FPGAs are increasingly used in safety-critical applications (e.g., in aerospace and automotive engineering). Safety standards stipulate that implemented countermeasures against run-time faults such as detection and isolation of affected components, automatic reconfiguration, and redundancy mechanisms must be adequately verified. To that end, fault injection tests by various means have been established as a suitable method.For such tests, faults can be provoked by radiation, simulation, or manipulating the design, for example, by inserting additional logic or manipulating the synthesis flow. This work briefly summarizes the various fault injection approaches with a focus on methods that are capable of stressing critical nets of a design running on actual hardware without requiring to re-synthesize. While the state-of-the-art tools can work with complex designs, they often lack controllability of the exact timing of the injection events (which is important to track the system's response on faults in a logic simulation) and/or use a high amount of FPGA resources. To overcome these issues, we propose a resource-saving netlist-based fault injection framework Fault InJection Instrumenter (FIJI) that can target individual nets at test runtime. This paper presents FIJI's work flow, implementation details, and an evaluation in terms of FPGA resources, timing impact, and performance during instrumentation and test execution. The FIJI framework has been made publicly available by the authors under an open-source license.
In today’s Internet, modern routers rely on high-performance reliable general-purpose multi-core packet processing systems in order to support the flexibility and the plethora of protocol operations and applications. These processing systems are programmable and have replaced the traditional-fixed logic ASICs in the data path of such routers. Hence, lots of vulnerabilities and faults are introduced as the result of such programmability making the systems susceptible to attacks and failures. Particularly, it is a difficult task to detect whether a processing core behaves correctly, or it has a failure resulting from errors or attacks. In this paper, we address this problem by proposing a novel approach to verify the correct operation of the network processor. We propose a secure, fault-tolerant, and reliable monitoring subsystem which functions in parallel with the processing core of the router and aids in the detection of attacks changing the processing behavior of the processor. We prove experimentally that our system has the ability to detect the malicious activity and securely restore the router’s operation to a different, but functionally equivalent, state. We also show experimentally that our approach has a better efficiency when compared with other existing work.
Dark silicon has recently emerged as a new problem in VLSI technology. Maximizing performance of chip-multiprocessors (CMPs) under power and thermal constraints is very challenging in the dark silicon era. Providing next-generation analytical models for future CMPs which consider the impact of power consumption of core and uncore components such as cache hierarchy and on-chip interconnect that consume significant portion of the on-chip power consumption is largely unexplored. In this article, we propose a detailed power model which is useful for future CMP power modeling. In the proposed architecture for future CMPs, we exploit emerging technologies such as non-volatile memories (NVMs) and 3D techniques to combat dark silicon. Results extracted from the simulations are compared with those obtained from the analytical model. Comparisons show that the proposed model accurately estimates the power consumption of CMPs running both multi-threaded and multi-programed workloads.
With the ever-growing concerns about carbon emissions and air pollution throughout the world, electric vehicles (EVs) are one of the most viable options for clean transportation. EVs are typically powered by a battery pack such as lithium-ion, which is created from a large number of individual cells. In order to enhance the durability and prolong the useful life of the battery pack, it is imperative to monitor and control the battery packs at the cell level. Model predictive controller (MPC) is considered as a feasible technique for cell-level monitoring and controlling of the battery packs. For instance, the fast-charge MPC algorithm keeps the Li-ion battery cell within its optimal operating parameters while reducing the charging time. In this case, the fast-charge MPC algorithm should be executed on an embedded platform mounted on an individual cell; however, the existing algorithm for this technique is designed for general-purpose computing. In this research work, we introduce novel, unique, and efficient embedded hardware and software architectures for the fast-charge MPC algorithm, considering the constraints and requirements associated with the embedded devices. We create two unique hardware versions: register-based and memory-based. Experiments are performed to evaluate and illustrate the feasibility and efficiency of our proposed embedded architectures. Our embedded architectures are generic, parameterized, and scalable. Our hardware designs achieved 100 times speedup compared to its software counterparts.
A new test data compression scheme for circular scan is proposed in this paper. For circular scan, the response of the previous test vector is used as the next test vector's template, and only the conflicting bits between the previous response and the next vector are required to be updated. To reduce the test data volume and test application time, the problem addressed here is minimizing the number of conflicting bits by optimally reordering test vectors. Each vector represents a city, and the number of conflicting bits between two test vectors is regarded as the distance between them. Thus, the problem corresponds to the travelling salesman problem (TSP), which is NP-complete. The genetic algorithm is used to solve this problem. The experimental results show that the proposed scheme could reduce the test data volume efficiently without any additional hardware cost.
The accuracy and poor real-time performance of moving objects in a dynamic range complex environment become the bottleneck problem of the target location and tracking. In order to improve the positioning accuracy and the quality of tracking service, we propose an embedded tracking algorithm based on multi-feature fusion and visual object compression. On the hand, according to the feature of the target, the optimal feature matching method is selected, and the multi-feature crowd fusion location model is proposed. On the other hand, to reduce the dimension of the multidimensional space composed of the moving object visual frame and the compression of the visual object, the embedded tracking algorithm is established. Experimental results show that the proposed tracking algorithm has high precision, low energy consumption, and low delay.
In recent years, the use of multiprocessor systems has become increasingly common. Even in the embedded domain, the development of platforms based on multiprocessor systems or the porting of legacy single-core applications are frequent needs. However, such designs are often complicated, as embedded systems are characterized by numerous non-functional requirements and a tight hardware/software integration. This work proposes a methodology for the development and validation of an embedded multiprocessor system. Specifically, the proposed method assumes the use of a portable, open source API to support the parallelization and the possibility of prototyping the system on a field-programmable gate array. On this basis, the proposed flow allows an early exploration of the hardware configuration space, a preliminary estimate of performance, and the rapid development of a system able to satisfy the design specifications. An accurate assessment of the actual performance of the system is then enforced by the use of an hardware-based profiling subsystem. The proposed design flow is described, and a version specifically designed for LEON3 processor is presented and validated. The application of the proposed methodology in a real case of industrial study is then presented and analyzed.
We proposed a crowd cloud routing protocol based on opportunistic computing to improve the data transmission efficiency, reliability, and reduce routing overhead in wireless sensor networks. Based on the analysis of the demand of big data processing in wireless sensor network, the data analysis and processing platform for wireless sensor network are designed based on the combination with the cloud computing. The cloud platform includes the main nodes, the nodes, and the core nodes. There are the engine and the drive between the wireless sensor network and the cloud server. Secondly, aiming at the problem of data transmission in the cloud platform, we design an opportunistic computing model which is suitable for wireless sensor networks to minimize the weight of routing management and network overhead. Then, we design an opportunistic calculation model to guarantee the data transmission scheme of the cloud platform. Finally, by eliminating the factors that may cause the link instability, the crowd cloud routing protocol is proposed. The experimental results show that the proposed crowd cloud routing protocol has the functions of real-time and reliability and reduces the cost of routing request.
State-based schedules use a time division multiple access (TDMA) mechanism that supports executing conditional semantics and making on-the-fly decisions at runtime in each communication cycle. Until now, state-based schedules are unable to tolerate transient faults due to the assumption that stations make the on-the-fly decision on which message to execute next. Stations may make a faulty decision at run time in an unreliable communication environment such as wireless medium due to the presence of transient faults. This faulty decision causes state inconsistency among the stations in the system. In this work, we extend state-based schedules to tolerate faulty decisions in environments where transient faults can occur at the communication layer. Our proposed approach generates fault-tolerant state-based schedules using an integer linear programming optimization model after reducing the possibility of state inconsistency through using a clock and a sampling rate synchronization mechanism. The optimization model maximizes the use of time slots to place checkpoints for fault tolerance and resolving state inconsistency.
In order to improve the bandwidth utilization of embedded system and the working efficiency of mobile system, we propose a crowd Petri network and bandwidth allocation scheme. These research results are suitable for mobile embedded system. On the one hand, we have established a mobile crowd network system based on crowd Petri net. The system can give full play to the advantages of the concurrent and distributed data, so as to provide the formal description of the data control behavior of the mobile system and the asynchronous concurrent protection of the mobile service. On the other hand, through the opportunistic bandwidth allocation, the system efficiency and the network resources of the crowd Petri network is the most appropriate configuration. In the process of optimizing the crowd data, an embedded control protocol is studied based on the combination of the user demand and the data element characteristics by the combination of the service quality and the resource consumption. Simulation results show the effectiveness and feasibility of the embedded protocol based on bandwidth allocation of crowd Petri network.
While mining topics in a document collection, in order to capture the relationships between words and further improve the effectiveness of discovered topics, this paper proposed a feedback recurrent neural network-based topic model. We represented each word as a one-hot vector and embedded each document into a low-dimensional vector space. During the process of document embedding, we applied the long short-term memory method to capture the backward relationships between words and proposed a feedback recurrent neural network to capture the forward relationships between words. In the topic model, we used the original and muted document pairs as positive samples and the original and random document pairs as negative samples to train the model. The experiments show that the proposed model consumes not only lower running time and memory but also has better effectiveness during topic analysis.
Optical principle embedded image analysis can effectively improve the accuracy of image recognition, but there is a problem of low efficiency and high computational complexity. In view of the above problems, we design an image fusion mechanism based on an optical embedded scheme. We have proposed the optical image space, which is a three-dimensional space coordinate system. Each sample point of the system represents a spot. Light points in the image are described using three quantities, which are light intensity, image concentration, and light. An embedded optical image analysis model is proposed. We use a mobile embedding scheme to map multiple points of light into the same optical surface. Optical crowd block structure was proposed for increasing image data in an optical image system. The structure can improve the continuity of the image regions in different coordinate systems. The mechanism of crowd fusion for mobile embedded images is proposed. The experimental results show that the proposed mechanism is superior in the aspects of image recognition accuracy and algorithm execution cost.
Smart grid, smart metering, electromobility, and the regulation of the power network are keywords of the transition in energy politics. In the future, the power grid will be smart. Based on different works, this article presents a data collection, analyzing, and monitoring software for a reference smart grid. We discuss two possible architectures for collecting data from energy analyzers and analyze their performance with respect to real-time monitoring, load peak analysis, and automated regulation of the power grid. In the first architecture, we analyze the latency, needed bandwidth, and scalability for collecting data over the Modbus TCP/IP protocol and in the second one over a RESTful web service. The analysis results show that the solution with Modbus is more scalable as the one with RESTful web service. However, the performance and scalability of both architectures are sufficient for our reference smart grid and use cases.
Rock acoustic emission is often used to study the evolution of brittle materials. The cause of rock internal damage can be monitored continuously and real-timely by sensing rock acoustic wave. However, the key problem is how to split the position and analyze the acoustic emission characteristics based on the acoustic tracking experiment. First, we collected the acoustic waves of rock evolution. Then, a linear relationship is established between the acoustic emission and the propagation process of rock. And we proposed a rock sound source crowd localization algorithm. The algorithm can accurately restore the internal deformation and failure process of the rock. Finally, we designed an acoustic emission characteristic analysis method based on the acoustic source and rock sound. Test results of the ten location algorithm show that the positioning error of the proposed algorithm is less than 0.005 m, which is obviously better than the least square method. The calculation of rock strength and splitting rate is consistent with the actual measurement by using the embedded acoustic emission characteristic analysis mechanism.
For complexity and efficiency of the multi-objective optimization, we proposed the mobile distance field-driven adaptive crowd optimization algorithm. In space, we modify the surface parameters based on the corresponding changes of the distance field to obtain the moving target’s moving track and moving surface. When the curve of the moving track is changed, the x axis and the y axis of the moving track are adjusted adaptively. In this paper, the moving process is divided into three processes: the target dynamic crowd control, the crowd model algorithm, and the predictive control of linear time domain based on the moving target prediction and crowd control algorithm. Then, the multi-objective optimization algorithm of moving objects is proposed by using the crowd model to predict the status and the position of the target. The experimental results show the high accuracy, low complexity, and high efficiency of the proposed optimization algorithm.
Optimizing energy consumption in modern mobile handheld devices plays a very important role as lowering energy consumption impacts battery life and system reliability. With next-generation smartphones and tablets, the number of sensors and communication tools will increase and more and more communication interfaces and protocols such as Wi-Fi, Bluetooth, GPRS, UMTS, and LTE will be incorporated. Consequently, the fraction of energy consumed by these components will be larger. Nevertheless, the use of the large amount of data from the different sensors can be beneficial to detect the changing user context, to understand habits, and to detect running application needs. All these information, when used properly, may lead to an efficient energy consumption control. This paper proposes a tool to analyze user/application interaction to understand how the different hardware components are used at run-time and optimize them. The idea here is to use machine learning methods to identify and classify user behaviors and habit information. Using this tool, a software has been developed to control at run-time system component activities that have high impacts on the energy consumption. The tool allows also to predict future applications usages. By this way, screen brightness, CPU frequency, Wi-Fi connectivity, and playback sound level can be optimized while meeting the applications and the user requirements. Our experimental results show that the proposed solution can lower the energy consumption by up to 30 % versus the out-of-the-box power governor, while maintaining a negligible system overhead.
As the adoption of sensing and control networks rises to encompass the most diverse fields, the need for simple, efficient interconnection between many different devices will become ever more pressing. Though wireless communication is certainly appealing, current technological limits still prevent its usage where high reliability is needed or where the electromagnetical environment is not really apt to let radio waves through. In these cases, a wired link, based on a robust and well-consolidated standard such as an RS-485 bus, might prove to be a good choice. In this paper, we present an extension to the routing strategy originally implemented in the recently proposed "tree or linear hopping network" (ToLHnet) protocol, aimed at better handling the special but important case of linear routing over a (possibly very long) wired link, such as an RS-485 bus. The ToLHnet protocol was especially developed to suit the need of low complexity for deployments on large control networks. Indeed, using it over RS-485 already makes it possible to overcome many of the traditional limitations regarding cable length, without requiring segmenting the bus to install repeaters. With the extension here proposed, it will also be possible to simultaneously reduce latency (i.e., increase throughput, should it matter) for short-distance communications over the same cable, largely increasing the overall network efficiency, with a negligible increase in the complexity of the nodes' firmware.
In order to improve the efficiency of mechanical and hydraulic control of the mechanical equipment, the analysis scheme of mechanical hydraulic characteristics based on lightweight crowd data was proposed in mobile embedded devices. Based on the mobile and embedded machinery equipment, a crowd lightweight data-driven analysis model is proposed to solve the hydraulic mechanical properties of nonlinear filtering with coarse-grained service detection. The engine of the mechanical equipment was connected with the hydraulic control module through the harmonic filter. Based on the output array of hydraulic characteristics and the transmission power of the mobile embedded node, the analysis scheme of mechanical hydraulic characteristics was proposed based on lightweight crowd data in mobile embedded devices. Based on the experiment evaluation result, the hydraulic analysis performance and mechanical equipment support ability of the proposed scheme is better than the static node scheme.
Internet simultaneous services of large-scale users will lead to server overload and information failure. Static content recommendation system cannot adapt to the dynamic similarity characteristics of users. So, how to perceive the high accuracy of recommendation scheme in dynamic environment becomes one of the key techniques in application of educational information and embedded application. We analyze the problem of low efficiency and high error of the recommendation technology based on the user’s requirement. And, we proposed the cooperative filtering recommendation system based on the dynamic similarity of different users. In order to improve the prediction accuracy of cooperative filtering algorithm, the user’s target content would be processed with crowd scheme. Then, the system is fused with the recommendation system. According to the weights of the fusion, the crowd recommended fusion scheme are proposed. The experimental results show that the fusion mechanism of cooperative embedded filtering and crowd content recommendation has obvious advantages in terms of content recommendation accuracy, reliability, and convergence speed.
It has become the hot research issue that solves the bottleneck of resource management in the development of Internet through virtualization. However, there are the challenges of mobility management, resource management, and network overhead management in the virtualization of the Internet. First, based on the mobile Internet network construction and management mode, the mobile Internet virtual model was proposed for managing the differences of the port communication between the mobile Internet protocol layer and protocol layer. Secondly, based on the network management cost control and the reconstruction of the Internet virtualization, we designed the network overhead crowd optimization space and management vector. The network overhead crowd management mechanism is proposed, which will transport the mobile virtualization Internet topology to point-to-point structure. Finally, the simulation results verified the advantages of the network overhead management mechanism of the virtual mobile Internet in terms of the cost and real time of the network overhead management.
