Waveguide invariant is widely used in underwater target passive ranging. In shallow water with uniform sound speed profile, the value of waveguide invariant is approximately a constant, while in shallow water with the...Waveguide invariant is widely used in underwater target passive ranging. In shallow water with uniform sound speed profile, the value of waveguide invariant is approximately a constant, while in shallow water with thermocline, it varies in a wide range. The waveguide invariant distributions and striations in these two conditions are analyzed respectively. On the basis of wavenumber difference between reflected modes and refracted modes, a wavenumber-frequency domain filtering technique is proposed to separate the two groups of modes. The required relationship between array element space, total array length and target azimuth for effective application is discussed. Finally, the simulation results indicate that in shallow water with a thermocline, refracted modes can be effectively filtered out using the wavenumber-frequency domain filtering technique and the target's range is estimated accurately. ? 2017 Beijing Institute of Aerospace Information.展开更多
A high-performance predictor for critical unstable generators(CUGs) of power systems is presented in this paper. The predictor is driven by the Map Reduce based parallelized neural networks. Specifically, a group of b...A high-performance predictor for critical unstable generators(CUGs) of power systems is presented in this paper. The predictor is driven by the Map Reduce based parallelized neural networks. Specifically, a group of back propagation neural networks(BPNNs), fed by massive response trajectories data, are efficiently organized and concurrently trained in Hadoop to identify dynamic behavior of individual generator. Rather than simply classifying global stability of power systems, the presented approach is able to distinguish unstable generators accurately with a few cycles of synchronized trajectories after fault clearing,enabling more in-depth emergency awareness based on wide-area implementation. In addition, the technique is of rich scalability due to Hadoop framework, which can be deployed in the control centers as a high-performance computing infrastructure for real-time instability alert.Numerical examples are studied using NPCC 48-machines test system and a realistic power system of China.展开更多
In order to currently motivate a wide range of various interactions between power network operators and electricity customers,residential load forecasting plays an increasingly important role in demand side response(D...In order to currently motivate a wide range of various interactions between power network operators and electricity customers,residential load forecasting plays an increasingly important role in demand side response(DSR).Due to high volatility and uncertainty of residential load,it is significantly challenging to forecast it precisely.Thus,this paper presents a short-term individual residential load forecasting method based on a combination of deep learning and k-means clustering,which is capable of effectively extracting the similarity of residential load and performing residential load forecasting accurately at the individual level.It first makes full use of k-means clustering to extract similarity among residential load and then employs deep learning to extract complicated patterns of residential load.The presented method is tested and validated on a real-life Irish residential load dataset,and the experimental results suggest that it can achieve a much higher prediction accuracy,in comparison with a published benchmark method.展开更多
基金supported by the National Natural Science Foundation of China(1137407261371171)
文摘Waveguide invariant is widely used in underwater target passive ranging. In shallow water with uniform sound speed profile, the value of waveguide invariant is approximately a constant, while in shallow water with thermocline, it varies in a wide range. The waveguide invariant distributions and striations in these two conditions are analyzed respectively. On the basis of wavenumber difference between reflected modes and refracted modes, a wavenumber-frequency domain filtering technique is proposed to separate the two groups of modes. The required relationship between array element space, total array length and target azimuth for effective application is discussed. Finally, the simulation results indicate that in shallow water with a thermocline, refracted modes can be effectively filtered out using the wavenumber-frequency domain filtering technique and the target's range is estimated accurately. ? 2017 Beijing Institute of Aerospace Information.
文摘A high-performance predictor for critical unstable generators(CUGs) of power systems is presented in this paper. The predictor is driven by the Map Reduce based parallelized neural networks. Specifically, a group of back propagation neural networks(BPNNs), fed by massive response trajectories data, are efficiently organized and concurrently trained in Hadoop to identify dynamic behavior of individual generator. Rather than simply classifying global stability of power systems, the presented approach is able to distinguish unstable generators accurately with a few cycles of synchronized trajectories after fault clearing,enabling more in-depth emergency awareness based on wide-area implementation. In addition, the technique is of rich scalability due to Hadoop framework, which can be deployed in the control centers as a high-performance computing infrastructure for real-time instability alert.Numerical examples are studied using NPCC 48-machines test system and a realistic power system of China.
基金supported by the Science and Technology Program of State Grid Corporation of China(Data Mining Technology of Potential High-Value Industrial Users for Data Operations,No.5700-202055267A-0-0-00)。
文摘In order to currently motivate a wide range of various interactions between power network operators and electricity customers,residential load forecasting plays an increasingly important role in demand side response(DSR).Due to high volatility and uncertainty of residential load,it is significantly challenging to forecast it precisely.Thus,this paper presents a short-term individual residential load forecasting method based on a combination of deep learning and k-means clustering,which is capable of effectively extracting the similarity of residential load and performing residential load forecasting accurately at the individual level.It first makes full use of k-means clustering to extract similarity among residential load and then employs deep learning to extract complicated patterns of residential load.The presented method is tested and validated on a real-life Irish residential load dataset,and the experimental results suggest that it can achieve a much higher prediction accuracy,in comparison with a published benchmark method.
