to make the power consumption model compatible with C-RAN, we give a modified power consumption model of base station (BS) on the basis of the well-known EARTH model. Then, to save the system power consumption, the sleeping strategy is introduced to dynamically switch ON/OFF the BS. In order to analyze BS mode under the sleeping strategy, the arriving users are modeled as a discrete-time queuing network. Based on the global balance equations of the queuing network, the probability that the BS is in active mode can be obtained. In the light of the above result, to further reduce the system power consumption, power control is introduced under the constraint of QoS and fronthaul capacity. Meanwhile, by applying Lyapunov method, a different way to consider the delay performance is provided, and at the same time, network stability is guaranteed. Simulation results show that the proposed algorithm can balance the power consumption and delay by adjusting relevant parameters, and achieve the goal of energy saving on the basis of delay control.

A number of emerging distributed platforms include fixed and robust workstations but, like dynamic and pervasive networks, are often built from mobile and resource-constrained devices. These networks are characterized by the volatility of their hosts and connections, which may lead to network fragmentation. Although increasingly common, they remain a challenging target for distributed applications. In this paper, we focus on component-based distributed applications by addressing the distribution and the deployment of software components on dynamic pervasive networks. We present a distribution scheme and some associated middleware mechanisms that allow a component to provide its services in an ubiquitous way. First, an architecture description language extension is proposed in order to specify a deployment, driven by constraints on the resources needed by components. Then, a propagative and autonomic deployment process is explained, which is based on a consensus algorithm adapted for dynamic networks. Lastly, implementation details and experiment results are given.

The drift away from monolithic towards distributed, service-oriented application scenarios results in a couple of new challenges concerning the management of these systems. One particular area is the management of dependencies between services. Dependencies can have different appearances, for instance, functional dependencies, semantic integrity conditions, or even dependencies to hardware resources. In this paper we consider services which are provided by software components. The usage of software components promises to allow for flexible and highly tailorable software systems. In the context of our research we consider dependencies in order to enhance the tailorability of component- based, distributed applications. We explain different occurrences of dependencies as well as the necessity of dependency management for adaptations in component-based applications. The paper focuses on a component architecture which allows the deployment of components as well as the management of dependencies between components.

Microelectronics mounted on a piezoelectric transducer: Method, simulations, and measurements

This study presents a comprehensive analysis of power consumption in the context of AR applications on the HoloLens 2. As an ablation study, the research systematically dissects various aspects, shedding light on both hardware and software components. The power consumption was examined in diverse scenarios, ranging from the device at idle to running AR applications of increasing complexity. Overall, the study provides insights into the power management aspects associated with Hololens 2 AR devices and applications, offering cues for optimizing energy efficiency and enhancing the user experience. The findings confirm that display-related factors, such as the screen brightness and content complexity, significantly impact power consumption. However, the results reveal that power usage does not scale linearly with the number of objects in an AR scene due to overhead factors and object occlusion. Furthermore, usage scenarios such as lighting conditions and large/minor user motions are analyzed. Moreover, the influence of different development platforms, Unity and Unreal, on power consumption is discussed, highlighting their respective contributions to energy usage. These findings might be useful for researchers, developers, and users of AR technology.