Online Static Security Assessment Module Using Artificial Neural Networks (original) (raw)
Related papers
Contingency analysis is an important task in today's power system. Fast and accurate contingency analysis is some of the major issues. In this paper two types of Artificial Neural Network (ANN) viz. Multilayer feed forward neural network (MLFFN) and Radial basis function network (RBFN) are used to implement online static security assessment. Newton Raphson (NR) method is done on an IEEE 118-test bus system and Composite Security Index (CSI) is calculated. Loads are varied from the base case values and for each load condition, line flow and bus voltages are calculated using a model based on the NR load flow method for training an ANN with the help of back propagation algorithm. Expected range of load variation and randomly selected 20-contingencies are tested in the training ANN model. The results obtained by the above ANN methods are matched with NR methods. The CSI is found out for various loads and contingencies in MLFFN and RBFN. The computation time required for MLFFN and RBFN is compared with NR method and found that RBFN is using less computation time average of 35.67291s.
International Journal of Electrical Power Energy Systems, 2012
This paper presents the application of cascade neural network (CANN) based approach for integrated security (voltage and line flow security) assessment. The developed cascade neural network is a combination of one screening module and two ranking modules, which are Levenberg-Marquardt Algorithm based neural networks (LMANNs). All the single line outage contingency cases are applied to the screening module, which is 3-layered feed-forward ANN having two outputs. The screening module is trained to classify them either in critical contingency class or in non-critical contingency class from the viewpoint of voltage/line loading. The screened critical contingencies are passed to the corresponding ranking modules, which are developed simultaneously by using parallel computing. Parallel computing deals with the development of programs where multiple concurrent processes cooperate in the fulfillment of a common task. For contingency screening and ranking, two performance indices: one based on voltage security of power system (VPI) and other based on line flow (MWPI) are used. Effectiveness of the proposed cascade neural network based approach has been demonstrated by applying it for contingency selection and ranking at different loading conditions for IEEE 30-bus and a practical 75-bus Indian system. The results obtained clearly indicate the superiority of the proposed approach in terms of speedup in training time of neural networks as compared to the case when the two ranking neural networks were developed sequentially to estimate VPI and MWPI.
ANN based integrated security assessment of power system using parallel computing
International Journal of Electrical Power & Energy Systems, 2012
This paper presents the application of cascade neural network (CANN) based approach for integrated security (voltage and line flow security) assessment. The developed cascade neural network is a combination of one screening module and two ranking modules, which are Levenberg-Marquardt Algorithm based neural networks (LMANNs). All the single line outage contingency cases are applied to the screening module, which is 3-layered feed-forward ANN having two outputs. The screening module is trained to classify them either in critical contingency class or in non-critical contingency class from the viewpoint of voltage/line loading. The screened critical contingencies are passed to the corresponding ranking modules, which are developed simultaneously by using parallel computing. Parallel computing deals with the development of programs where multiple concurrent processes cooperate in the fulfillment of a common task. For contingency screening and ranking, two performance indices: one based on voltage security of power system (VPI) and other based on line flow (MWPI) are used. Effectiveness of the proposed cascade neural network based approach has been demonstrated by applying it for contingency selection and ranking at different loading conditions for IEEE 30-bus and a practical 75-bus Indian system. The results obtained clearly indicate the superiority of the proposed approach in terms of speedup in training time of neural networks as compared to the case when the two ranking neural networks were developed sequentially to estimate VPI and MWPI.
Study of Neural Network Models for Security Assessment in Power Systems
This paper presents the application of different Neural Network (NN) models for classifying the power system states as secure/insecure. Traditional method of security evaluation involves performing load flow and transient stability analysis for each contingency, making it infeasible for real time application. Pattern Recognition (PR) approach is recognized as an alternative tool. The NN models adopted for classification includes Multilayer Perceptron (MLP), Learning Vector Quantization (LVQ), Probabilistic Neural Network (PNN) and Adaptive Resonance Theory Mapping (ARTMAP). The NN models designed are tested on 14 Bus, 30 bus and 57 Bus IEEE standard test systems. The performance of various NN models are studied in training and testing phases and the results are compared.
POWER SYSTEM SECURITY ASSESSMENT AND CONTINGENCY ANALYSIS USING SUPERVISED LEARNING APPROACH
The most important requirement and need for proper operation of power system is maintenance of the system security. The security assessment analysis is done to determine until what period the power system remains in the safe operable mode. Contingency screening is done to identify critical contingencies in order to take preventive actions at the right time. The severity of a contingency is determined by two scalar performance indices: Voltage-reactive power performance index(í µí±í µí°¼í µí±£í µí±) and line MVA performance index(í µí±í µí°¼í µí±í µí±£í µí±). Performance indices are calculated based on the conventional method known as Newton Raphson load flow program. Contingency ranking is done based on the severity of the contingencies. In this proposed work, contingency analysis is done with IEEE 14 bus. Since the system parameters are dynamic in nature and keeps on changing, there is need of so ft computing technologies. Supervised learning approach that uses Feed-Forward Artificial Neural Network(FFNN) is employed using pattern recognition methodology for security assessment and contingency analysis. A feature selection technique based on the correlation coefficient has been employed to identify the inputs for thee FFNN. With these soft computing techniques, greater accuracy is achieved.
ONLINE POWER SYSTEM CONTINGENCY SCREENING AND RANKING METHODS USING RADIAL BASIS NEURAL NETWORKS
This paper presents a supervising learning approach using Multilayer Feed Forward Neural Network(MFFN) and Radial Basis Fuction Neural Network(RBFN) to deal with fast and accurate static security assessment (SSA) and contingency analysis of a large electric power systems. The degree of severity of contingencies is measured by two scalar performance indices (PIs): Voltage-reactive power performance index, PIVQ and line MVA performance index, PIMVA. For each (N-1) contingency, thePerformance Index (PI) is computed using the Newton Raphson (NR) method. A correlation coefficient feature selection technique has been utilized to identify the inputs for the MFFN and RBFN. The proposed method has been applied on an IEEE 39-bus New England test system at different operating conditions comparing to single line outage and the results demonstrate the suitability of the methodology for on-line power system security assessment at Energy Management Center. The performace of the proposed ANN models is compared withNewton Raphson (NR) method and the results shows that the proposed model is effective and reliable in terms of static security assessment of power systems.
Power system static security assessment using self-organizing neural network
2006
Artificial neural network approach to the problem of static security assessment of power system is presented. This paper utilizes the artificial neural net of Kohonen's self-organizing feature map (SOFM) technique that trans- forms input patterns into neurons on the two-dimensional grid to classify the secure/insecure status of the power system. SOFM uses the line flows under different component cases as inputs and self-organizes to obtain the clus- ter of the components based on their loading limits. The output of SOFM provides information about the violation of the constraints from which the operating state of the power system can be identified, which can be classified as secure or insecure. The proposed method of security assessment was initially demonstrated for a model 3 genera- tor 6-bus system and later extended to IEEE-14, -30 and -57 bus systems.
ANN Application For On-Line Power System Security Assessment
2006 International Conference on Probabilistic Methods Applied to Power Systems, 2006
The paper presents the preliminary results of an on-going research activity concerning the application of ANN (Artificial Neural Network) for on-line identification of potential harmful states in power systems (contingency screening). The necessity of on-line Static Security Assessment with a good degree of confidence and the evaluation of indices for successive indications to power system operators of possible remedial actions is deeply felt in the new context of liberalized electrical energy markets. The paper addresses primarily the use of ANN for contingency screening. It describes and reports the activity for choosing the most suitable ANN structure and training the ANN for a realistic power system. The chosen ANNs are then trained and used to assess the security state of a larger power system representing an equivalent model of the Italian HV grid.
Contingency Constrained Power System Security Assessment using Cascade Neural Network
A unified approach to power system security assessment and contingency analysis suitable for on-line applications is proposed. The severity of the contingency is measured by two scalar Performance Indices (PIs): Voltage-reactive power performance index, PIVQ and line MVA performance index, PIMVA. In this paper, a two stage cascade neural network is developed: Stage I employs Multi-Layer Perceptron (MLP) neural network trained by back propagation algorithm for estimating PIs and Stage II utilizes Kohonen's Self Organizing Feature Map (KSOFM) for contingency screening and ranking. The effectiveness of proposed methodology is tested on IEEE 39-bus New England system at different loading conditions corresponding to single line outage. The overall accuracy of the test results highlights the suitability of the approach for on-line applications to fast and accurate security assessment and contingency analysis.
Static Security Assessment Using a Probabilistic Neural Network Based Classifier
2011
In this paper, a probabilistic neural network (PNN) based classifier is used to judge the static security of the power system. The proposed classifier classifies the security of the power system based on the voltage profile of each bus in reference to changes in the generation and load profile in the system. The probabilistic neural network is used and compared with the radial basis function neural network (RBFNN) and the backpropagation neural network (BPNN). The PNN shows superior results in comparison to other techniques. The proposed methodology is examined using three IEEE standard test systems, where the input to the neural network is the voltage profile at each bus, the output of the PNN classifies the security of the power system into three classes, normal, alert and emergency.