Voltage sag is a temporary voltage drop at the fundamental component of utility voltage line. Because of its nature, fast detecting and compensating of sag is very critical. In this work, adaptive neural network is pr...
详细信息
ISBN:
(纸本)9781467350723
Voltage sag is a temporary voltage drop at the fundamental component of utility voltage line. Because of its nature, fast detecting and compensating of sag is very critical. In this work, adaptive neural network is proposed for detection and compensating of sag conditions. The neural network part uses Adaline structure to model the fundamental component of line voltage. Moreover, an adaptive learning rule is applied on the neural network algorithm to enhance the system speed in detecting voltage sag magnitude and phase. For compensating the fault, another controller plant is implemented that uses Levenberg-Marquardt backpropagation algorithm. This plant is trained during normal condition of voltage line and memorizes its peak magnitude. While voltage sag happens, it compares difference between the magnitudes of the normal condition to the sag situation and generates proper switching signal for the compensator. The proposed compensator in this work is series active power filter which has ability to compensate power system harmonics at the same time.
The future mobile networks will have to support increasing number of mobile users and provide efficient services that are context sensitive. Because of the limited amount of wireless resources, the better utilization ...
详细信息
The future mobile networks will have to support increasing number of mobile users and provide efficient services that are context sensitive. Because of the limited amount of wireless resources, the better utilization of system resources is required. Lately there has been an increasing interest to develop predictive algorithms for user movements in order to provide better optimization. In this paper we suggest an algorithm for the implementation of the selective reservation concept for handover resources. We propose a next-move prediction scheme using the history of the user's movement directions and a backpropagation neural network algorithm. We show that for certain types of movement patterns the accuracy of 100% can be achieved. The developed algorithm is light-weight and does not require excessive computing power, and could be into terminals.
This paper proposes a method to accurately predict the maximum output power of the solar photovoltaic arrays under the shadow conditions by using neural network, a combined method using the multilayer perceptrons feed...
详细信息
This paper proposes a method to accurately predict the maximum output power of the solar photovoltaic arrays under the shadow conditions by using neural network, a combined method using the multilayer perceptrons feed forward network and the back-propagation algorithm. Using the solar irradiation levels, the ambient temperature and the sun's position angles as the input signals, and the maximum output power of the solar photovoltaic array as an output signal, the training data for the neural network is received by measurement on a particular time, when solar panel is shaded. After training, the neural network model's accuracy and generalization are verified by the test data. This model, which is called the shading function, is able to predict the shadow effects on the solar PV arrays for long term with low computational efforts.
A new method is discussed using neural network models in combination with empirical orthogonal function (EOF) analysis for the basin-scale wind-wave forecast. For the Bay of Bengal region EOF analysis has been perform...
详细信息
A new method is discussed using neural network models in combination with empirical orthogonal function (EOF) analysis for the basin-scale wind-wave forecast. For the Bay of Bengal region EOF analysis has been performed separately on the significant wave height (SWH) data, zonal (U) and meridional (V) components of wind data. For basin scale forecast the dominant principal component (PC) has been subjected to univariate and multivariate neural network models for future predictions. In the univariate approach, only past values of SWH time series are used and in the multivariate approach, U and V time series are used to predict future SWH values. Efficiency in terms of accuracy and speed of four different backpropagation algorithms, namely, Levenberg-Marquardt (LM), Bayesian Regularization (BR), Scaled Conjugate Gradient (SCG) and Fletcher Conjugate Gradient (CGF) have been compared for 1 to 12 multistep ahead time steps and 1 to 13 neurons. After training the models using varied neurons and the PCs, representing the entire basin, the neurons are fixed at which minimum errors are obtained. Further experiments are conducted using the fixed neurons and the PCs for 1 to 12 time steps ahead SWH prediction. Finally independent datasets consisting of normal and cyclonic wind-wave parameters are tested successfully using the above fixed neurons for delays (1 to 12) corresponding to 3 days or 72 h forecast. The novelty of the study lies is the usage of the PCs which represent the entire basin rather than computations at individual locations which are expensive technically and time consuming.
暂无评论