Developing platform specific model for MPSoC architecture from UML-based embedded software models

In this paper, we describe a technique to design UML-based software models for MPSoC architecture, which focuses on the development of the platform specific model of embedded software. To develop the platform specific model, we define a process for the design of UML-based software model and suggest an algorithm with precise actions to map the model to MPSoC architecture. In order to support our design process, we implemented our approach in an integrated tool. Using the tool, we applied our design technique to a target system. We believe that our technique provides several benefits such as improving parallelism of tasks and fast-and-valid mapping of software models to hardware architecture.     

Energy consumption and execution time estimation of embedded system applications

Embedded systems often have conflicting constraints such as energy and time which considerably harden the design of those systems. In this context, this work proposes a mechanism for supporting design decisions on energy consumption and performance of embedded system applications. In order to depict the practical usability of the proposed methodology, a real case study as well as customized examples are presented. The estimates obtained through the conceived model are 93% close to the respective measures obtained from the real hardware platform.     

The case for reconfigurable hardware in wearable computing

Wearable computers are embedded into the mobile environment of their users. A design challenge for wearable systems is to combine the high performance required for tasks such as video decoding with the low energy consumption required to maximise battery runtimes and the flexibility demanded by the dynamics of the environment and the applications. In this paper, we demonstrate that reconfigurable hardware technology is able to answer this challenge. We present the concept and the prototype implementation of an autonomous wearable unit with reconfigurable modules (WURM). We discuss experiments that show the uses of reconfigurable hardware in WURM: ASICs-on-demand and adaptive interfaces. Finally, we present an experiment with an operating system layer for WURM.     

Impact of level-2 cache sharing on the performance and power requirements of homogeneous multicore embedded systems

In order to satisfy the needs for increasing computer processing power, there are significant changes in the design process of modern computing systems. Major chip-vendors are deploying multicore or manycore processors to their product lines. Multicore architectures offer a tremendous amount of processing speed. At the same time, they bring challenges for embedded systems which suffer from limited resources. Various cache memory hierarchies have been proposed to satisfy the requirements for different embedded systems. Normally, a level-1 cache (CL1) memory is dedicated to each core. However, the level-2 cache (CL2) can be shared (like Intel Xeon and IBM Cell) or distributed (like AMD Athlon). In this paper, we investigate the impact of the CL2 organization type (shared Vs distributed) on the performance and power consumption of homogeneous multicore embedded systems. We use VisualSim and Heptane tools to model and simulate the target architectures running FFT, MI, and DFT applications. Experimental results show that by replacing a single-core system with an 8-core system, reductions in mean delay per core of 64% for distributed CL2 and 53% for shared CL2 are possible with little additional power (15% for distributed CL2 and 18% for shared CL2) for FFT. Results also reveal that the distributed CL2 hierarchy outperforms the shared CL2 hierarchy for all three applications considered and for other applications with similar code characteristics.     

Minimax method in optimizing energy consumption in real-time embedded systems

The main principles of the minimax method designed for solving energy consumption optimization problems in real-time embedded systems are presented. Results of comparing ways to minimize energy consumption in systems with on-line minimax and off-line DVS/DFS scheduling are given. In terms of energy consumption minimization, the minimax method is shown to ensure optimal division of the task into two subtasks. This method can be applied both to systems with tasks arbitrarily distributed in time and to periodic multitasking systems with rigid timing constraints.     

基于嵌入式软件算法级能耗问题研究

能耗已经成为嵌入式系统设计中一个重要的约束条件.嵌入式系统是典型的软件驱动执行系统,硬件的电路活动直接导致系统参数功耗,而软件中的指令执行和数据存取等操作底层的微处理、总线、Cache、存储器和I/O接口等硬件的活动都会间接的导致系统参数功耗.在现代“低碳经济”的背景下嵌入系统的功耗已经引起人们关注的一个重点.而软件设计早期对高层所作的功率耗评估和优化对整个系统的的能耗影响最为显著.本文通过构建算法级能耗估算模型,并通过实例采用神经网络算法、遗传算法等进行能耗求解,同时在求解过程中进行能耗分析.     

BIM-based investigation of total energy consumption in delivering building products

Considerable efforts have been made to reduce buildings’ operational energy use over the last decades, but little attention has been paid to reduce the material transportation and construction energy. Focusing only on the operation phase forgoes the opportunity to reduce other building-related energy consumption, and even if the environmental impacts arising from construction and transportation are small as compared to the operation phases, its cumulative impact at the national level is of concern.The energy consumed by a building is divided into two parts embodied energy and operation energy. Further, the embodied energy is constituted of energy intensity of materials, energy consumed during transportation and energy consumed for construction. This paper proposes a methodology to integrate embodied energy consumption into a BIM platform and provides a seamless analysis based on available information. Plug-ins are developed to fulfill a convenient linkage between the BIM model and external databases. Simulation models are created, which can be used as templates for energy optimization during transportation and construction. By analyzing different resource combination scenarios, lower energy consumption can be achieved.     

Provisioning of energy consumption information for mobile ads

Advertisement-embedded mobile applications have been reported to consume a non-trivial amount of energy. Although a few studies have focused on the energy consumption of mobile advertisements (ads), no previous work has addressed the mobile ad ecosystem, which consists of users, application developers, and ad providers. In this paper, we define the advertisement energy information (AEI) required for the mobile ad ecosystem, and we propose a set of application programming interfaces (APIs) to provide AEI that considers various requirements of the underlying ecosystem. To realize the APIs, we developed a system service in Android to collect the AEI accurately and with low overhead. The experiment results show the validity of the proposed scheme, and the case studies demonstrate the usefulness of the proposed APIs.     

A high-level energy consumption model for heterogeneous data centers

Data centers consume anywhere between 1.7% and 2.2% of the United States’ power. A handful of studies focused on ways of predicting power consumption of computing platforms based on performance events counters. Most of existing power-consumption models retrieve performance counters from hardware, which offer accurate measurement of energy dissipation. Although these models were verified on several machines with specific CPU chips, it is difficult to deploy these models into data centers equipped by heterogeneous computing platforms. While models based on resource utilization via OS monitoring tools can be used in heterogeneous data centers, most of these models were linear model. In this paper, we analyze the accuracy of linear models with the SPECpower benchmark results, which is a widely adopted benchmark to evaluate the power and performance characteristics of servers. There are 392 published results until October 2012; these servers represent most servers in heterogeneous data centers. We use R-squared, RMSE (Root Mean Square Error) and average error to validate the accuracy of the linear model. The results show that not all servers fit the linear model very well. 6.5% of R-squared values are less than 0.95, which means linear regression does not fit the data very well. 12.5% of RMSE values are greater than 20, which means there is still big difference between modeled and real power consumption. We extend the linear model to high degree polynomial models. We found the cubic polynomial model can get better results than the linear model. We also apply the linear model and the cubic model to estimate real-time energy consumption on two different servers. The results show that linear model can get accurate prediction value when server energy consumption swing in a small range. The cubic model can get better results for servers with small and wide range.     

Trade-off analysis between machining time and energy consumption in impeller NC machining

Electrical energy is directly linked to society's prosperity across the globe; much of this due to the diverse innovations on manufacturing processes. Keeping pace with the high energy demand growth will require constant efforts in terms of investment and research in order to bring new alternatives of usage. This paper outlines the application of multiple response optimization in order to analyze the trade-off between machining time and energy consumption in 5-axis impeller rough machining to find a possible balance between them. It is well known that a higher speed reduces machining time but increases energy consumption, and vice versa. A quantitative form of the relationship between the involved factors was obtained by utilizing response surface methodology (RSM) together with the desirability function method. Four independent factors were selected, namely, spindle speed, feed rate, depth and width of cut. The responses are the consumed energy and the machining time. The results showed that selecting an appropriate feed rate is crucial to balance the trade-offs between energy and time. Spindle speed is the major factor for energy consumption, while width of cut is the most influential factor for machining time.     

Multi-source data analytics for AM energy consumption prediction

The issue of Additive Manufacturing (AM) system energy consumption attracts increasing attention when many AM systems are applied in digital manufacturing systems. Prediction and reduction of the AM energy consumption have been established as one of the most crucial research targets. However, the energy consumption is related to many attributes in different components of an AM system, which are represented as multiple source data. These multi-source data are difficult to integrate and to model for AM energy consumption due to its complexity. The purpose of this study is to establish an energy value predictive model through a data-driven approach. Owing to the fact that multi-source data of an AM system involves nested hierarchy, a hybrid approach is proposed to tackle the issue. This hybrid approach incorporates clustering techniques and deep learning to integrate the multi-source data that is collected using the Internet of Things (IoT), and then to build the energy consumption prediction model for AM systems. This study aims to optimise the AM system by exploiting energy consumption information. An experimental study using the energy consumption data of a real AM system shows the merits of the proposed approach. Results derived using this hybrid approach reveal that it outperforms pre-existing approaches.     

Design space exploration for partially reconfigurable architectures in real-time systems

In this paper, we introduce FoRTReSS (Flow for Reconfigurable archiTectures in Real-time SystemS), a methodology for the generation of partially reconfigurable architectures with real-time constraints, enabling Design Space Exploration (DSE) at the early stages of the development. FoRTReSS can be completely integrated into existing partial reconfiguration flows to generate physical constraints describing the architecture in terms of reconfigurable regions that are used to floorplan the design, with key metrics such as partially reconfigurable area, real-time or external fragmentation. The flow is based upon our SystemC simulator for real-time systems that helps develop and validate scheduling algorithms with respect to application timing constraints and partial reconfiguration physical behaviour. We tested our approach with a video stream encryption/decryption application together with Error Correcting Code and showed that partial reconfiguration may lead to an area improvement up to 38% on some resources without compromising application performance, in a very small amount of time: less than 30 s.     

A hybrid integrated architecture for energy consumption prediction

Irresponsible and negligent use of natural resources in the last five decades has made it an important priority to adopt more intelligent ways of managing existing resources, especially the ones related to energy. The main objective of this paper is to explore the opportunities of integrating internal data already stored in Data Warehouses together with external Big Data to improve energy consumption predictions. This paper presents a study in which we propose an architecture that makes use of already stored energy data and external unstructured information to improve knowledge acquisition and allow managers to make better decisions. This external knowledge is represented by a torrent of information that, in many cases, is hidden across heterogeneous and unstructured data sources, which are recuperated by an Information Extraction system. Alternatively, it is present in social networks expressed as user opinions. Furthermore, our approach applies data mining techniques to exploit the already integrated data. Our approach has been applied to a real case study and shows promising results. The experiments carried out in this work are twofold: (i) using and comparing diverse Artificial Intelligence methods, and (ii) validating our approach with data sources integration.     

Stacking Deep learning and Machine learning models for short-term energy consumption forecasting

Accurate prediction of electricity consumption is essential for providing actionable insights to decision-makers for managing volume and potential trends in future energy consumption for efficient resource management. A single model might not be sufficient to solve the challenges that result from linear and non-linear problems that occur in electricity consumption prediction. Moreover, these models cannot be applied in practice because they are either not interpretable or poorly generalized. In this paper, a stacking ensemble model for short-term electricity consumption is proposed. We experimented with machine learning and deep models like Random Forests, Long Short Term Memory, Deep Neural Networks, and Evolutionary Trees as our base models. Based on the experimental observations, two different ensemble models are proposed, where the predictions of the base models are combined using Gradient Boosting and Extreme Gradient Boosting (XGB). The proposed ensemble models were tested on a standard dataset that contains around 500,000 electricity consumption values, measured at periodic intervals, over the span of 9 years. Experimental validation revealed that the proposed ensemble model built on XGB reduces the training time of the second layer of the ensemble by a factor of close to 10 compared to the state-of-the-art , and also is more accurate. An average reduction of approximately 39% was observed in the Root mean square error.     

A-PIE: An algorithm for preserving privacy,quality of information,and energy consumption in Participatory Sensing Systems

We present A-PIE, a hybrid privacy-preserving mechanism for Participatory Sensing Systems that provides a high level of privacy protection as well as a high quality of information while minimizing the energy consumption. A-PIE takes into consideration the variability of the variable of interest to identify clusters, and divides the target area in cells of different sizes. A-PIE applies anonymization or double-encryption to balance privacy protection, quality of information and energy consumption based on the cell’s size. Extensive experimentation, using a real air monitoring system, shows the superior performance of the proposed mechanism when compared with most important privacy-preserving mechanisms.     

Software performance tuning of software product family architectures: Two case studies in the real-time embedded systems domain

Software performance is an important non-functional quality attribute and software performance evaluation is an essential activity in the software development process. Especially in embedded real-time systems, software design and evaluation are driven by the needs to optimize the limited resources, to respect time deadlines and, at the same time, to produce the best experience for end-users. Software product family architectures add additional requirements to the evaluation process. In this case, the evaluation includes the analysis of the optimizations and tradeoffs for the whole products in the family. Performance evaluation of software product family architectures requires knowledge and a clear understanding of different domains: software architecture assessments, software performance and software product family architecture. We have used a scenario-driven approach to evaluate performance and dynamic memory management efficiency in one Nokia software product family architecture. In this paper we present two case studies. Furthermore, we discuss the implications and tradeoffs of software performance against evolvability and maintenability in software product family architectures.     

Forecasting building energy consumption: Adaptive long-short term memory neural networks driven by genetic algorithm

The real-world building can be regarded as a comprehensive energy engineering system; its actual energy consumption depends on complex affecting factors, including various weather data and time signature. Accurate energy consumption forecasting and effective energy system management play an essential part in improving building energy efficiency. The multi-source weather profile and energy consumption data could enable integrating data-driven models and evolutionary algorithms to achieve higher forecasting accuracy and robustness. The proposed building energy consumption forecasting system consists of three layers: data acquisition and storage layer, data pre-processing layer and data analytics layer. The core part of the data analytics layer is a hybrid genetic algorithm (GA) and long-short term memory (LSTM) neural network model for accurate and robust energy prediction. LSTM neural network is adopted to capture the interrelationship between energy consumption data and time. GA is adopted to select the optimal architecture for LSTM neural networks to improve its forecasting accuracy and robustness. The hyper-parameters for determining LSTM architecture include the number of LSTM layers, number of neurons in each LSTM layer, dropping rate of each LSTM layer and network learning rate. Meanwhile, the effects of historical weather profile and time horizon of past information are also investigated. Two real-life educational buildings are adopted to test the performance of the proposed building energy consumption forecasting system. Experiments reveal that the proposed adaptive LSTM neural network performs better than the existing feedforward neural network and LSTM-based prediction models in accuracy and robustness. It also outperforms those LSTM networks whose hyper-parameters are determined by grid search, Bayesian optimisation and PSO. Such accurate energy consumption prediction can play an essential role in various areas, including daily building energy management, decision making of facility managers, building information model designs, net-zero energy operation, climate change mitigation and circular economy.     

An empirical analysis of energy consumption of cross-platform frameworks for mobile development

The increasing fragmentation of mobile devices market has created the problem of supporting all the possible mobile platforms to reach the highest number of potential users. One possible solution is to use cross-platform frameworks, that let develop only one application that is then deployed to all the supported target platforms. Currently available cross-platform frameworks follow different approaches to deploy the final application, and all of them has pros and cons. In this paper, we evaluate and compare together the current frameworks for cross-platform mobile development considering one of the most important aspect when dealing with mobile devices: energy consumption. Our analysis shows and measure how the adoption of cross-platform frameworks impacts energy consumption with respect to the native mobile development, identifies which are the most consuming tasks, and tries to define a final rank among all the different approaches. Moreover, we highlight future development necessary to improve performances of cross-platform frameworks to reach native development performances.     

嵌入式系统动态数据结构优化的并行进化算法

为了更好地解决现代多媒体嵌入式系统动态数据结构优化问题,结合NSGA-II和SPEA2两个多目标进化算法,引入岛屿模型和多线程机制,提出了一种并行多目标进化算法--PMOEA-NS。基于多核计算机系统,使用PMOEA-NS具体的3个不同并行算法和串行NSGA-II、SPEA2,对一个实际动态嵌入式应用程序进行优化实验和计算,结果表明:与串行算法NSGA-II和SPEA2相比,并行算法不但提高了优化过程的速度,而且改善了解的质量和多样性。