Heterogeneity-conscious parallel query execution

Purpose – This paper aims to describe the creation of innovative and intelligent systems to optimise energy efficiency in manufacturing. The systems monitor energy consumption using ambient intelligence (AmI) and knowledge management (KM) technologies. Together they create a decision support system as an innovative add-on to currently used energy management systems. Design/methodology/approach – Energy consumption data (ECD) are processed within a service-oriented architecture-based platform. The platform provides condition-based energy consumption warning, online diagnostics of energy-related problems, support to manufacturing process lines installation and ramp-up phase and continuous improvement/optimisation of energy efficiency. The systems monitor energy consumption using AmI and KM technologies. Together they create a decision support system as an innovative add-on to currently used energy management systems. Findings – The systems produce an improvement in energy efficiency in manufacturing small- and medium-sized enterprises (SMEs). The systems provide more comprehensive information about energy use and some knowledge-based support. Research limitations/implications – Prototype systems were trialled in a manufacturing company that produces mooring chains for the offshore oil and gas industry, an energy intensive manufacturing operation. The paper describes a case study involving energy-intensive processes that addressed different manufacturing concepts and involved the manufacture of mooring chains for offshore platforms. The system was developed to support online detection of energy efficiency problems. Practical implications – Energy efficiency can be optimised in assembly and manufacturing processes. The systems produce an improvement in energy efficiency in manufacturing SMEs. The systems provide more comprehensive information about energy use and some knowledge-based support. Social implications – This research addresses two of the most critical problems in energy management in industrial production technologies: how to efficiently and promptly acquire and provide information online for optimising energy consumption and how to effectively use such knowledge to support decision making. Originality/value – This research was inspired by the need for industry to have effective tools for energy efficiency, and that opportunities for industry to take up energy efficiency measures are mostly not carried out. The research combined AmI and KM technologies and involved new uses of sensors, including wireless intelligent sensor networks, to measure environment parameters and conditions as well as to process performance and behaviour aspects, such as material flow using smart tags in highly flexible manufacturing or temperature distribution over machines. The information obtained could be correlated with standard ECD to monitor energy efficiency and identify problems. The new approach can provide effective ways to collect more information to give a new insight into energy consumption within a manufacturing system.

Heterogeneous processors that mix big high performance cores with small low power cores promise excellent single-threaded performance coupled with high multi-threaded throughput and higher performance-per-watt. A significant portion of the commercial multicore heterogeneous processors are likely to have a common instruction set architecture( ISA). However, due to limited design resources and goals, each core is likely to contain ISA extensions not yet implemented in the other core. Therefore, such heterogeneous processors will have inherent functional asymmetry at the ISA level and face significant software challenges. This paper analyzes the software challenges to the operating system and the application layer software on a heterogeneous system with functional asymmetry, where the ISA of the small and big cores overlaps. We look at the widely deployed Intel® Architecture and propose solutions to the software challenges that arise when a heterogeneous processor is designed around it. We broadly categorize functional asymmetries into those that can be exposed to application software and those that should be handled by system software. While one can argue that new software written should be heterogeneity-aware, it is important that we find ways in which legacy software can extract the best performance from heterogeneous multicore systems.

Efficiency of electron transport processes

Heat Treatment Process Energy Efficient Design and Optimisation

Currently, the traditional magnesium oxide production process is facing exceptional challenges arising from carbon emission restrictions and environmental protection. Waste bischofite pyrolysis has attracted much attention as a promising technology to address these challenges. Nonetheless, this process has primarily been demonstrated on a laboratory scale, with limited studies on an industrial scale. A comprehensive exergy analysis was conducted for the entire process and individual subunits within the pyrolysis process to identify potential areas for process enhancement. A FORTRAN subroutine based on empirical correlations of pyrolysis product yields was developed considering the impact of decomposition reactions on the simulation. Furthermore, the optimization of energy and exergy efficiency of the system was discussed in terms of the carbon dioxide emission factor, equivalence ratio, and pyrolysis temperature. The results show that the primary energy bottleneck lies in the combustion phase. In addition, the optimal energy and exergy efficiency conditions are a carbon dioxide emission factor of 5.3, an equivalent ratio of 1.15, and a pyrolysis temperature of 1100 °C. In comparison to the pilot-scale conditions, the energy efficiency and exergy efficiency increase by 2.55 and 3.61%, respectively. At this time, the MgO yield is 100%, and the HCl concentration is above 9.33%.

Energy efficiency evaluation of industrial park customers is carried out to help customers develop optimization strategies and improve the energy efficiency level. The evaluation indexes are proposed based on pressure-state-response (PSR) model and the redundant indexes are selected by combining principal component analysis (PCA) and correlation analysis. Thus the dynamic energy efficiency index system is constructed. The weight of indexes is calculated by the entropy weight method (EWM). An energy efficiency evaluation model based on improved Grey-technique for order preference by similarity to ideal solution (TOPSIS) is proposed, which replaces the Euclidean distance by weighted grey correlation degree and can accurately evaluate customers’ energy efficiency level. An energy efficiency optimization model is proposed, which can maximize optimization benefits while improving energy efficiency. The validity of the evaluation and optimization models is verified by the case study of an industrial park.

Energy efficiency (EE) optimization is investigated for a multi-user cognitive radio network (CRN) over multiple-input-multiple-output (MIMO) interference channels (ICs). To reduce the system overhead due to information exchange among the secondary CR uses (SUs), the EE optimization problem is formulated as a non-cooperative game, where each SU transmitter competes against the other SU pairs by optimizing its transmit covariance matrix. Specifically, each multi-antenna SU maximizes locally its energy efficiency in terms of the number of bits transmitted per unit energy consumption, subject to the per-SU transmit power constraint and the primary user (PU) perceived total interference constraint. It is proved that the formulated non-cooperative game admits at least one Nash equilibrium (NE), and the sufficient condition for a unique NE is derived subsequently. Primal decomposition is employed in the local EE optimization problem to relax the coupling PU perceived interference constraint such that fully distributed operation is allowed. A distributed iterative EE optimization algorithm (DIEEOA) is then proposed to obtain the unique NE, which is shown to converge to the global optimum. Linear precoding techniques are employed to mitigate the impacts of multi-user interference and imperfect channel state information (CSI). Through numerical simulations, effectiveness of the proposed scheme is validated and the system setting parameters' impacts on the performance are studied.

Next-generation wireless communications are expected to provide reliable high-rate connectivity. The recent concept of fog-enabled architecture comes to rescue by invoking a substantial amount of data storage close to end-user devices for meeting these challenges. Thus, caching popular contents at heterogeneous devices, e.g., fog nodes (FNs) or fog access points (FAPs), constitutes a promising technique of reducing both the traffic and the energy consumption of the backhaul links. Therefore, in this paper, we propose an energy-efficient caching and node association algorithm for cache-aided fog networks. First, we solve the problem of energy-efficient content caching and delivery in the FNs/FAPs in conjunction with a fixed node association strategy, where the FNs communicate either with other FNs by node-to-node (N2N) communications or with the FAPs in their proximity. In both caching scenarios, we investigate the relationship between the caching probability of the file and the energy-efficient content delivery by formulating the associated energy efficiency (EE) optimization problem under caching memory constraints. Then, we derive a joint modulation mode allocation strategy and caching policy for each content caching node and conceive a joint node association and caching algorithm for maximizing the EE. Finally, we quantify both the overall EE and throughput for demonstrating that the proposed caching and transmission strategy achieves significant performance improvements.

Recently, FPGA-based CNN accelerators have demonstrated superior energy efficiency compared to high-performance devices like GPGPUs. However, due to the constrained on-chip resource and many other factors, single-board FPGA designs may have difficulties in achieving optimal energy efficiency. In this paper we present a deeply pipelined multi-FPGA architecture that expands the design space for optimal performance and energy efficiency. A dynamic programming algorithm is proposed to map the CNN computing layers efficiently to different FPGA boards. To demonstrate the potential of the architecture, we built a prototype system with seven FPGA boards connected with high-speed serial links. The experimental results on AlexNet and VGG-16 show that the prototype can achieve up to 21x and 2x energy efficiency compared to optimized multi-core CPU and GPU implementations, respectively.

The unmanned aerial vehicle (UAV) assisted communication can significantly improve the coverage and spectrum efficiency of the Internet of Things (IoT). One main feature of IoT is short packet communication (SPC), in which the data transmission uses finite block-length codewords. The transmission rate and the packet error rate will affect the effective throughput of the IoT. In this paper, we investigate the impact of SPC on the performance of UAV-enabled spectrum sharing network. Specifically, the optimization of energy efficiency (EE) in the UAV communication system is considered since the battery of the UAV is usually limited. We design the packet error rate, the sensing duration, the normalized sensing threshold and the UAV’s transmit power to maximize the EE under the constraint that the primary user is sufficiently protected. Since the system parameters are intertwined with each other, we employ a successive optimization algorithm to solve the optimization problem by dividing it into three subproblems. Then, an efficient iterative algorithm is proposed to obtain the optimal parameters. Simulation results reveal that the proposed algorithm can converge to global optimal value and has better EE performance than other benchmark schemes. And there is a fundamental tradeoff between the throughput and the EE.

The present current study aimed at analyzing the input–output energies and optimizing energy efficiency and greenhouse gases (GHG) in crops production at the northeast of Iran. The results of this research showed that the total energy inputs were equal to 42.4, 28.6, and 72.8 GJha−1 for, wheat, barley, and sugar beet, respectively. It was also shown that the highest energy efficiency, the lowest GHG emissions, and GHG intensity all belonged to barley production. The highest percentage of GHG intensity pertained to sugar beet production (41%), which was followed by wheat (38%) and barley (21%). It was also revealed that GHG intensity is a better criterion for the study of GHG since it also makes use of the energy output information in crops. The optimal model responses for the crop type and proper cultivation planning was 284432 hectares in terms of barley production, while those responses for wheat and sugar beet were zero and, thereby, they were eliminated from the model of Multiple Goal Programming (MGP). In the same way, this model could increase energy efficiency to 444875, while GHG emissions and its intensity decreased by 213259 tonCO2eq and 1.3 tonCO2eq MJoutput−1 per year, respectively.

Cell discontinuous transmission (DTX) has been proposed as a solution to reduce the energy consumption of cellular networks. This paper investigates the impact of network traffic load on the spectral and energy efficiency of cellular networks with DTX. The signal-to-interference-plus-noise ratio (SINR) distribution as a function of traffic load is derived first. Then, the sufficient condition for ignoring thermal noise and simplifying the SINR distribution is investigated. Based on the simplified SINR distribution, the network spectral and energy efficiency as functions of network traffic load are derived. It is shown that the network spectral efficiency increases monotonically in traffic load, while the optimal network energy efficiency depends on the ratio of the sleep-mode power consumption to the active-mode power consumption of base stations. If the ratio is larger than a certain threshold, the network energy efficiency increases monotonically with network traffic load and is maximized when the network is fully loaded. Otherwise, the network energy efficiency first increases and then decreases in network traffic load. The optimal load can be identified with a binary search algorithm. The power ratio threshold depends solely on the path loss exponent α, e.g., 56% for α = 4. All these analytic results are further validated by the numerical simulations.

Heterogeneous-ISA multi-core architectures have emerged as a promising design paradigm given the ever-increasing demands on single threaded performance. Such architectures comprise multiple cores that differ not just in micro-architectural parameters (e.g., fetch width, ROB size) but also in their Instruction Set Architectures (ISAs). These architectures extract previously latent performance gains by executing different phases of the program on the core (and ISA) best suited to it, as opposed to executing the entire program on a single ISA. In such a computing paradigm, maximum performance is only extracted when we ensure that at every point in the program’s execution, the program runs on the core best suited to it. In this work, we propose a migration framework that practically and accurately decides when to migrate the program across different cores (and ISAs) to extract maximum performance gains. Under the covers, this framework combines a regression based performance modelling technique with a greedy scheduling algorithm. Our performance modelling technique leverages hardware performance counters prevalent in all major processors today to accurately estimate the performance of the program on different ISAs to within an error of 6%. Putting it together with our greedy scheduler enables our framework to achieve single thread performance speedups of 29.6% with respect to a baseline single ISA heterogeneous architecture.

Energy efficiency improvement and optimization of energy aspects on new developments and projects has always potential to reduce emissions. It also has potential to reduce depletion of non-renewable energy resources, in addition to the potential benefits in project economics, through reduction of capital and/or operating cost. Realizing the gravity, GASCO which is one of the largest onshore gas processing companies, decided to develop a comprehensive Framework to focus energy efficiency improvement and optimization at project phase. GASCO started by outlining the specific objectives to be achieved regarding energy optimization and energy efficiency improvement thru energy aspects consideration, with emphasis on complete project lifecycle. Subsequently, developed the comprehensive framework to achieve the objectives. This framework is referred as GASCO Project Energy Optimization (PEO) Framework. The PEO Framework provides a structured process for review and optimization of energy aspects on new projects and defines the requirements for energy planning and reporting throughout the project lifecycle. Key components of the framework include processes for assessment and optimization of energy aspects, techniques for assessing energy aspects through workshops and desk top studies and guidance on energy optimization at an overall level, process system level and detailed equipment level. GASCO implemented the PEO Framework on two of its major projects. Numerous challenges were faced during initial implementation of PEO Framework. Few of the key challenges faced were lack of integration of energy optimization activities with traditional working of multiple disciplines engaged on the project, lack of familiarization with PEO Framework, difficulty in PEO Framework based scope comprehension and benefits quantification. GASCO tackled these challenges by appropriate improvement measures including PEO Framework introduction and orientation sessions for project personnel, nomination of focal person to respond all PEO Framework related clarifications and development or improvement of methodologies and techniques on case to case basis. Substantial benefits were realized in PEO Framework implementation in terms of system improvement as well as project-specific energy performance improvement. Few of the benefits availed include demonstration of effective energy information flow across discrete phases of project lifecycle, energy aspects reporting and tracking, experience of organizing and conducting Energy Review Workshops, introduction of energy related performance guarantees and development of technique for benefits quantification. PEO Framework implementation on two projects has substantively achieved the underlying objective of formal evaluation of energy aspects. Further, awareness and knowledge about PEO Framework procedures & requirements has increased among GASCO staff as well as project teams of respective Consultant / PMC. The paper throws light on the key attributes and features of PEO framework and shares the experience of its implementation on two major projects.

ABSTRACTNonlinearity in parallel compliance can be exploited to improve the performance of locomotion systems in terms of (1) energy efficiency, (2) control robustness, and (3) gait optimality; that is, attaining energy efficiency across a set of motions. Thus far, the literature has investigated and validated only the first two benefits. In this study, we present a new mathematical framework for designing nonlinear compliances in cyclic tasks encompassing all three benefits. We present an optimization‐based formulation for each benefit to obtain the desired compliance profile. Furthermore, we analytically prove that, compared to linear compliance, using nonlinear compliance leads to (1) lower energy consumption, (2) better closed‐loop performance, specifically in terms of tracking error, and (3) a higher diversity of natural frequencies. To compare the performance of linear and nonlinear compliance, we apply the proposed methods to a diverse set of robotic systems performing cyclic tasks, including a 2‐DOF manipulator, a 3‐DOF bipedal walker, and a hopper model. Compared to linear compliance, the nonlinear compliance leads to better performance in all aspects; for example, a 70% reduction in energy consumption and tracking error for the manipulator simulation. Regarding gait optimality, for all robotic simulation models, compared to linear compliance, the nonlinear compliance has lower energy consumption and tracking error over the considered set of motions. The proposed analytical studies and simulation results strongly support the idea that using nonlinear compliance significantly improves robotic system performance in terms of energy efficiency, control robustness, and gait optimality.