This paper describes the function,structure and working status of the data buffer unitDBU,one of the most important functional units on ITM-1.It also discusses DBU’s supportto the multiprocessor system and Prolog lan...This paper describes the function,structure and working status of the data buffer unitDBU,one of the most important functional units on ITM-1.It also discusses DBU’s supportto the multiprocessor system and Prolog language.展开更多
In opportunistic networks, most existing buffer management policies including scheduling and passive dropping policies are mainly for routing protocols. In this paper, we proposed a Utility-based Buffer Management str...In opportunistic networks, most existing buffer management policies including scheduling and passive dropping policies are mainly for routing protocols. In this paper, we proposed a Utility-based Buffer Management strategy(UBM) for data dissemination in opportunistic networks. In UBM, we first design a method of computing the utility values of caching messages according to the interest of nodes and the delivery probability of messages, and then propose an overall buffer management policy based on the utility. UBM driven by receivers completely implements not only caching policies, passive and proactive dropping policies, but also scheduling policies of senders. Simulation results show that, compared with some classical dropping strategies, UBM can obtain higher delivery ratio and lower delay latency by using smaller network cost.展开更多
针对现阶段用电设备状态监测技术存在的处理速度较慢、准确率较低等问题,文中基于多突变点检测和模板匹配策略提出了一种用电设备在线状态监测方法。该方法在缓冲区模型和滑动窗口模型的基础上,利用多路搜索树突变点检测(Ternary Search...针对现阶段用电设备状态监测技术存在的处理速度较慢、准确率较低等问题,文中基于多突变点检测和模板匹配策略提出了一种用电设备在线状态监测方法。该方法在缓冲区模型和滑动窗口模型的基础上,利用多路搜索树突变点检测(Ternary Search Tree and Kolmogorov-Smirnov,TSTKS)算法形成窗口维度和缓冲区维度的特征向量,通过两种维度的模板匹配实现用电设备的运行状态匹配和状态切换时刻定位。基于家用电冰箱的仿真实验结果表明,所提方法具有检测速度快、准确率高等优点,可为用电设备状态监测领域提供参考。展开更多
传统离线数据分析方法对于处理即时性高和流量大的数据存在缺陷,而在线检测模型可以满足数据流分析的实时性要求。文中提出了一种基于多阈值模板的在线检测方法。该方法结合多路搜索树突变点检测(Ternary Search Tree and Kolmogorov-Sm...传统离线数据分析方法对于处理即时性高和流量大的数据存在缺陷,而在线检测模型可以满足数据流分析的实时性要求。文中提出了一种基于多阈值模板的在线检测方法。该方法结合多路搜索树突变点检测(Ternary Search Tree and Kolmogorov-Smirnov,TSTKS)算法进行在线检测,基于突变点密度更新窗口长度从而提高了突变点检测精度。采用等量分级策略实现对时序数据的自学习、匹配和分类,进而对大规模病变数据进行状态检测和预测。仿真实验和病变数据的实验结果表明,所提方法具有效果高、分类准确等优点,为大规模时序数据进行快速分类研究提供了新方法。展开更多
A data acquisition system （DAS） to implement high-speed, real-time and multi-channel data acquisition and store is presented. The control of the system is implemented by the combination of complex programable logic ...A data acquisition system （DAS） to implement high-speed, real-time and multi-channel data acquisition and store is presented. The control of the system is implemented by the combination of complex programable logic device （CPLD） and digital signal processing （DSP）, the bulk buffer of the system is implemented by the combination of CPLD, DSP, and synchronous dynamic random access memory （SDRAM）, and the data transfer is implemented by the combination of DSP, first in first out （FIFO）, universal serial bus （USB） and USB hub. The system could not only work independently in single-channel mode, but also implement high-speed real-time multi-channel data acquisition system （MCDAS） by the combination of multiple single-channels. The sampling rate and data storage capacity of each channel could reach up to 100 million sampiing per second and 256 MB respectively.展开更多
The Wireless Sensor network is distributed event based systems that differ from conventional communica-tion network. Sensor network has severe energy constraints, redundant low data rate, and many-to-one flows. Aggreg...The Wireless Sensor network is distributed event based systems that differ from conventional communica-tion network. Sensor network has severe energy constraints, redundant low data rate, and many-to-one flows. Aggregation is a technique to avoid redundant information to save energy and other resources. There are two types of aggregations. In one of the aggregation many sensor data are embedded into single packet, thus avoiding the unnecessary packet headers, this is called lossless aggregation. In the second case the sensor data goes under statistical process (average, maximum, minimum) and results are communicated to the base station, this is called lossy aggregation, because we cannot recover the original sensor data from the received aggregated packet. The number of sensor data to be aggregated in a single packet is known as degree of ag-gregation. The main contribution of this paper is to propose an algorithm which is adaptive to choose one of the aggregations based on scenarios and degree of aggregation based on traffic. We are also suggesting a suitable buffer management to offer best Quality of Service. Our initial experiment with NS-2 implementa-tion shows significant energy savings by reducing the number of packets optimally at any given moment of time.展开更多
基金the High Technology Research and Development Programme of china.
文摘This paper describes the function,structure and working status of the data buffer unitDBU,one of the most important functional units on ITM-1.It also discusses DBU’s supportto the multiprocessor system and Prolog language.
基金supported by the National Natural Science Fund of China under Grant No. 61472097the Education Ministry Doctoral Research Foundation of China (20132304110017)the International Exchange Program of Harbin Engineering University for Innovation-oriented Talents Cultivation
文摘In opportunistic networks, most existing buffer management policies including scheduling and passive dropping policies are mainly for routing protocols. In this paper, we proposed a Utility-based Buffer Management strategy(UBM) for data dissemination in opportunistic networks. In UBM, we first design a method of computing the utility values of caching messages according to the interest of nodes and the delivery probability of messages, and then propose an overall buffer management policy based on the utility. UBM driven by receivers completely implements not only caching policies, passive and proactive dropping policies, but also scheduling policies of senders. Simulation results show that, compared with some classical dropping strategies, UBM can obtain higher delivery ratio and lower delay latency by using smaller network cost.
文摘针对现阶段用电设备状态监测技术存在的处理速度较慢、准确率较低等问题,文中基于多突变点检测和模板匹配策略提出了一种用电设备在线状态监测方法。该方法在缓冲区模型和滑动窗口模型的基础上,利用多路搜索树突变点检测(Ternary Search Tree and Kolmogorov-Smirnov,TSTKS)算法形成窗口维度和缓冲区维度的特征向量,通过两种维度的模板匹配实现用电设备的运行状态匹配和状态切换时刻定位。基于家用电冰箱的仿真实验结果表明,所提方法具有检测速度快、准确率高等优点,可为用电设备状态监测领域提供参考。
文摘传统离线数据分析方法对于处理即时性高和流量大的数据存在缺陷,而在线检测模型可以满足数据流分析的实时性要求。文中提出了一种基于多阈值模板的在线检测方法。该方法结合多路搜索树突变点检测(Ternary Search Tree and Kolmogorov-Smirnov,TSTKS)算法进行在线检测,基于突变点密度更新窗口长度从而提高了突变点检测精度。采用等量分级策略实现对时序数据的自学习、匹配和分类,进而对大规模病变数据进行状态检测和预测。仿真实验和病变数据的实验结果表明,所提方法具有效果高、分类准确等优点,为大规模时序数据进行快速分类研究提供了新方法。
文摘A data acquisition system （DAS） to implement high-speed, real-time and multi-channel data acquisition and store is presented. The control of the system is implemented by the combination of complex programable logic device （CPLD） and digital signal processing （DSP）, the bulk buffer of the system is implemented by the combination of CPLD, DSP, and synchronous dynamic random access memory （SDRAM）, and the data transfer is implemented by the combination of DSP, first in first out （FIFO）, universal serial bus （USB） and USB hub. The system could not only work independently in single-channel mode, but also implement high-speed real-time multi-channel data acquisition system （MCDAS） by the combination of multiple single-channels. The sampling rate and data storage capacity of each channel could reach up to 100 million sampiing per second and 256 MB respectively.
文摘The Wireless Sensor network is distributed event based systems that differ from conventional communica-tion network. Sensor network has severe energy constraints, redundant low data rate, and many-to-one flows. Aggregation is a technique to avoid redundant information to save energy and other resources. There are two types of aggregations. In one of the aggregation many sensor data are embedded into single packet, thus avoiding the unnecessary packet headers, this is called lossless aggregation. In the second case the sensor data goes under statistical process (average, maximum, minimum) and results are communicated to the base station, this is called lossy aggregation, because we cannot recover the original sensor data from the received aggregated packet. The number of sensor data to be aggregated in a single packet is known as degree of ag-gregation. The main contribution of this paper is to propose an algorithm which is adaptive to choose one of the aggregations based on scenarios and degree of aggregation based on traffic. We are also suggesting a suitable buffer management to offer best Quality of Service. Our initial experiment with NS-2 implementa-tion shows significant energy savings by reducing the number of packets optimally at any given moment of time.
