In this work, we propose a combinative strategy based on regression and clustering for solving point set matching problems under a Bayesian framework, in which the regression estimates the transformation from the model to the scene- and the clustering establishes the correspondence between two point sets. The point set matching model is illustrated by a hierarchical directed graph, and the matching uncertainties are approximated by a coarse-to-fine variational inference algorithm. Furthermore, two Gaussian mixtures are proposed for the estimation of heteroscedastic noise and spurious outliers, and an isotropic or anisotropic covariance can be imposed on each mixture in terms of the transformed model points. The experimental results show that the proposed approach achieves comparable performance to state-of-the-art matching or registration algorithms in terms of both robustness and accuracy.
The high penetration of renewable energy increases the difficulty of optimal dispatch and brings challenges to the safe and economic operation of the distribution network. This paper proposed an active and reactive power coordinated optimal dispatch model, and the spatial-temporal correlation of wind power output is considered. Firstly, the copula function and non-parametric estimation methods are adopted to model the spatial-temporal correlation of wind power. Secondly, the parameters in the copula fitting function are estimated based on the maximum likelihood estimation method. Besides, the active power and reactive power outputs of various flexible resources in the active distribution network (ADN) are coordinated. The proposed model can significantly reduce the network loss of the ADN, improve efficiency, and optimize the power purchase plan. A case study on a modified IEEE 33-bus system verified the effectiveness of the proposed method.
Burglary is a violent criminal act that infringes on the property of others. In order to better understand the criminal model and make full use of law enforcement resources, this paper uses the space-time analysis technology to study the spatial distribution, spatial dependence and the rules of burglary cases in the main urban area of a city in 2016. The LGCP (Log-Gaussian Cox Process) model combines with the Bayesian framework to establish a continuous spatial random fields. The model is calculated using INLA(Integrated Nested Laplace Approximation) and SPDE(Stochastic Partial Differential Equations). Studies have shown that burglary cases have different trend values at different time points and different spatial locations, and have strong correlations in adjacent time periods and spatial random fields. The intensity of burglary and the spatial distribution of retail points and cultural education are linear relationship, and there is a complex nonlinear relationship with the spatial trend of sports and leisure points, but it presents a positive correlation in the whole, the more concentrated the sports and leisure, cultural education and wholesale and retail are, the higher the risk of burglary.
Based on the boundary characteristic and frequency characteristic of cable, a protection method for VSC-HVDC cable is proposed in this paper, which only uses the single-end transient current signal. First, the frequency components of the currents at the DC-side and AC-side of the DC boundary are extracted by means of S transform, and the magnitude of the high frequency components of DC-side current is employed to detect the fault. Then, the ratio of the magnitude of the high frequency components of the DC- and AC-side currents is calculated to identify the internal fault from the close-up external fault. Finally, the ratio of the high and low frequency components of the DC-side current is calculated to identify the internal fault from the opposite external fault. This protection method is verified on basis of a two-terminal VSC-HVDC model with EMTDC/PSCAD. Various types of faults are simulated, and the simulation results show that this method can identify the internal faults under different conditions rapidly, while can ignore the external faults reliably.