In order to remedy the defect that the determination of weight in fuzzy comprehensive evaluation is impacted by subjectivity, the combination weight is introduced. In this paper, the optimization Model combines the su...
详细信息
In order to remedy the defect that the determination of weight in fuzzy comprehensive evaluation is impacted by subjectivity, the combination weight is introduced. In this paper, the optimization Model combines the subjective weight and objective weight, which is solved by PSO, is built. At the same time, In order to give full consideration to the uncertain and fuzzy factors which involved in the grid planning, this paper combines the combination weight and fuzzy comprehensive evaluation to assess the grid-planning scheme. The calculation results of IEEE Garver-6 show that the proposed fuzzy comprehensive evaluation system is clear in theory and convenient to calculate, the combination weight is objective and reasonable as well as its results are scientific and intuitive.
The Smart Grid(SG) has widely supported the electric power from the Distributed Generation(DG). It becomes a practical standard to generate the electric power from a renewable energy into the distribution system to co...
详细信息
The Smart Grid(SG) has widely supported the electric power from the Distributed Generation(DG). It becomes a practical standard to generate the electric power from a renewable energy into the distribution system to compensate for the power demand, especially in the peak time. However, the advancement of the SG continuing with the classical problem of active power loss as the traditional grid. This research aimsto solve the active power loss problem by analyzing the elements and study to solve, in the scope of the organization that provides the electrical power. In order to solve the problem, the solutions can be achieved by feeder routing with adjusting cost Dijkstra's algorithm, afterward decided the allocation and sizing of DG by using the Evolutionary Computing(EC) which are Harmony Search(HS), Artificial Bee Colony(ABC), and particleswarmoptimization(PSO) algorithms. The experiment evaluates the performance of the algorithm usingpower flow analysis, Backward/Forward Sweep Method, on the IEEE 33-bus system. From the experimental result, the PSO provides the best performance. The overall active power loss in the case 3 DGs was reduced from 202.67 to 52.29 k W, representing 74.20%reduction.
Membrane Bio-Reactor(MBR) technology plays an important role in modern sewage treatment, but the performance of the MBR technology is seriously affected by the membrane fouling. In general, the result of membrane foul...
详细信息
ISBN:
(纸本)9781509055081
Membrane Bio-Reactor(MBR) technology plays an important role in modern sewage treatment, but the performance of the MBR technology is seriously affected by the membrane fouling. In general, the result of membrane fouling is decline of MBR membrane flux, and the effect of MBR sewage treatment is directly affected by the decrease of membrane flux. In order to predict MBR membrane flux accurately and rapidly, the forecasting model of MBR membrane flux based on particleswarm improving wavelet neural network algorithm (PSO_WNN) was established. In view of the complexity of the MBR membrane fouling factor, in the beginning,the main components of the factors affecting the flux of MBR membrane were analyzed .The important factor is extracted as the input of the PSO_WNN prediction model, and the membrane flux is used as the ***, the PSO_WNN simulation model is established, and the prediction results are obtained by using the model. By comparing the predicted data and experimental data, the predictive accuracy of this algorithm is high on the membrane flux, and compared with the BP neural network model, the comparative results show that the PSO_WNN forecasting model has higher predicted accuracy.
The direct-drive permanent magnet synchronous generator (DDPMSG) for wind power system uses a back-to-back double PWM converter. PI controller based on decoupling control strategies is used to control generator side c...
详细信息
ISBN:
(纸本)9781467363204
The direct-drive permanent magnet synchronous generator (DDPMSG) for wind power system uses a back-to-back double PWM converter. PI controller based on decoupling control strategies is used to control generator side converter and grid side converter. But the parameters of the PI controller are difficult to obtain correctly. Though manual tuning method is applied to regulate the parameters, the method would waste a lot of time and greatly depend on the experience. The paper analyses the mathematical model of direct-drive permanent magnet synchronous wind power generation system. It presents a particleswarmoptimization (PSO) method for determining the parameters of PI controller for PMSG to improve the control ability. PSO is powerful stochastic evolutionary algorithm that is used to find the global optimum solution in search space. Under the condition of wind speed mutation, the simulation results of PMSG system after PI parameter optimization show that the PI control with PSO algorithm can fit the real value. The PSO controller has fast convergence rate, strong adaptability and good dynamic performance.
Evolutionary algorithms combined with artificial neural network (ANN) have been applied in RFID tag antenna optimization platform. An effective method for RFID tag antenna optimization by particleswarmoptimization (...
详细信息
Evolutionary algorithms combined with artificial neural network (ANN) have been applied in RFID tag antenna optimization platform. An effective method for RFID tag antenna optimization by particleswarmoptimization (PSO) algorithm or genetic algorithm (GA) combined with ANN is presented in this paper. ANN is used to establish the non-linear model of tag antenna which is shown to be as accurate as an electromagnetic simulator and can be used for constructing the fitness function of PSO and GA. The PSO and GA optimizers are developed and executed in C++. Finally, this optimization method is turned out to be much more efficient than any electromagnetic simulator optimization. In addition, the PSO optimization results show that it is faster than GA.
Dissolved gas analysis is an effective method for the early detection of incipient fault in power transformers. To improve the capability of interpreting the result of dissolved gas analysis, a technology is propo...
详细信息
ISBN:
(纸本)9781424479573
Dissolved gas analysis is an effective method for the early detection of incipient fault in power transformers. To improve the capability of interpreting the result of dissolved gas analysis, a technology is proposed in this paper. The particleswarmoptimization (PSO) technique is used to integrate with Back Propagation (BP) neural networks, and using particleswarm to optimize the network's weights and biases, the fault of transformers is simulated and discussed. The results show that the accuracy of PSO-BP method is significantly higher than that of the conventional three-ratio method. So the algorithm based on PSO-BP network model provides a more accurate, safe and reliable result for the fault diagnosis of transformers.
In this paper,a short-term load forecasting model and a load early warning model for charging station based on PSO-SVM are *** swarmoptimization(PSO) is used to optimize the parameters of support vector machine(SVM) ...
详细信息
In this paper,a short-term load forecasting model and a load early warning model for charging station based on PSO-SVM are *** swarmoptimization(PSO) is used to optimize the parameters of support vector machine(SVM) model,and the PSO-SVM load forecasting model for the optimal nuclear parameters of charging station is established according to the normalized root mean square error(NRMS).On the basis of it,a load warning model of charging station is established and verified by an *** show that the short-term load forecasting model based on PSO-SVM and the load forecasting model of charging station meet the requirements of forecasting and forecasting accuracy.
The natural calamity or disaster may destroy all communication networks especially a cellular network that relies on a tower. Although many solutions to an ad hoc wireless network have been proposed, forming a network...
详细信息
The natural calamity or disaster may destroy all communication networks especially a cellular network that relies on a tower. Although many solutions to an ad hoc wireless network have been proposed, forming a network covering a respective region with mobile robots toward optimal coverage remains to be an open problem. In this paper, we take the initiative to handle the optimal network coverage and path selection in disaster region with the help of multiple movable/rover robots. This paper consists of load balance distribution algorithm and optimal coverage algorithm applied to find the next optimally possible node location for all robots. Next, the robots maneuvering in an unknown disaster environment to identify the optimal path between the source and destination by using a particle swarm optimization algorithm. Finally, simulated results show that the algorithms can significantly improve the network coverage in the entire region, and the optimal path can effectively identify the optimal solution for all rover robots.
Taking the comprehensive performance of a new type of high-speed unmanned surface vehicle(USV) including its rapidity, maneuverability, seakeeping and overturning resistance into consideration, this paper establishes ...
详细信息
ISBN:
(纸本)9781510835702
Taking the comprehensive performance of a new type of high-speed unmanned surface vehicle(USV) including its rapidity, maneuverability, seakeeping and overturning resistance into consideration, this paper establishes a mathematical model of the performance comprehensive optimization of high-speed USV. And according to the mathematical model and optimizationalgorithm, comprehensive optimization software based on a variety of optimizationalgorithms was designed and compiled to analyze the relevant calculation. The results indicates that the optimization effect of the growth mechanism is more superior to the roulette mechanism;genetic algorithm of growth mechanism and particle swarm optimization algorithm would have the best results in the optimization of the 5000 th generation, and it can get the rapidity optimization system had greater influence on the total optimization system;and what's more, the optimal values of hull length and other key design variables and partial parameters of different algorithms are obtained.
Intrusion detection plays more important role in network security today. This paper introduces a method, particleswarmoptimization and support vector machine, to intrusion detection system, and presents a new design...
详细信息
Intrusion detection plays more important role in network security today. This paper introduces a method, particleswarmoptimization and support vector machine, to intrusion detection system, and presents a new design of ID Based on particleswarmoptimization and Support Vector Machine. This paper presents an optimal selection approach of the SVM parameters(regulation parameter C and the radial basis function width parameter σ ) based on particle swarm optimization algorithm. The experiments show that the optimal parameter selection approach based on PSO is available and the Research of Intrusion Detection Based on particleswarmoptimization and Support Vector Machine is effective in reducing the number of alerts, false positive, false negative better.
暂无评论