Research Article

Intelligent Integrated Approach for Voltage Balancing Using Particle Swarm Optimization and Predictive Models

Table 5

A comparison between the proposed PSO technique and other techniques.

Comparison criteriaWork in [18] published in 2023Work in [13] published in 2023Work in [28] published in 2020Work in [33] published in 2020Work in [30] published in 2019The proposed approachNotes

Power compensatorCVSR3ph-CHB multilevel converterTCRTSC-TCRTCRTCRThe majority of these researches utilized TCR to solve the problem of unbalanced voltages
AlgorithmRegulating the bias dc circuits of CVSR. The ac reactance was adjusted based on the B-H of the core. The generated dc bias magnetic flux is used to balance the three-phase voltagesDecoupling coordinates transformation to design three loops, a current tracking loop, a voltage regulation loop, and a voltage balance loopPSOTriangular membership functionThe firing angles of the TCR required to retrieve the system balance conditions were determined by trial and errorPSOThe proposed PSO algorithm uses the mathematical model of the power system to determine the required set of TCR firing angles. Thus, it is more accurate compared to the ones in [28, 30]. Additionally, this operation is performed offline which make the proposed approach faster than the one proposed in [13, 18]
ControllerIterative process depending on measuring the load voltages, searching for the dc biases, and calculating the relative error between the voltagesModel based PI and PR closed loop controllerANNFuzzy logicANNGPR and SVMSVM and GPR have the upper hand over the ANN in regression. They give higher accuracy and consume less time comparable to sophisticated ANN with elaborated features in regression tasks
VUF range<5%Undefined3.44–6.93%Undefined3.48–4.68%3.90–8.42%The proposed approach covers a wider range of VUF
Average response time (at 50 Hz)>60 ms>200 ms57.92 ms>43 ms60 ms20 msThe response time of the proposed approach is the shortest time with just 20 ms