CPUs Energy Consumption Reduction for Asynchronous Parallel Methods Running over Grids

It is widely accepted that the asynchronous parallel methods are more suitable than the synchronous ones on a grid architecture. Indeed, they outperform the synchronous methods, because they overlap the communications of the synchronous methods with computations. However, they also usually execute more iterations than the synchronous ones and thus consume more energy. To reduce the energy consumption of the CPUs executing such methods, the Dynamic voltage and frequency scaling technique can be used. It lowers the frequency of a CPU to reduce its energy consumption, but it also decreases its computing power. Therefore, the frequency that gives the best trade-off between energy consumption and performance must be selected. This paper presents a new online frequency selecting algorithm for parallel iterative asynchronous methods running over grids. It selects a vector of frequencies that gives the best trade-off between energy consumption and performance. New energy and performance models were used in this algorithm to predict the execution time and the energy consumption of synchronous, asynchronous, or hybrid iterative applications running over grids. The proposed algorithm was evaluated on the SimGrid simulator. The experiments showed that synchronously applying the proposed algorithm to the asynchronous version of the application reduces on average its energy consumption by 22% and speeds it up by 5.72%. Finally, the proposed algorithm was also compared to a method that uses the well-known energy and delay product and the comparison results showed that it outperforms this method in terms of energy consumption and performance.

This chapter presents the principles of asynchronous iterative methods and shows how these methods can be applied to sub-structuring methods. Asynchronous iterative methods are not used much today, but new needs arise from new hardware architectures and asynchronous methods become a suitable solution for large scale computation. The major reason is that these methods are much less dependent on the interconnection latency and bandwidth. This chapter first introduces the asynchronous concept on simple iterative algorithms. Next the extension to asynchronous sub-structuring methods is presented. Numerical results, showing the robustness and efficiency of these asynchronous sub-structuring methods, are finally presented.

Near Zero Energy Building implementation requires effective energy management and sufficient energy production. Thailand follows Energy Efficiency Plan 2018 and Alternative Energy Development Plane 2018, which are the energy reduction plan and alternative energy production plan, respectively. However, these plans are country scale guidelines, neither of them provides detail on a building or a household scale. This paper presents a case study of energy improvement on an existing building. The pre-improvement energy consumption was analyzed in detail. Accordingly, both energy reduction measures combine with PV energy production together with energy storage were deployed. Post- improvement energy consumption and production are discussed and Near Zero Energy Building an index is proposed. The results show that the energy reduction measures decrease the specific energy consumption of the pre-improvement energy consumption down 38.82%, which is from the value of 116.02 kWh/m2-yr to 70.99 kWh/m2-yr. Together with PV production, which generates electrical energy with the amount of 50.4 kWh/m2-yr, the net specific energy consumption of the sample building is 20.59 kWh/m2-yr. However, the installation cost of PV system is higher than the energy reduction cost. This makes increasing energy production to cover pre-improvement energy consumption financially impractical. The management of energy production and energy reduction should be deployed together to make a Near Zero Energy Building financially practical.

Models of energy consumption and performance are necessary to understand and identify system behavior, prior to designing advanced controls that can balance out performance and energy use. This paper considers the energy consumption and performance of servers running a relatively simple file-compression workload. We found that standard techniques for system identification do not produce acceptable models of energy consumption and performance, due to the intricate interplay between the discrete nature of software and the continuous nature of energy and performance. This motivated us to perform a detailed empirical study of the energy consumption and performance of this system with varying compression algorithms and compression levels, file types, persistent storage media, CPU DVFS levels, and disk I/O schedulers. Our results identify and illustrate factors that complicate the system's energy consumption and performance, including nonlinearity, instability, and multi-dimensionality. Our results provide a basis for future work on modeling energy consumption and performance to support principled design of controllable energy-aware systems.

Predicting energy consumption and savings in the housing stock: A performance gap analysis in the Netherlands

There has been extensive research on mapping and scheduling tasks on a many-core SoC. However, none considers the optimization of communication types, which can significantly affect performance, energy consumption, and local memory usage of the SoC. This paper presents an approach to automatic mapping and scheduling of tasks and communications on a many-core SoC. The key idea is to decide the type of each communication between message passing and shared memory when we do the mapping and scheduling. By assigning a proper type to each communication, we can optimize the energy consumption, performance, or energy-delay product. To solve the optimization problem, the approach adopts a probabilistic algorithm coupled with some heuristics. To enhance throughput of the system, it performs software pipelined scheduling of the tasks using a modified iterative modulo scheduling technique. Experiments show that our algorithm achieves on average 50.1% lower energy consumption, 21.0% higher throughput, and 64.9% lower energy- delay product, compared to shared memory only communication.

Chapter 2 provides an overview of a literature study of the existing knowledge on energy consumption from the urban to the user scale, energy performance modelling methods, the energy performance gap, and insights to determinants of heating energy and electricity consumption. This review first helped to set up a reference point for the reasons to actual occupant behavior, how perception, lifestyle, norms, rules lead to various actions at home (Figure 1). Secondly, through this study, a framework for the relationship between occupant behavior and energy consumption was created (Figure 2), based on the determinants of behavior, i.e. occupant characteristics (educational, economic, social), dwelling characteristics (envelope, systems, lighting and appliances…). This literature study set the context and also the first steps of this research. The determinants found through this review (Table 2) gave input to the content and structure of the questions of the survey designed for the OTB dataset.

This thesis explores the feasibility of converting the current New Zealand commercial building stock to Net Zero Energy (NZE). The analysis presented is grounded in real building performance and construction information. The goal was to establish results that are as realistic as possible to actual building performance. The Net Zero Energy Building (Net ZEB) concept is one of many low energy building movements that respond to the issues of climate change and energy security. The Net ZEB concept strives to reduce demand for energy and then to offset any residual energy consumption with non-CO2 emitting renewable energy technologies. The (re-)design focus for Net ZEBs is to reduce annual energy consumption to be equal to or less than any generated renewable energy. This is an important concept since approximately 40 percent of all energy and emissions worldwide are building related. If all buildings were designed and operated to be NZE, the existing energy can be used by other sectors which will increase energy security. Conversely, reducing the fossil fuel CO2 producing component of the energy consumed by buildings has the benefit of negating building’s contribution to climate change. The Net ZEB concept assumes each building is grid-connected, and balances the energy taken from the grid against the energy put back into the grid over a year. This study exploits the available synergies of the grid connection to achieve NZE for the whole building stock. Thus each individual building does not need to be NZE at the site, but they act as a community to reach NZE collectively. Furthermore, any grid-tied renewable energy does not need to be offset, only the non-renewable portion. A NZE target was calculated to determine the percentage reduction in current energy consumption needed before the current commercial building stock could be considered NZE. It was found that a 45 percent reduction in primary energy would offset all non-renewable CO2 emitting energy supply currently consumed by the New Zealand commercial building stock. Previous studies assessing whether converting an entire stock of commercial buildings to NZE is possible used prototypical building energy models. Prototypical models represent a hypothetical average building and have many assumptions about the way a building is operated. This thesis develops a method that takes a representative sample of real commercial buildings and makes calibrated energy models that can be aggregated to represent energy consumption for all commercial buildings in New Zealand. The developed calibration method makes use of as-built building information and a standardised procedure for identifying the inaccurate model inputs which need to be corrected for a building energy model to be calibrated. To further base the process in reality, a set of Energy Conservation Measures (ECM) that had been implemented in real Net ZEBs worldwide was adopted for the proposed retrofits. These ECMs were combined into Net ZEB solution sets for retrofitting the aggregated commercial building models. Optimisation of the Net ZEB solution sets was performed on hundreds of models to maximise energy savings. It took over six months for all of the optimisations to be completed. This thesis demonstrates the estimated New Zealand commercial building stock’s energy consumption based upon the calibrated energy models was robust by comparing it to an external estimate. It shows that NZE can be achieved by applying well understood Net ZEB solution sets to the New Zealand commercial building stock. 96 percent of the NZE goal is attainable just through demand reduction without the use of onsite renewable energy generation. The additional four percent of reduction required to meet NZE is easily attainable with onsite renewable generation. Another benefit is that the retrofitted commercial buildings will provide improved thermal comfort for the occupants. Having established NZE was possible, this thesis concludes with an analysis of the broader implications of achieving the NZE goal. It identifies the next step would be to design a NZE commercial building stock that reduces the stresses on the existing energy infrastructure. The Solution Set adopted was not developed with the interaction of the building and electrical grid in mind. To have a practical implementation of NZE will require costing and community prioritisation. This would be the next phase of work assessing nationwide NZE retrofit.

As a model for energy transition to low-carbon economy, Denmark is of great importance for studying internal relationships between economic growth, both energy consumption and production, and Carbon emissions. Based on Denmark’s data for the total consumption of petroleum oil and gas resources, total production of oil and gas resources, gross domestic product(constant 2010 US$) and CO2 emissions over the time span 1984-2016, Johansen test shows that there is no cointegration relationship between CO2 emissions and oil and gas consumption, and the autoregressive distributed lag (ARDL) boundary cointegration test shows that there is no cointegration relationship between CO2 emissions and economic growth. Nevertheless, ARDL boundary cointegration test is used to confirm the existence of cointegration between economic growth and both the energy production and consumption. We then establish an error correction model to analyze the short-term relationship between these two cointegrated metrics. The Granger causality test indicates that there is one-way causality between economic growth and energy consumption and energy production; in particular, economic changes help explain changes of energy consumption and production in the future. Finally, the empirical analysis results are further discussed with consideration of Denmark’s energy policies and the current state of its energy economy. The results of the present study can help the other countries in the design of energy development, the clean and low carbon energy transition policies for sustainable and long-term economic development.

The energy consumption of parallel-connected pumps in heating, ventilation, and air-conditioning (HVAC) systems make up a large proportion of building energy consumption leading to an increasing attention for the pump operation. The centralized and distributed methods have been proposed to solve the pump optimization problem, which need the global clock to be synchronized and lead to the increasing system cost and idle time. In this paper, we propose an asynchronous distributed control algorithm for parallel-connected pumps in HVAC systems, which does not need the global clock, reduces the idle time and has the convergence guarantee. Under the bounded delay, the algorithm makes the optimal control decision for pumps to minimize energy consumption and meet the system demand. The theoretical analysis on convergence of the algorithm is established. The whole system is fully distributed and each pump is controlled by an intelligent node that runs identical control code and does not need to be synchronous. Numerical simulations on 6 parallel-connected pumps for different working cases are given to illustrate the effectiveness of the proposed algorithm and compare with the method from other field. The results show that our method strictly meets the constraint and minimizes system energy consumption, fully uses parallel computational resources. The running time of our asynchronous method is near 46% faster than synchronous setting.

Insulating glass unit (IGU) degradation has been studied extensively. However, there is limited understanding of how present durability evaluation standards relate to product lifetime. Furthermore, there is debate on how to quantify performance of installed windows over time to better understand degradation processes. More knowledge on these topics is required to link durability evaluation to product lifetime projections based on energy performance. Energy models provide helpful estimations of total annual building energy consumption. However, most models are based on “as installed” performance of envelope components and fail to account for performance degradation. This can lead to an underestimation of building lifetime energy consumption. A better understanding of the relationship between durability and energy performance can inform integration of degradation dynamics into energy modeling software. This will improve lifetime building energy consumption estimations as well as inform appropriate retrofit strategies and timing. This paper reviews current durability literature, various standards for window performance ratings and weathering methods, existing in situ IGU energy performance measurement techniques, and whole-building energy effects. The challenges and disparities among various studies are analyzed and discussed. The authors hope that further work in this area will lead to the development of improved in situ test methods to assess IGU degradation in the field and link this knowledge to improved energy performance modeling approaches.

A model-based approach for simultaneous water and energy reduction in a pulp and paper mill

Cloud computing becomes a powerful trend in the development of ICT services. It allows dynamic resource scaling from infinite resource pool for supporting Cloud users. Such scenario leads to necessity of larger size of computing infrastructure and increases processing power. Demand on the cloud computing is continually growth that makes it changes to scope of green cloud computing. It aims to reduce energy consumption in Cloud computing while maintaining a better performance. However, there is lack of performance metric that analyzing trade-off between energy consumption and performance. Considering high volume of mixed users’ requirements and diversity of services offered; an appropriate performance model for achieving better balance between Cloud performance and energy consumption is needed. In this work, we focus on green Cloud Computing through scheduling optimization model. Specifically, we investigate a relationship between performance metrics that chosen in scheduling approaches with energy consumption for energy efficiency. Through such relationship, we develop an energy-based performance model that provides a clear picture on parameter selection in scheduling for effective energy management. We believed that better understanding on how to model the scheduling performance will lead to green Cloud computing.

This study introduces an advanced mathematical methodology for predicting energy generation and consumption based on temperature variations in regions with diverse climatic conditions and increasing energy demands. Using a comprehensive dataset of monthly energy production, consumption, and temperature readings spanning ten years (2010–2020), we applied polynomial, sinusoidal, and hybrid modeling techniques to capture the non-linear and cyclical relationships between temperature and energy metrics. The hybrid model, which combines sinusoidal and polynomial functions, achieved an accuracy of 79.15% in estimating energy consumption using temperature as a predictor variable. This model effectively captures the seasonal and non-linear consumption patterns, demonstrating a significant improvement over conventional models. In contrast, the polynomial model for energy production, while yielding partial accuracy (R² = 0.65), highlights the need for more advanced techniques to fully capture the temperature-dependent nature of energy production. The results indicate that temperature variations significantly affect energy consumption, with higher temperatures driving increased energy demand for cooling, while lower temperatures affect production efficiency, particularly in systems like hydropower. These findings underscore the necessity for integrating sophisticated models into energy planning to ensure resilience in energy systems amidst climate variability. The study offers critical insights for policymakers to optimize energy generation and distribution in response to changing climatic conditions.

ObepME: An online building energy performance monitoring and evaluation tool to reduce energy performance gaps