Salp swarm algorithm and phasor measurement unit based hybrid robust neural network model for online monitoring of voltage stability

• Published in: Wireless networks Vol. 27; no. 2; pp. 843 - 860
• Main Authors: Nageswara Rao, A., Vijayapriya, P.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.02.2021; Springer Nature B.V
• Subjects: Algorithms; Artificial neural networks; Communications Engineering; Computer Communication Networks; Electric power systems; Electrical Engineering; Engineering; IT in Business; Learning theory; Measuring instruments; Monitoring; Networks; Neural networks; Phasors; Stability analysis; Testing time; Voltage stability; Wireless networks; Voltage stability monitoring index (VSMI); Artificial neural network (ANN); Salp swarm algorithm (SSA); Phasor measurement units (PMU)
• ISSN: 1022-0038; 1572-8196
• DOI: 10.1007/s11276-019-02161-w

Incessant assessment of voltage stability is lively aspect to safeguard the electrical power system operation. The traditional methods for online assessment in terms of voltage stability analysis are extremely time consuming and also difficult for supervising it in online. In connection to this a novel model based on Salp swarm algorithm and artificial neural network (SSA–ANN) is considered for online monitoring of voltage stability in this manuscript. As we know that ANN is an influential and promising predictive tool to attain the efficacy and accuracy in terms of training and testing time. The input for model is the PMU data and the output for the model is voltage stability margin index which is used for voltage stability monitoring. SSA is used for tuning the Meta parameters such as the activation functions and number of nodes along with the learning rate. The solution method opted for this stability monitoring utilises the magnitude of voltage and its corresponding phase angle which are attained from the PMU as the inputs to the neural network model. The efficiency of the proposed model is verified by means of various test cases and compared with the same data set to attest it’s pre-eminence.