A Unified Intelligent Framework for Economic Load Dispatch and Real-Time Transient Stability Monitoring in the IEEE 39-Bus Power System Using Genetic Algorithm and Artificial Neural Network

Subject Areas : Artificial Intelligence

Masih Sobhani ¹ , Azadeh Zarif Loloei ² , Amir Haghverdi ³

1 -
2 - Department of Electrical Engineering, Par.C, Islamic Azad University, Tehran, Iran
3 - Department of Electrical Engineering, Par.C, Islamic Azad University, Tehran, Iran

Received: 2025-11-05 Accepted : 2025-11-06 Published : 2025-11-14

Keywords: Economic Load Dispatch, Transient Stability, Genetic Algorithm, Artificial Neural Network, Power System Optimization. ,

Abstract :

This paper presents a unified intelligent framework that simultaneously optimizes economic operation and enables real-time transient stability monitoring in the IEEE 39-bus power system. A Genetic Algorithm is employed for Economic Load Dispatch, minimizing fuel costs to $51,972.58 per hour under a 6150 MW demand, yielding a 4.8% reduction ($22.14 million annually) compared to conventional lambda-iteration methods ($54,500/h). The GA’s global convergence in non-convex cost landscapes is theoretically analyzed using the Schema Theorem and Markov chain dynamics, ensuring robust handling of quadratic cost functions and transmission losses. For transient stability, a lightweight feedforward Artificial Neural Network with 20 input neurons (rotor angles and bus voltages), two hidden layers (10 and 5 neurons), and one output neuron predicts system synchronism with 92% accuracy across 40 test scenarios, computing stability margins from -75.07° to 59.33°. Compared to time-domain simulations (5–10 s/scenario, ~85% accuracy), the ANN delivers near-instantaneous predictions. A comprehensive review of hybrid intelligent methods (2023–2025) positions this work as a bridge between decoupled optimization and stability paradigms. Integration challenges with Phasor Measurement Units including latency, noise, topology changes, and cyber threats are rigorously discussed, with practical solutions such as denoising autoencoders and transfer learning proposed for field deployment. The GA-ANN synergy preconditions optimal dispatch for stability forecasting, offering a scalable pathway for smart grid Energy Management Systems. Future enhancements include regression-based ANN, PMU-driven online retraining, and hybrid physics-informed models to further enhance reliability in dynamic, renewable-rich grids.

References:

[1] Bills, G W. "On-line stability analysis study, RP 90-1." , Oct. 1970..
[2] M. A. Pai, Energy Function Analysis for Power System Stability, Kluwer Academic Publishers, 1989.
[3] A. J. Wood and B. F. Wollenberg, Power Generation, Operation, and Control, Wiley, 1984.
[4] C. E. Fosha and O. I. Elgerd, "The megawatt-frequency control problem: A new approach via optimal control theory," IEEE Transactions on Power Apparatus and Systems, vol. PAS-89, no. 4, 1970.
[5] J. H. Holland, Adaptation in Natural and Artificial Systems, University of Michigan Press, 1975.
[6] Kavita Borana, “Genetic Algorithms And Its Application To Economic Load Dispatch,” AIP Conf. Proc. 1324, 239–243, 2010.
[7] Mamdouh El Haj Assad, Mohammad Alhuyi Nazari, Mehdi A. Ehyaei and Marc A. Rosen, “Design and Performance Optimization of Renewable Energy System,” January 2021
[8] Mehdi A. Ehyaei, Mojtaba Tahani, Pouria Ahmadi, Mohammad Esfandiari, “Optimization of fog inlet air cooling system for combined cycle power plants using genetic algorithm,” Applied Thermal Engineering, Volume 76, , Pages 449-461, 5 February 2015.
[9] P. Kundur, Power System Stability and Control, McGraw-Hill, 1994.
[10] P. M. Anderson and A. A. Fouad, Power System Control and Stability, IEEE Press, 1977.
[11] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning representations by back-propagating errors," Nature, vol. 323, 1986.
[12] Tayo Badrudeen, Nnamdi Nwulu, Saheed Lekan GbadamosiSaheed, “Neural Network Based Approach for Steady-State Stability Assessment of Power Systems,” Sustainability 15(2):1667, January 2023.
[13] Utkarsh Pandey, Anshumaan Pathak, Adesh Kumar and Surajit Mondal, “Applications of artificial intelligence in power system operation, control and planning: a review,” Clean Energy, 2023
[14] Vijay Kumar, Jagdev Singh, Yaduvir Singh and Sanjay Sood, “Optimal Economic Load Dispatch Using Genetic Algorithms.” International Journal of Electrical, Electronic and Communication Sciences, ISSN: 2517-9438,Vol:9, No:4, 2015.
[15] Milena Ramos, “Neural Networks to Transient Stability Analysis of Electrical Power Systems” Proceedings of the V Brazilian Conference on Neural Networks, 2016.
[16] J. Machowski, J. W. Bialek, and J. R. Bumby, Power System Dynamics: Stability and Control, Wiley, 2008.
[17] Bishnu Sahu, Avipsa Lall, Soumya Das and T. Manoj Kumar Patra, “Economic Load Dispatch in Power System using Genetic Algorithm.” International Journal of Computer Applications 67(7):17-22, April 2013.
[18] Dragan Kukolj, Dragan A. Popovic, “Fast dynamic stability analysis of a power system using artificial neural networks.” European Transactions on Electrical Power, May 2007
[19] U. Pandey, A. Pathak, A. Kumar, and S. Mondal, “Applications of artificial intelligence in power system operation, control and planning: a review,” Clean Energy, vol. 7, no. 4, pp. 729–743, 2023.
[20] Mikail Purlu & Belgin Emre Turkay, “Dynamic Economic Dispatch with Valve Point Effect by Using GA and PSO Algorithm,” Conference: 2018 6th International Conference on Control Engineering & Information Technology (CEIT), 2018.
[21] Ying-Yi Hong and Hao Zeng, “Decentralized Multi-Area Economic Dispatch in Power Systems Using the Consensus Algorithm,” Energies 2024,17, 3609.
[22] Izzuddin Fathin Azhar, Lesnanto Multa Putranto, Roni Irnawan, “Development of PMU-Based Transient Stability Detection Methods Using CNN-LSTM Considering Time Series Data Measurement,” Energies . Power Syst., Vol. 15, no. 21, p. 8241, Nov 2022.
[23] Xuezao Wang.,et al, “Fast Critical Clearing Time Calculation for Power Systems with Synchronous and Asynchronous Generation,” March 2025. [24] Stavros Adam., et al. Macready, “No Free Lunch Theorem: A Review,” May 2019.
[25] H. Mühlenbein and D. Schlierkamp-Voosen, “Predictive models for the breeder genetic algorithm I. Continuous parameter optimization,” Evol. Comput., vol. 1, no. 1, pp. 25–49, 1993.
[26] Carleton Coffrin & Line Roald. “Convex Relaxations in Power System Optimization: A Brief Introduction,” IEEE Trans. Power Syst., vol. 34, no. 3, pp. 2221–2231, May 2019.
[27] A. G. Phadke and J. S. Thorp, Synchronized Phasor Measurements and Their Applications, 2nd ed. Springer, 2017.
[28] K. E. Martin., et al, “Synchrophasor Measurements Under the IEEE Standard C37.118.1-2011 With Amendment C37.118.1a,” IEEE Trans. Power Del., vol. 30, no. 3, pp. 1314–1322, Jun. 2015.
[29] Luigi Vanfretti & Joe H. Chow, “Real-time synchrophasor data interpolation and cleansing for wide-area monitoring,” Conference: 17th Power Systems Computation Conference (PSCC), Stockholm, Sweden, 2011.
[30] H. M. Khalid and J. C.-H. Peng, “Immunity toward data-injection attacks in smart grids with variable measurement sampling rates,” IEEE Trans. Smart Grid, vol. 11, no. 2, pp. 1205–1216, Mar. 2020.
[31] Y. Liu, Y. Sun, and P. Zhang, “Transient Stability Assessment Using Deep Transfer Learning,” IEEE Access, . PP(99):1-1 2023.
[32] Y. Liu, P. Ning, and M. K. Reiter, “False data injection attacks against state estimation in electric power grids,” ACM Trans. Inf. Syst. Secur., vol. 14, no. 1, pp. 1–33, Jun. 2011.