In the Ethernet lossless Data Center Networks (DCNs) deployedwith Priority-based Flow Control (PFC), the head-of-line blocking problemis still difficult to prevent due to PFC triggering under burst trafficscenarios ev...In the Ethernet lossless Data Center Networks (DCNs) deployedwith Priority-based Flow Control (PFC), the head-of-line blocking problemis still difficult to prevent due to PFC triggering under burst trafficscenarios even with the existing congestion control solutions. To addressthe head-of-line blocking problem of PFC, we propose a new congestioncontrol mechanism. The key point of Congestion Control Using In-NetworkTelemetry for Lossless Datacenters (ICC) is to use In-Network Telemetry(INT) technology to obtain comprehensive congestion information, which isthen fed back to the sender to adjust the sending rate timely and accurately.It is possible to control congestion in time, converge to the target rate quickly,and maintain a near-zero queue length at the switch when using ICC. Weconducted Network Simulator-3 (NS-3) simulation experiments to test theICC’s performance. When compared to Congestion Control for Large-ScaleRDMA Deployments (DCQCN), TIMELY: RTT-based Congestion Controlfor the Datacenter (TIMELY), and Re-architecting Congestion Managementin Lossless Ethernet (PCN), ICC effectively reduces PFC pause messages andFlow Completion Time (FCT) by 47%, 56%, 34%, and 15.3×, 14.8×, and11.2×, respectively.展开更多
A comparison study is performed to contrast the improvements in the tropical Pacific oceanic state of a low-resolution model respectively via data assimilation and by an increase in horizontal resolution. A low resolu...A comparison study is performed to contrast the improvements in the tropical Pacific oceanic state of a low-resolution model respectively via data assimilation and by an increase in horizontal resolution. A low resolution model (LR) (1°lat by 2°lon) and a high-resolution model (HR) (0.5°lat by 0.5°lon) are employed for the comparison. The authors perform 20-yr numerical experiments and analyze the annual mean fields of temperature and salinity. The results indicate that the low-resolution model with data assimilation behaves better than the high-resolution model in the estimation of ocean large-scale features. From 1990 to 2000, the average of HR's RMSE (root-mean-square error) relative to independent Tropical Atmosphere Ocean project (TAO) mooring data at randomly selected points is 0.97℃ compared to a RMSE of 0.56℃ for LR with temperature assimilation. Moreover, the LR with data assimilation is more frugal in computation. Although there is room to improve the high-resolution model, the low-resolution model with data assimilation may be an advisable choice in achieving a more realistic large-scale state of the ocean at the limited level of information provided by the current observational system.展开更多
网络遥测是一种新型的网络测量技术,具有实时性强、准确性高、开销低的特点。现有网络遥测技术存在无法收集多粒度网络数据、无法有效存储大量原始网络数据、无法快速提取及生成网络遥测信息、无法利用内核态及用户态特性设计网络遥测...网络遥测是一种新型的网络测量技术,具有实时性强、准确性高、开销低的特点。现有网络遥测技术存在无法收集多粒度网络数据、无法有效存储大量原始网络数据、无法快速提取及生成网络遥测信息、无法利用内核态及用户态特性设计网络遥测方案等问题。为此,提出了一种融合内核态及用户态的、基于遥测数据图和同步控制块的多粒度、可扩展、覆盖全网的网络遥测机制(a nEtwork telemetry mechAnism based on telemetry data Graph in kerneL and usEr mode,EAGLE)。EAGLE设计了一种能够收集多粒度数据且数据平面上灵活可控的网络遥测数据包结构,用于获取上层应用所需的数据。此外,为快速存储、查询、统计、聚合网络状态数据,实现网络遥测数据包所需遥测数据的快速提取与生成,EAGLE提出了一种基于遥测数据图及同步控制块的网络遥测信息生成方法。在此基础上,为了最大化网络遥测机制中网络遥测数据包的处理效率,EAGLE提出了融合内核态及用户态特性的网络遥测信息嵌入架构。在Open vSwitch上实现了EAGLE方案并进行了测试,测试结果表明,EAGLE能够收集多粒度数据并快速提取与生成遥测数据,且仅增加极少量的处理时延及资源占用率。展开更多
针对传统卫星温度预测方法在预测精度和鲁棒性方面表现不佳,难以满足高维度耦合数据预测需求的问题,提出一种针对卫星温度遥测数据的多元时序数据预测模型——改进的时间序列处理模块(advanced time series processing module,ATSPM)-Ne...针对传统卫星温度预测方法在预测精度和鲁棒性方面表现不佳,难以满足高维度耦合数据预测需求的问题,提出一种针对卫星温度遥测数据的多元时序数据预测模型——改进的时间序列处理模块(advanced time series processing module,ATSPM)-Net。首先,构建了包含一维卷积和门控循环单元(gated recurrent unit,GRU)的ATSPM,以对高度耦合的遥测数据中的时间依赖关系进行多尺度提取。接着,设计了多元时序数据预测模型ATSPM-Net。通过堆叠ATSPM,ATSPM-Net确保模型的灵活感受野,从而实现高准确率和鲁棒性的遥测数据预测。最后,在5个数据集上进行的数值实验结果表明,相较于其他类型的时序数据预测模型,ATSPM-Net在参数量较少的情况下能展现出更优异的温度预测性能。展开更多
为了提高太阳电池阵多变量预测的精度,解决阳电池阵遥测参数存在周期波动与增长性互相耦合的问题,提出一种基于STL-Prophet-Informer模型的太阳电池阵多变量预测算法.该算法首先应用局部加权周期趋势分解算法(seasonal and trend decomp...为了提高太阳电池阵多变量预测的精度,解决阳电池阵遥测参数存在周期波动与增长性互相耦合的问题,提出一种基于STL-Prophet-Informer模型的太阳电池阵多变量预测算法.该算法首先应用局部加权周期趋势分解算法(seasonal and trend decomposition procedure based on loess,STL)对太阳电池阵的多个参数分解为趋势分量、周期分量和残差分量,然后采用对趋势性数据预测效果较好的Prophet预测趋势分量,Informer模型预测周期分量和残差分量,最后将各分量预测结果相加后得到总的太阳电池阵参数预测值.以某卫星太阳电池阵实际遥测数据做算例分析,提出算法的各项误差评价指标和单一的Informer模型、LSTM模型等相比有明显减小,将该组合预测模型用于太阳电池阵多变量参数预测中,可以提高参数预测精度,提升卫星自主运行性能.展开更多
针对海量变电站遥测数据堆积,导致数据修正误差较大的问题,设计基于结构化数据传送(Structured Data Transfer,SDT)的智慧变电站站端遥测数据修正系统。通过遥测数据前端处理模块并行处理转换数据。利用遥测数据判读模块,结合专家测试...针对海量变电站遥测数据堆积,导致数据修正误差较大的问题,设计基于结构化数据传送(Structured Data Transfer,SDT)的智慧变电站站端遥测数据修正系统。通过遥测数据前端处理模块并行处理转换数据。利用遥测数据判读模块,结合专家测试库知识判读反馈数据。根据实际数据中显著数据污染率,确定待修正遥测数据。结合异常数据决策规则,应用基于SDT数据修正技术压缩海量遥测数据,避免待修正遥测数据大量堆积。设定SDT数据压缩强制记录限度,将最大误差序列作为系统输入量,构建修正函数,获取站端遥测数据修正结果。测试结果表明,该系统修正的视在功率数据和电流与理想数据存在最大为0.2 MVA和8 A的误差,能够为智慧变电站稳定运行提供可靠数据。展开更多
The research of coupling WRF （Weather Research and Forecasting Model） with a land surface model is enhanced to explore the interaction of the atmosphere and land surface; however, regional applicability of WRF model...The research of coupling WRF （Weather Research and Forecasting Model） with a land surface model is enhanced to explore the interaction of the atmosphere and land surface; however, regional applicability of WRF model is questioned. In order to do the validation of WRF model on simulating forcing data for the Heihe River Basin, daily meteorological observation data from 15 stations of CMA （China Meteorological Administration） and hourly meteorological observation data from seven sites of WATER （Watershed Airborne Telemetry Experimental Research） are used to compare with WRF simulations, with a time range of a whole year for 2008. Results show that the average MBE （Mean Bias Error） of daily 2-m surface temperature, surface pressure, 2-m relative humidity and 10-m wind speed were -0.19 ℃, -4.49 hPa, 4.08% and 0.92 m/s, the average RMSE （Root Mean Square Error） of them were 2.11 ℃, 5.37 hPa, 9.55% and 1.73 m/s, and the average R （correlation coefficient） of them were 0.99, 0.98, 0.80 and 0.55, respectively. The average MBE of hourly 2-m surface temperature, surface pressure, 2-m relative humidity, 10-m wind speed, downward shortwave radiation and downward longwave were-0.16 ℃,-6.62 hPa,-5.14%, 0.26 m/s, 33.0 W/m^2 and-6.44 W/m^2, the average RMSE of them were 2.62 ℃, 17.10 hPa, 20.71%, 2.46 m/s, 152.9 W/m^2 and 53.5 W/m^2, and the average R of them were 0.96, 0.97, 0.70, 0.26, 0.91 and 0.60, respectively. Thus, the following conclusions were obtained： （1） regardless of daily or hourly validation, WRF model simulations of 2-m surface temperature, surface pressure and relative humidity are more reliable, especially for 2-m surface air temperature and surface pressure, the values of MBE were small and R were more than 0.96; （2） the WRF simulating downward shortwave radiation was relatively good, the average R between WRF simulation and hourly observation data was above 0.9, and the average R of downward longwave radiation was 0.6; （3） both wind speed and rainfall simulated from WRF model did not agree well with observation data.展开更多
Nowadays, we experience an abundance of Internet of Things middleware solutions that make the sensors and the actuators are able to connect to the Internet. These solutions, referred to as platforms to gain a widespre...Nowadays, we experience an abundance of Internet of Things middleware solutions that make the sensors and the actuators are able to connect to the Internet. These solutions, referred to as platforms to gain a widespread adoption, have to meet the expectations of different players in the IoT ecosystem, including devices [1]. Low cost devices are easily able to connect wirelessly to the Internet, from handhelds to coffee machines, also known as Internet of Things (IoT). This research describes the methodology and the development process of creating an IoT platform. This paper also presents the architecture and implementation for the IoT platform. The goal of this research is to develop an analytics engine which can gather sensor data from different devices and provide the ability to gain meaningful information from IoT data and act on it using machine learning algorithms. The proposed system is introducing the use of a messaging system to improve the overall system performance as well as provide easy scalability.展开更多
基金supported by the National Natural Science Foundation of China (No.62102046,62072249,62072056)JinWang,YongjunRen,and Jinbin Hu receive the grant,and the URLs to the sponsors’websites are https://www.nsfc.gov.cn/.This work is also funded by the National Science Foundation of Hunan Province (No.2022JJ30618,2020JJ2029).
文摘In the Ethernet lossless Data Center Networks (DCNs) deployedwith Priority-based Flow Control (PFC), the head-of-line blocking problemis still difficult to prevent due to PFC triggering under burst trafficscenarios even with the existing congestion control solutions. To addressthe head-of-line blocking problem of PFC, we propose a new congestioncontrol mechanism. The key point of Congestion Control Using In-NetworkTelemetry for Lossless Datacenters (ICC) is to use In-Network Telemetry(INT) technology to obtain comprehensive congestion information, which isthen fed back to the sender to adjust the sending rate timely and accurately.It is possible to control congestion in time, converge to the target rate quickly,and maintain a near-zero queue length at the switch when using ICC. Weconducted Network Simulator-3 (NS-3) simulation experiments to test theICC’s performance. When compared to Congestion Control for Large-ScaleRDMA Deployments (DCQCN), TIMELY: RTT-based Congestion Controlfor the Datacenter (TIMELY), and Re-architecting Congestion Managementin Lossless Ethernet (PCN), ICC effectively reduces PFC pause messages andFlow Completion Time (FCT) by 47%, 56%, 34%, and 15.3×, 14.8×, and11.2×, respectively.
基金This study is supported by the Key Program of Chinese Academy of Sciences KZCX3 SW-221the National Natural Science Foundation of China(Grant No.40233033 and 40221503).
文摘A comparison study is performed to contrast the improvements in the tropical Pacific oceanic state of a low-resolution model respectively via data assimilation and by an increase in horizontal resolution. A low resolution model (LR) (1°lat by 2°lon) and a high-resolution model (HR) (0.5°lat by 0.5°lon) are employed for the comparison. The authors perform 20-yr numerical experiments and analyze the annual mean fields of temperature and salinity. The results indicate that the low-resolution model with data assimilation behaves better than the high-resolution model in the estimation of ocean large-scale features. From 1990 to 2000, the average of HR's RMSE (root-mean-square error) relative to independent Tropical Atmosphere Ocean project (TAO) mooring data at randomly selected points is 0.97℃ compared to a RMSE of 0.56℃ for LR with temperature assimilation. Moreover, the LR with data assimilation is more frugal in computation. Although there is room to improve the high-resolution model, the low-resolution model with data assimilation may be an advisable choice in achieving a more realistic large-scale state of the ocean at the limited level of information provided by the current observational system.
文摘网络遥测是一种新型的网络测量技术,具有实时性强、准确性高、开销低的特点。现有网络遥测技术存在无法收集多粒度网络数据、无法有效存储大量原始网络数据、无法快速提取及生成网络遥测信息、无法利用内核态及用户态特性设计网络遥测方案等问题。为此,提出了一种融合内核态及用户态的、基于遥测数据图和同步控制块的多粒度、可扩展、覆盖全网的网络遥测机制(a nEtwork telemetry mechAnism based on telemetry data Graph in kerneL and usEr mode,EAGLE)。EAGLE设计了一种能够收集多粒度数据且数据平面上灵活可控的网络遥测数据包结构,用于获取上层应用所需的数据。此外,为快速存储、查询、统计、聚合网络状态数据,实现网络遥测数据包所需遥测数据的快速提取与生成,EAGLE提出了一种基于遥测数据图及同步控制块的网络遥测信息生成方法。在此基础上,为了最大化网络遥测机制中网络遥测数据包的处理效率,EAGLE提出了融合内核态及用户态特性的网络遥测信息嵌入架构。在Open vSwitch上实现了EAGLE方案并进行了测试,测试结果表明,EAGLE能够收集多粒度数据并快速提取与生成遥测数据,且仅增加极少量的处理时延及资源占用率。
文摘针对传统卫星温度预测方法在预测精度和鲁棒性方面表现不佳,难以满足高维度耦合数据预测需求的问题,提出一种针对卫星温度遥测数据的多元时序数据预测模型——改进的时间序列处理模块(advanced time series processing module,ATSPM)-Net。首先,构建了包含一维卷积和门控循环单元(gated recurrent unit,GRU)的ATSPM,以对高度耦合的遥测数据中的时间依赖关系进行多尺度提取。接着,设计了多元时序数据预测模型ATSPM-Net。通过堆叠ATSPM,ATSPM-Net确保模型的灵活感受野,从而实现高准确率和鲁棒性的遥测数据预测。最后,在5个数据集上进行的数值实验结果表明,相较于其他类型的时序数据预测模型,ATSPM-Net在参数量较少的情况下能展现出更优异的温度预测性能。
文摘为了提高太阳电池阵多变量预测的精度,解决阳电池阵遥测参数存在周期波动与增长性互相耦合的问题,提出一种基于STL-Prophet-Informer模型的太阳电池阵多变量预测算法.该算法首先应用局部加权周期趋势分解算法(seasonal and trend decomposition procedure based on loess,STL)对太阳电池阵的多个参数分解为趋势分量、周期分量和残差分量,然后采用对趋势性数据预测效果较好的Prophet预测趋势分量,Informer模型预测周期分量和残差分量,最后将各分量预测结果相加后得到总的太阳电池阵参数预测值.以某卫星太阳电池阵实际遥测数据做算例分析,提出算法的各项误差评价指标和单一的Informer模型、LSTM模型等相比有明显减小,将该组合预测模型用于太阳电池阵多变量参数预测中,可以提高参数预测精度,提升卫星自主运行性能.
文摘针对海量变电站遥测数据堆积,导致数据修正误差较大的问题,设计基于结构化数据传送(Structured Data Transfer,SDT)的智慧变电站站端遥测数据修正系统。通过遥测数据前端处理模块并行处理转换数据。利用遥测数据判读模块,结合专家测试库知识判读反馈数据。根据实际数据中显著数据污染率,确定待修正遥测数据。结合异常数据决策规则,应用基于SDT数据修正技术压缩海量遥测数据,避免待修正遥测数据大量堆积。设定SDT数据压缩强制记录限度,将最大误差序列作为系统输入量,构建修正函数,获取站端遥测数据修正结果。测试结果表明,该系统修正的视在功率数据和电流与理想数据存在最大为0.2 MVA和8 A的误差,能够为智慧变电站稳定运行提供可靠数据。
基金supported by grant from the National High Technology Research and Development Program (863) of China (Grant No.2009AA122104)grants from the National Natural Science Foundation of China (No.40901202, No.40925004)+1 种基金supported by the CAS Action Plan for West Development Program (Grant No.KZCX2-XB2-09)Chinese State Key Basic Research Project (Grant No.2007CB714400)
文摘The research of coupling WRF （Weather Research and Forecasting Model） with a land surface model is enhanced to explore the interaction of the atmosphere and land surface; however, regional applicability of WRF model is questioned. In order to do the validation of WRF model on simulating forcing data for the Heihe River Basin, daily meteorological observation data from 15 stations of CMA （China Meteorological Administration） and hourly meteorological observation data from seven sites of WATER （Watershed Airborne Telemetry Experimental Research） are used to compare with WRF simulations, with a time range of a whole year for 2008. Results show that the average MBE （Mean Bias Error） of daily 2-m surface temperature, surface pressure, 2-m relative humidity and 10-m wind speed were -0.19 ℃, -4.49 hPa, 4.08% and 0.92 m/s, the average RMSE （Root Mean Square Error） of them were 2.11 ℃, 5.37 hPa, 9.55% and 1.73 m/s, and the average R （correlation coefficient） of them were 0.99, 0.98, 0.80 and 0.55, respectively. The average MBE of hourly 2-m surface temperature, surface pressure, 2-m relative humidity, 10-m wind speed, downward shortwave radiation and downward longwave were-0.16 ℃,-6.62 hPa,-5.14%, 0.26 m/s, 33.0 W/m^2 and-6.44 W/m^2, the average RMSE of them were 2.62 ℃, 17.10 hPa, 20.71%, 2.46 m/s, 152.9 W/m^2 and 53.5 W/m^2, and the average R of them were 0.96, 0.97, 0.70, 0.26, 0.91 and 0.60, respectively. Thus, the following conclusions were obtained： （1） regardless of daily or hourly validation, WRF model simulations of 2-m surface temperature, surface pressure and relative humidity are more reliable, especially for 2-m surface air temperature and surface pressure, the values of MBE were small and R were more than 0.96; （2） the WRF simulating downward shortwave radiation was relatively good, the average R between WRF simulation and hourly observation data was above 0.9, and the average R of downward longwave radiation was 0.6; （3） both wind speed and rainfall simulated from WRF model did not agree well with observation data.
文摘Nowadays, we experience an abundance of Internet of Things middleware solutions that make the sensors and the actuators are able to connect to the Internet. These solutions, referred to as platforms to gain a widespread adoption, have to meet the expectations of different players in the IoT ecosystem, including devices [1]. Low cost devices are easily able to connect wirelessly to the Internet, from handhelds to coffee machines, also known as Internet of Things (IoT). This research describes the methodology and the development process of creating an IoT platform. This paper also presents the architecture and implementation for the IoT platform. The goal of this research is to develop an analytics engine which can gather sensor data from different devices and provide the ability to gain meaningful information from IoT data and act on it using machine learning algorithms. The proposed system is introducing the use of a messaging system to improve the overall system performance as well as provide easy scalability.
