Kusum Verma

PMU-ANN based real time monitoring of power system electromechanical oscillations

Power system oscillations monitoring is a vital issue in operation of modern interconnected power systems. The existing methods for identifying the electromechanical modes are time-consuming and require modelling of the entire system that includes a large number of states and are performed offline. In this paper, an integrated Phasor Measurement Unit and Artificial Neural Network (PMU-ANN) based approach for online and real time monitoring of power system electromechanical oscillations is proposed. The placement of PMU is obtained using Integer Linear Programming (ILP). The data obtained from PMU is given as input to a multilayer Feedforward Neural Network (FFNN) and its output gives all the information related to the modes of the system and the mode ranking. The effectiveness of the proposed approach is investigated on IEEE 39-bus test system. The results show that the proposed approach is fast with less computational burden and is suitable for online and real time oscillations monitoring of the power systems under varying operating conditions.

Preventive and Emergency Control of Power System for Transient Stability Enhancement

This paper presents preventive and emergency control measures for on line transient stability (security) enhancement. For insecure operating state, generation rescheduling based on a real power generation shift factor (RPGSF) is proposed as a preventive control measure to bring the system back to secure operating state. For emergency operating state, two emergency control strategies namely generator shedding and load shedding have been developed. The proposed emergency control strategies are based on voltage magnitudes and rotor trajectories data available through Phasor Measurement Units (PMUs) installed in the systems. The effectiveness of the proposed approach has been investigated on IEEE-39 bus test system under different contingency and fault conditions and application results are presented.

Real-Time Monitoring of Post-Fault Scenario for Determining Generator Coherency and Transient Stability Through ANN

Power system monitoring and control in real time is a challenging task for modern power system due to large operational constraints. The deployment of phasor measurement units (PMUs) at key locations provides an opportunity for devising effective power system monitoring and control measures. In this study, a new method is proposed to determine the real-time transient stability status and identification of the coherent generator groups by predicting the rotor angle values following a large disturbance through radial basis function neural network. The first six cycles of synchronously sampled post-fault data measurements from PMUs consisting of rotor angles and voltages of generators are taken as the input to the neural network to predict the future state of the system. The proposed method can also determine the synchronism state of the individual machine in real time. The proposed scheme is demonstrated on the IEEE-39 bus test system at different operating conditions.

Generator coherency determination in a smart grid using artificial neural network

Smart grid is a concept of modern power grid that an intelligently integrates all supply, grid and demand elements connected to it in order to efficiently deliver sustainable, economic and secure electricity supplies. Power system security is one of the major objectives of the Smart Grid. This paper presents an artificial neural network based approach for fast and accurate assessment of transient security status and generator coherency. Radial basis function (RBF) neural network is employed to obtain the objectives for a given operating condition. The methodology can serve as decision making tool for the power planners to take preventive control actions for generation shedding/rescheduling for online applications. A feature selection technique based on the correlation coefficient has been employed. The effectiveness of the proposed methodology is demonstrated by overall accuracy of the test results for unknown patterns for IEEE 39-bus New England system.

Determination of vulnerable machines for online transient security assessment in smart grid using artificial neural network

Smart grid integrates effective harnessing of control, communication and computer technologies in the operation of present day bulk power system to create several possibilities for meeting challenges of the electricity industry. This paper presents an artificial neural network based approach for fast and accurate power system transient security assessment. Radial basis function (RBF) neural network is employed to assess the transient security status by identifying each vulnerable generating machine that will lose synchronism for a given operating condition. The model can serve as decision making tool for the power planners to take preventive control actions for generation shedding/rescheduling for online applications. A feature selection technique based on the class separability index and correlation coefficient has been employed. The effectiveness of the proposed methodology is demonstrated by overall accuracy of the test results for unknown patterns for IEEE 39-bus New England system

Intelligent wide area monitoring of power system oscillatory dynamics in real time

The oscillatory stability of the system is becoming a vital problem to be taken into consideration in modern interconnected power systems operation. The information about poorly damped modes and their source should be known to the operator in real time to apply any control actions. But the conventional methods are usually time consuming and offline. In this paper, an intelligent Wide Area Measurement System (WAMS) based method employing Phasor Measurement Unit and Artificial Neural Network (PMU-ANN) is proposed, capable of identifying poorly damped low frequency oscillations and the responsible critical generator in real time under varying system operating conditions. The optimal PMU Placement is obtained using Integer Linear Programming (ILP). The input to ANN is the real time data obtained from PMU and output is the online mode related information like participation factor, damping of modes, and the most critical generator. The effectiveness of the proposed approach is investigated on IEEE 39-bus test system. The test results obtained for unseen operating conditions proves that the proposed method effectively monitors the power system oscillatory dynamics and identify the poorly damped modes and their source in real time with very less computational burden.

Real time intelligent oscillatory stability monitoring and coherent groups identification

Power system oscillation monitoring and control in real-time is an important issue to be taken into consideration in modern interconnected power systems operation. This paper proposes a method to find the system damping and identification of coherent groups in the system following a disturbance in real-time using Artificial Neural Network. The first four cycles of post disturbance data comprising of bus voltage magnitudes and angles measured from optimally placed Phasor Measurement Units using Integer Linear Programming. The dimensionality reduction is also done using Principal Component Analysis. The results show that the proposed method is very fast and predict the damping and coherent groups accurately in real-time for all operating conditions including topological variations, with very less computational burden. The effectiveness of proposed approach is tested on IEEE 39-bus test system.

PMU-ANN based approach for real time voltage stability monitoring

Voltage Stability is one of the major problems to be taken into consideration for secure and reliable operation of modern power systems. This paper presents a Phasor Measurement Unit and Artificial Neural Network (PMU-ANN) based approach for voltage stability monitoring in real time. The proposed approach uses the Feed Forward Neural Network (FFNN). The input to FFNN is voltage magnitude and voltage angle measured from PMU. The optimal placement of PMU is obtained by Integer Linear Programming (ILP). Various voltage stability indices are used as indicator for voltage stability monitoring. The effectiveness of the proposed approach is demonstrated on New England 39 bus test system.

Artificial neural network based early detection of real-time transient instability for initiation of emergency control through wide-area synchrophasor measurements

This paper proposes an approach for early detection of transient instability of power system for initiating the emergency control in time. The synchrophasor measurements are used for real-time monitoring of the system. The Artificial Neural Network (ANN) is used as classifier for predicting the transient instability status of the system with rotor angles and speeds (frequency) of generator as inputs at different consecutive cycle lengths after fault clearing. The stability status obtained from ANN can be utilized for initiating the emergency control actions within few cycles from fault clearing. The proposed scheme is able to successfully predict the transient stability status of the system for unseen operating conditions with varying topology. The proposed method is investigated on IEEE-39 New England system for its real-time applications and results obtained reflect the effectiveness of the proposed methodology.

Real-time identification of generator coherent groups through synchrophasor measurements and ANN

Power system monitoring and control in real-time is a challenging task for modern power system due to large number of operational constraints involved. This paper proposes a method to find the real-time transient stability state and identification of the coherent generator groups by predicting the rotor angle values following a large disturbance through radial basis function neural network. The first six cycle data of rotor angles and voltages of generators from fault clearing obtained through synchrophasor measurements are taken as the input to the neural network. The proposed method is also able to determine synchronism state of the individual machine in real-time. The proposed scheme is investigated on IEEE-39 bus test system to show the effectiveness of the proposed scheme.