The deregulated electricity sector needs an improvement in the Available Transfer Capability (ATC) towards the maintenance of power network at balanced condition and to utilize the system in effective manner. Independent System Operator (ISO) maintains the ancillary services by ensuring the reliability of the power system. One of the major functions of ancillary service provider is to maintain the voltage and power flow at stable level. To improve the ATC, both the line power flow and bus voltage profile have to be modified and it is taken care by the ISO. The major limiting criterion for ATC is bus voltage profile. It is well known that the device Thyristor Controlled Series Compensation TCSC which is one of the Flexible AC Transmission System (FACTS) devices can modify the line flow by adjusting the line reactance and Static VAR compensator (SVC) can improve the bus voltage profile by injecting reactive power to the bus. In this research, an Artificial Neural Network (ANN) based estimation of control parameter of FACTS devices such as TCSC and SVC for ATC enhancement is used. The proposed approach uses two different ANN network to find the different TCSC and SVC control parameters to improve the ATC values without violating its voltage constraints for real time transactions. The ANN algorithms such as Radial Basis Function (RBF) as well as Back Propagation Algorithm (BPA) were used to find the TCSC and SVC Parameters and the results are compared. The proposed methods are demonstrated through Reliability Test System (RTS) of IEEE 24 bus. The simulation output represents the suitability of the anticipated method for Real Time estimation of FACTS devices control parameter settings for ATC Enhancement.

放松管制的电力部门需要提高可用传输能力 (ATC)，以将电网维持在平衡状态并有效利用系统。独立系统运营商 (ISO) 通过确保电力系统的可靠性来维护辅助服务。辅助服务提供商的主要功能之一是将电压和潮流保持在稳定水平。为了改进 ATC，必须修改线路潮流和母线电压曲线，这由 ISO 负责。ATC 的主要限制标准是母线电压曲线。众所周知，作为柔性交流输电系统 (FACTS) 设备之一的晶闸管控制串联补偿装置 TCSC 可以通过调整线路电抗来修改线路流量，而静态无功补偿器 (SVC) 可以通过注入来改善总线电压曲线总线的无功功率。在这项研究中，使用基于人工神经网络 (ANN) 的 FACTS 设备（例如 TCSC 和 SVC）的控制参数估计来增强 ATC。所提出的方法使用两个不同的 ANN 网络来找到不同的 TCSC 和 SVC 控制参数，以提高 ATC 值，而不会违反实时事务的电压约束。采用径向基函数（RBF）和反向传播算法（BPA）等人工神经网络算法求解TCSC和SVC参数，并对结果进行比较。所提出的方法通过 IEEE 24 总线的可靠性测试系统 (RTS) 进行了演示。模拟输出代表了用于 ATC 增强的 FACTS 设备控制参数设置的实时估计的预期方法的适用性。