Sensitivity based voltage instability alleviation using ANN
01 Oct 2003-International Journal of Electrical Power & Energy Systems (Elsevier)-Vol. 25, Iss: 8, pp 651-657
TL;DR: A noble method for power system voltage instability estimation and improvement using ANN is presented in this paper, which is based on the fact that reactive power injections at critical buses of the power system help to steer the system away from a developing voltage collapse.
About: This article is published in International Journal of Electrical Power & Energy Systems.The article was published on 2003-10-01. It has received 3 citations till now. The article focuses on the topics: Voltage optimisation & Voltage regulation.
Citations
More filters
TL;DR: In this article, the performance of various NN controllers is compared with one another as well as to other types of controllers, and the design of a proper NN control can maintain first-swing stability, damp oscillation, ensure voltage stability and the reliable supply of electric power.
72 citations
01 Mar 2006
TL;DR: An extended bibliography of ANN application to power systems is presented, which discusses the ability of ANN to learn complex non-linear relations, and their modular structure, which allows parallel processing.
Abstract: Applications of artificial neural networks (ANN) to power systems is an area of growing interest. The main reasons are the ability of ANN to learn complex non-linear relations, and their modular structure, which allows parallel processing. This paper presents an extended bibliography of ANN application to power systems. Brief discussion on applications of ANN to various power systems problems have also been presented in this paper.
23 citations
TL;DR: This work uses the hybrid intelligent algorithm Genetic Algorithm - Artificial Bee Colony with hybridization with ABC to identify the source effectively and gives better optimal solution as compared to individual intelligent algorithm.
Abstract: Reactive power and voltage control is a minimization problem. In this paper the multi objective function consist of minimization of real power losses, minimization of voltage deviation and minimization of voltage stability index subjected to equality and inequality constraints are considered. This can be achieved by proper adjustment of control variables such as the generator voltages, the transformer tap settings, and the switchable VAR sources that would minimize the real power loss, the voltage deviation and the voltage stability index. In this work, the hybrid intelligent algorithm Genetic Algorithm - Artificial Bee Colony (GA- ABC) are used. The hybrid algorithms used are the combination of best features of two intelligent algorithms. GA has good crossover operator and hence inspires hybridization with ABC to identify the source effectively. The population is evolving iteration by iteration to find global optimal solution. To evaluate the performance of the developed algorithm standard IEEE 30 bus system is used. This hybrid algorithm gives better optimal solution as compared to individual intelligent algorithm.
References
More filters
TL;DR: Back-propagation repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector, which helps to represent important features of the task domain.
Abstract: We describe a new learning procedure, back-propagation, for networks of neurone-like units. The procedure repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector. As a result of the weight adjustments, internal ‘hidden’ units which are not part of the input or output come to represent important features of the task domain, and the regularities in the task are captured by the interactions of these units. The ability to create useful new features distinguishes back-propagation from earlier, simpler methods such as the perceptron-convergence procedure1.
23,814 citations
TL;DR: This paper provides an introduction to the field of artificial neural nets by reviewing six important neural net models that can be used for pattern classification and exploring how some existing classification and clustering algorithms can be performed using simple neuron-like components.
Abstract: Artificial neural net models have been studied for many years in the hope of achieving human-like performance in the fields of speech and image recognition. These models are composed of many nonlinear computational elements operating in parallel and arranged in patterns reminiscent of biological neural nets. Computational elements or nodes are connected via weights that are typically adapted during use to improve performance. There has been a recent resurgence in the field of artificial neural nets caused by new net topologies and algorithms, analog VLSI implementation techniques, and the belief that massive parallelism is essential for high performance speech and image recognition. This paper provides an introduction to the field of artificial neural nets by reviewing six important neural net models that can be used for pattern classification. These nets are highly parallel building blocks that illustrate neural net components and design principles and can be used to construct more complex systems. In addition to describing these nets, a major emphasis is placed on exploring how some existing classification and clustering algorithms can be performed using simple neuron-like components. Single-layer nets can implement algorithms required by Gaussian maximum-likelihood classifiers and optimum minimum-error classifiers for binary patterns corrupted by noise. More generally, the decision regions required by any classification algorithm can be generated in a straightforward manner by three-layer feed-forward nets.
7,798 citations
"Sensitivity based voltage instabili..." refers methods in this paper
...Adaptive error back propagation algorithm [11-13] is used to train MLP....
[...]
TL;DR: This paper provides an introduction to the field of artificial neural nets by reviewing six important neural net models that can be used for pattern classification and exploring how some existing classification and clustering algorithms can be performed using simple neuron-like components.
Abstract: Artificial neural net models have been studied for many years in the hope of achieving human-like performance in the fields of speech and image recognition. These models are composed of many nonlinear computational elements operating in parallel and arranged in patterns reminiscent of biological neural nets. Computational elements or nodes are connected via weights that are typically adapted during use to improve performance. There has been a recent resurgence in the field of artificial neural nets caused by new net topologies and algorithms, analog VLSI implementation techniques, and the belief that massive parallelism is essential for high performance speech and image recognition. This paper provides an introduction to the field of artificial neural nets by reviewing six important neural net models that can be used for pattern classification. These nets are highly parallel building blocks that illustrate neural net components and design principles and can be used to construct more complex systems. In addition to describing these nets, a major emphasis is placed on exploring how some existing classification and clustering algorithms can be performed using simple neuron-like components. Single-layer nets can implement algorithms required by Gaussian maximum-likelihood classifiers and optimum minimum-error classifiers for binary patterns corrupted by noise. More generally, the decision regions required by any classification algorithm can be generated in a straightforward manner by three-layer feed-forward nets.
3,164 citations
"Sensitivity based voltage instabili..." refers methods in this paper
...Adaptive error back propagation algorithm [11-13] is used to train MLP....
[...]
01 Jan 1986
1,393 citations
"Sensitivity based voltage instabili..." refers methods in this paper
...Adaptive error back propagation algorithm [11-13] is used to train MLP....
[...]
TL;DR: In this article, a method for the online testing of a power system is proposed which is aimed at the detection of voltage instabilities, and an indicator L is defined which varies in the range between 0 (noload of system) and 1 (voltage collapse).
Abstract: A method for the online testing a power system is proposed which is aimed at the detection of voltage instabilities. Thereby an indicator L is defined which varies in the range between 0 (noload of system) and 1 (voltage collapse). Based on the basic concept of such an indicator various models are derived which allow to predict a voltage instability or the proximity of a collapse. The indicator uses information of a normal load flow. The advantage of the method lies in the simplicity of the numerical calculation and the expressiveness of the result.
1,012 citations