Search

Eastern Regional (ER) grid of India is one of the five regional grids consisting of voltage level 765 kV, 400 kV, 220 kV and numerous buses at lower voltage range. ER grid is the backbone of the Indian Grid as it is one of the main power generating hubs. Stability of the Indian Grid depends a lot on ER grid as it is the core of the generation and transmission system. For performing stability studies and to determine the weak area of the grid generally L-Index method is used. For detailed analysis like computation of voltage recovery time, maximum frequency deviation and critical clearing time of the buses of the system L-Index method is not suitable. Hence dynamic simulation is performed as it provides options to compute various parameters of ER Grid. The system has been studied using 197 buses of voltage levels 220 kV and above and transmission lines running over a length of 23,693 km. In this paper the power flow modelling, simulation and analysis of the Eastern Grid of India is performed. L-Index algorithm along with dynamic simulation provides the scope of computation of voltage recovery time, maximum frequency deviation and critical clearing time (by introducing an initial transient disturbance) along with the prediction of weak area of the system which gives a complete picture of transient stability of ER Grid. [ABSTRACT FROM AUTHOR]

• Conflict between computation efficiency and accuracy exists in model-driven method. • Data-driven method is able to correct error of model-driven method. • Error tolerance difference is considered in training objection data-driven method. The critical clearing time (CCT) is one of the most important indexes for large-disturbance rotor angle stability margin evaluation. In practice, model-driven methods are usually realized based on simplified models to ease the computational burden, but the accuracy is sacrificed. To solve this problem, a data-driven method is adopted in this paper for fast error correction of a model-driven method, creating an integrated method. Both a reliable accuracy and an acceptable computation speed can be achieved with this integrated method. Meanwhile, involvement of model-driven method helps enhance robustness of the integrated method to training sample insufficiency, measurement error and power system scale. In addition, the data-driven method is further transformed on the basis of a cost-sensitive approach where the error tolerance for different actual CCT values should be differentiated during the training process instead of being treated equally in the common data-driven method. To mitigate the negative effect caused by such transformations, an ensemble learning structure is also constructed. In this paper, an integrated extended equal-area criterion (IEEAC) and an extreme learning machine (ELM) are applied as model-driven and data-driven methods, respectively. A genetic algorithm (GA) is used in the ensemble learning structure construction. Validations show that the proposed integrated method with the transformed data-driven method can improve the CCT prediction accuracy and avoid the polarization of the error distribution. [ABSTRACT FROM AUTHOR]