This paper proposes an incremental smooth support vector regression (ISSVR) method for TS fuzzy modeling. Under certain assumptions on membership functions, we propose an optimization problem for TS fuzzy modeling bas...
This paper proposes an incremental smooth support vector regression (ISSVR) method for TS fuzzy modeling. Under certain assumptions on membership functions, we propose an optimization problem for TS fuzzy modeling based on the structural risk minimization principle. We show that this problem is an SVR problem with non-positive definite kernels. It cannot be solved using conventional SVR. Then we establish a connection between this TS fuzzy modeling problem and smooth support vector regression (SSVR), which is a smoothing strategy for solving SVR. The problem is always solvable using SSVR because SSVR puts no restrictions on the kernel. Then we apply an incremental approach to the SSVR by selecting informative samples from the training dataset. Taking advantage of SSVR, more forms of membership functions can be used in our model compared with conventional methods. Experiments show that the proposed ISSVR-based TS fuzzy model has good generalization ability with small number of fuzzy rules.
Residential demand response is of greater importance in the smart grid. While under the condition of dynamic energy price and uncertain energy request from the consumers, it is a particular problem to explicitly model...
详细信息
Residential demand response is of greater importance in the smart grid. While under the condition of dynamic energy price and uncertain energy request from the consumers, it is a particular problem to explicitly model this uncertainty and schedule the devices. In this paper we use markov model to depict this uncertainty, and formulate an optimization problem to minimize the average total cost in an infinite horizon. Because it's hard to get the transition probability information about the energy price and energy request, we derive a parameterized online learning algorithm to determine the power allocation of deferable electricity appliance and control the storage. A numerical example show that this algorithm is effective and can significantly reduce the long term cost.
In this paper, a multi-level model-based control strategy is applied to control large scale urban traffic networks. Structure of the strategy contains two levels, i.e., a coordinator in the upper level and model predi...
详细信息
In this paper, a multi-level model-based control strategy is applied to control large scale urban traffic networks. Structure of the strategy contains two levels, i.e., a coordinator in the upper level and model predictive controllers in the lower level. The coordinator aims to keep the distribution of vehicles in the network homogeneous, and the two-level structure makes the computational burden acceptable. The simulation shows the performance of multilevel model-based control is close to that of centralized model predictive control and better than decentralized control. Meanwhile, the computational complexity is greatly reduced comparing with centralized control.
In this paper a multi-period planning and scheduling problem under demand correlations is addressed. A stochastic optimization model using restricted time structure is formulated. This model involves the minimization ...
详细信息
In this paper a multi-period planning and scheduling problem under demand correlations is addressed. A stochastic optimization model using restricted time structure is formulated. This model involves the minimization of the operation cost subject to constraints for the satisfaction of crude mix demands with a prespecified level of probability. A chance constrained programming that converts the stochastic programming to a deterministic one is developed for solving the problem. The deterministic problem is then solved by a proposed approximation algorithm iteratively. Finally, case studies are effectively solved by the proposed approaches. The results shows that the cost can be effectively reduced compared with the operations without considering the demand correlation.
In the present work,a new subspace decomposition approach of fault deviation is developed for fault diagnosis via reconstruction for principle component analysis(PCA) based monitoring *** focuses on decomposing the fa...
详细信息
ISBN:
(纸本)9781479900305
In the present work,a new subspace decomposition approach of fault deviation is developed for fault diagnosis via reconstruction for principle component analysis(PCA) based monitoring *** focuses on decomposing the fault effects in different monitoring subspaces,principal subspace(PCS) and residual subspace(RS),and finding the significant fault deviations that are responsible for the concerned alarming monitoring *** is achieved by analyzing the relative changes of fault process in comparison with the normal status and designing a two-step feature decomposition *** fault data space is decomposed into two different parts for the purpose of fault reconstruction in PCS and RS of monitoring system *** is composed of the concerned fault deviations that contribute to alarming monitoring statistics which are thus significant to remove the out-of-control *** other is composed of general variations that are deemed to follow normal rules or insignificant to remove alarming monitoring *** feasibility and performance are illustrated with experimental data.
Particle systems are important building block for simulating vivid and detail-rich effects in virtual *** of the most difficult aspects of particle systems has been detecting collisions between particles and mesh *** ...
详细信息
Particle systems are important building block for simulating vivid and detail-rich effects in virtual *** of the most difficult aspects of particle systems has been detecting collisions between particles and mesh *** to the huge computation,a variety of proxy-based approaches have been proposed recently to perform visually correct ***,all either limit the complexity of the scene,fail to guarantee non-penetration,or are too slow for real-time use with many *** this paper,we propose a new octree-based proxy for colliding particles with meshes on the *** approach works by subdividing the scene mesh with an octree in which each leaf node associates with a representative normal corresponding to the normals of the triangles that intersect the *** present a view-visible method,which is suitable for both closed and non-closed models,to label the empty leaf nodes adjacent to nonempty ones with appropriate back/front property,allowing particles to collide with both sides of the scene *** show how collisions can be performed robustly on this proxy structure in place of the original mesh,and describe an extension that allows for fast traversal of the octree structure on the *** experiments show that the proposed method is fast enough for real-time performance with millions of particles interacting with complex scenes.
A stabilized Distributed MPC for large scale system is proposed and its designation is given in this paper for improving the global performance of closed-loop system. To make the performance of closed-loop system more...
详细信息
In this paper, a new fusion model for daytime visibility index estimation using traffic monitoring cameras is proposed, which does not depend on any preset targets or an accurate geometric calibration. In the proposed...
详细信息
ISBN:
(纸本)9781479905607
In this paper, a new fusion model for daytime visibility index estimation using traffic monitoring cameras is proposed, which does not depend on any preset targets or an accurate geometric calibration. In the proposed method, two features Average Sobel Gradient and Dark Channel Ratio are extracted from the input image to construct a visibility range estimation model, and the visibility index is computed based on it. A sunny detector and the gray-scale histogram duration verifications are adopted to improve the accuracy of the model. For evaluating the performance of the proposed method, some experiments have been performed. Experimental results show that the proposed method achieves higher accuracy than other two compared methods.
This paper focuses on the slot allocation scheme of MAC protocol to achieve energy-efficiency for the Wireless Body Area Network (WBAN). The WBAN is adopted to realize the wireless communication between the patient an...
详细信息
This paper focuses on the slot allocation scheme of MAC protocol to achieve energy-efficiency for the Wireless Body Area Network (WBAN). The WBAN is adopted to realize the wireless communication between the patient and the monitoring station in a healthcare system. The energy of miniature sensor nodes in WBAN is mainly consumed in the wireless interface and MAC protocol. We propose a time division multiple access (TDMA) protocol which takes advantage of the fixed topology of the WBAN. To implement the sensor energy efficiency, a slot allocation scheme is taken into account. Considering the heterogeneity of nodes, we formulate the problem as a Binary Integer Nonlinear Dynamic Programming (BINDP) to setup data priorities to achieve high slot utilization. Two heuristic algorithms are designed to solve the problem. Our results show that the proposed algorithms have the advantages of less energy consumption, higher slot utilization rate, and lower delay of the system.
This paper investigates an efficiency of signal control methodology, which mainly focuses on dealing with the traffic congestion problem in those key congested links and is applicable to be implemented in a hierarchic...
详细信息
This paper investigates an efficiency of signal control methodology, which mainly focuses on dealing with the traffic congestion problem in those key congested links and is applicable to be implemented in a hierarchical control structure in large-scale heterogeneous urban traffic networks. In this methodology, an algorithm for finding the most congested path is presented firstly, and the urban traffic flow is modeled by using a simplified macroscopic modeling framework. Then the problem of network-wide signal control is formulated as a linear programming problem that aims at minimizing the number of vehicles(or densities) in congested links so as to improve the mobility of the network and mitigate the traffic congestion. For the application of this method in real time, the multi-variables optimization problem including constraints is embedded in a model-based dynamic control procedure. Finally, different traffic demand scenarios are designed and four evaluation criteria are applied to measure the performance of the proposed method in a hypothetical road network. Compared with the fixed-time control strategy, the simulation results show that it is an effective and feasible way to regulate the traffic flow and mitigate the congestion in large-scale urban networks.
暂无评论