Real-time Transient Stability Assessment Research Articles

Real-Time Transient Stability Assessment Based on Genetic Algorithm-Extreme Learning Machine

In this paper an genetic algorithm-extreme learning machine (ELM) based real-time transient stability assessment method is proposed. This method uses genetic algorithm (GA) to search optimal input weights and hidden biases in the principle of cross validation to establish GA-ELM classifier. In order to do real-time transient stability assessment, generator trajectories of rotor angle, rotor speed, voltage magnitude, electromagnetic power and imbalance power in-and post-disturbance are chosen as original features for the quick access based synchronously sampled values. Simulation results of New-England 39-bus system show that this method has good performance in power system transient stability assessment.

Novel Techniques for Real Time Computing Critical Clearing Time SIME-B and CCS-B

Real time transient stability assessment mainly depends on real-time prediction. Unfortunately, conventional techniques based on offline analysis are too slow and unreliable in complex power systems. Hence, fast and reliable stability prediction methods and simple stability criterions must be developed for real time purposes. In this paper, two new methods for real time determining critical clearing time based on clustering identification are proposed. This article is covering three main sections: (i) clustering generators and recognizing critical group; (ii) replacing the multi-machine system by a two-machine dynamic equivalent and eventually, to a one-machine-infinite-bus system; (iii) presenting a new method to predict post-fault trajectory and two simple algorithms for calculating critical clearing time, respectively established upon two different transient stability criterions. The performance is expected to figure out critical clearing time within 100ms-150ms and with an acceptable accuracy.

Real-time transient stability assessment model using extreme learning machine

In recent years, computational intelligence and machine learning techniques have gained popularity to facilitate very fast dynamic security assessment for earlier detection of the risk of blackouts. However, many of the current state-of-the-art models usually suffer from excessive training time and complex parameters tuning problems, leading to inefficiency for real-time implementation and on-line model updating. In this study, a new transient stability assessment model using the increasingly prevalent extreme learning machine theory is developed. It has significantly improved the learning speed and can enable effective on-line updating. The proposed model is examined on the New England 39-bus test system, and compared with some state-of-the-art methods in terms of computation time and prediction accuracy. The simulation results show that the proposed model possesses significant superior computation speed and competitively high accuracy.

Transient stability Assessment using Artificial Neural Network Considering Fault Location

This paper describes the capability of artificial neural network for predicting the critical clearing time of power system. It combines the advantages of time domain integration schemes with artificial neural network for real time transient stability assessment. The training of ANN is done using selected features as input and critical fault clearing time (CCT) as desire target. A single contingency was applied and the target CCT was found using time domain simulation. Multi layer feed forward neural network trained with Levenberg Marquardt (LM) back propagation algorithm is used to provide the estimated CCT. The effectiveness of ANN, the method is demonstrated on single machine infinite bus system (SMIB). The simulation shows that ANN can provide fast and accurate mapping which makes it applicable to real time scenario.

Transient behavior of a distribution network incorporating decentralized generation

Dispersed or decentralized storage and generation of electric energy (noted DSG) finds its source in cogeneration using either clean fuels or renewable resources, such as solar and wind. Typically these small energy sources are grafted to existing networks through weak utilities ties. This paper discusses a particular operating problem that may be faced by the electrical utility wishing to integrate DSGs. The latter are especially at risk of losing their utility ties following some electrical disturbances such as short circuits, line outages, etc. and consequently risk losing synchronism or being separated from the main network. Hence the anticipated penetration of DSGs in distribution networks will be accompanied by an increase in system vulnerability. Here we describe transient stability simulations of distribution networks in which DSGs are integrated, and in particular we investigate their needs in terms of frequency regulation. In our simulations the distribution network is fed simultaneously by the main power system and by one or two DSGs; this allows us to study the interactions between all of the components. All simulation scenarios include a small three-phase turbine-alternator powered on gas (TAG) synchronously connected to the distribution network. The second DSG is either a directly-connected TAG, or photovoltaic cells (PV) interfaced to the distribution network through a three-phase converter and accumulators. Equipped with a continuous frequency measurement capability, real time transient stability assessment of DSG distribution/main network interconnections is now possible. An algorithm, which achieves that goal, has been developed and tested on a power system model subjected to various contingencies.

Probabilistic on-line transient stability analysis

The feasibility of a probabilistic framework for real-time transient stability assessment (TSA) is explored. The main contribution of the probabilistic approach consists in a natural framework for dynamic security assessment (DSA). An advantage of the proposed approach is the enlargement of the time horizon for TSA, which allows contingency analysis to be performed over a longer time. The assessment of the instability probability allows the severity of contingencies and their likelihood to be considered on a common basis.

Generalized one-machine equivalents in transient stability studies

We consider an emerging class of hybrid methods which basically reduce a multimachine power system into a one-machine infinite bus (OMIB) equivalent and then apply the suitably adapted equal-area criterion. A time-domain transient stability program is used to refresh the OMIB parameters at each time step to arrive at "generalized" OMIBs. The scheme is able to provide accurate real-time transient stability assessment under any power system modeling, any stability scenario and any instability mode. On the other hand, similar generalized OMIBs may potentially be designed for real-time transient stability emergency control, by using real-time measurements. The purpose of this letter is to highlight some unique enhancements to the class of methods offered by the generalized OMIB concept.