A hybrid approach for enhancing and optimizing the power quality and power flow in Smart Grid Connected System. Issue 2 (20th October 2022)

• Record Type: Journal Article
• Authors: Dsouza, Anil Kumar; T, Ananthapadmanabha; MV, Likith Kumar
• Is Part Of: Systems engineering. Volume 26:Issue 2(2023)
• Page Start: 133
• Page End: 148
• Publication Date: 2022-10-20
• Subjects: active and reactive power variation -- control signal -- DC‐link voltage -- load current -- power flow management -- real and reactive power -- renewable energy sources -- source and load side; Systems engineering -- Periodicals; 620.0011
• DOI: 10.1002/sys.21645
• Languages: English
• ISSNs: 1098-1241

Abstract

Abstract: This article proposes a hybrid approach for power flow management and power quality (PQ) improvement in smart grid (SG) system. The proposed methodology is designed into two phases, power flow management is the first stage and power quality improvement is the second stage of the system. The key purpose of the proposed method is "to regulate that power flow depends on variation of source and load side parameters deliver the highest PQ." The initial phase of power flow management is executed by using Improved Binary Sailfish Optimizer (IBSFO) approach. The control signal is recognized by the IBSFO approach against active and reactive power variation. The second phase of power quality enhancement is implemented by K2ORBFNN, which is the combination of Kho‐Kho optimization (KKO) and Radial Basis Function Neural Network (RBFNN). The gain parameter of the proportional integral (PI) controller is tuned based on load current, DC link, and voltage sources using K2ORBFNN approach. The prediction of optimal control signal minimizes the error which is obtained by RBFNN approach. The proposed method is utilized to attain compensating non‐linear load current harmonics, compensating reactive load power requirement, compensating unbalanced load current with neutral current. Finally, the performance of proposed system is executed in the MATLAB platform and performance is compared with existing techniques. The efficiency under the trails of 100, 200, 500, and 1000 attains 99.1673%, 99.4567%, 99.8402%, and 99.9879%.