INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue X, October 2025

Voltage Stability Assessment Techniques for Enhancing Power

System Stability

¹Sanjay Kannaujiya, ¹Arvind Kumar, ¹Sharad Kumar, ²Vikas Sharma

¹School of Engineering & Technology, Shri Venkateshwara University, Gajraula, U.P. India

²Department of Computer Applications, SRM Institute of Science and Technology, Delhi NCR Campus, Ghaziabad, U.P.

India

DOI: https://doi.org/10.51583/IJLTEMAS.2025.1410000124

Abstract—Voltage stability is a critical aspect of maintaining the reliable operation of modern power systems, particularly with

the increasing integration of renewable energy sources, dynamic loads, and complex grid configurations. This paper presents a

comprehensive analysis of voltage stability assessment techniques aimed at enhancing the overall stability and resilience of power

systems. Various methodologies, including continuation power flow, modal analysis, and time-domain simulation, are explored to

evaluate system performance under different operating conditions. The study emphasizes the identification of weak buses, critical

voltage margins, and potential collapse points to aid in preventive control strategies. Furthermore, the role of advanced

computational intelligence methods such as Artificial Neural Networks (ANN), Fuzzy Logic, and Machine Learning algorithms

in improving predictive accuracy and real-time monitoring is discussed. Comparative results demonstrate the efficiency of hybrid

assessment models in detecting instability precursors and optimizing reactive power compensation. The findings contribute to the

development of more robust voltage stability frameworks, ensuring secure and efficient power system operation in the evolving

energy landscape.

Keywords—Voltage Stability, Power System Stability, Continuation Power Flow, Modal Analysis, Machine Learning, Reactive

Power Compensation, Renewable Integration, Predictive Assessment, Smart Grid, Computational Intelligence.

I. Introduction

The stability of a power system is a fundamental requirement to ensure the continuous and reliable supply of electricity to

consumers. Among the various forms of stability—such as rotor angle stability, frequency stability, and voltage stability—the

latter has emerged as one of the most crucial factors influencing modern power system performance. Voltage stability refers to

the ability of a power system to maintain steady acceptable voltages at all buses under normal operating conditions and after

being subjected to a disturbance. A system is considered voltage unstable when a disturbance, increment in load, or change in

system condition causes a progressive and uncontrollable decline in voltage. Such conditions may lead to voltage collapse,

resulting in partial or complete blackouts, equipment damage, and operational inefficiencies. With the rapid evolution of power

networks due to increasing demand, renewable energy integration, and deregulation of electricity markets, ensuring voltage

stability has become more challenging than ever before. Traditionally, voltage stability issues were confined to heavily loaded

systems operating near their maximum capacity. However, in recent years, the introduction of distributed generation (DG),

intermittent renewable energy sources such as wind and solar, and the widespread use of power electronic converters have

significantly altered system dynamics. These elements introduce nonlinearity and variability, affecting voltage profiles and

reactive power balance within the grid. Moreover, the proliferation of electric vehicles (EVs), microgrids, and smart grid

infrastructures adds additional stress on voltage regulation mechanisms. The uncertainty and fluctuating nature of renewable

generation can lead to voltage instability, particularly in weak grid areas where reactive power support is insufficient. Therefore,

accurate assessment techniques for voltage stability have become indispensable for system operators and planners to ensure grid

reliability and operational security. Over the past decades, several voltage stability assessment (VSA) methods have been

developed to predict, analyze, and mitigate instability phenomena. The most commonly employed techniques include

continuation power flow (CPF), modal analysis, and time-domain simulation. CPF provides valuable insights into system

behavior as loading conditions gradually increase, identifying the maximum load ability point beyond which voltage collapse

occurs. Modal analysis, on the other hand, focuses on the linearized system model to determine the critical modes responsible for

voltage instability, offering an effective way to identify weak buses and regions requiring reactive power compensation. Time-

domain simulation techniques, although computationally intensive, provide a dynamic perspective by modeling system responses

to disturbances over time. These classical methods have been complemented in recent years by advanced computational

intelligence (CI) approaches, such as Artificial Neural Networks (ANN), Fuzzy Logic Systems (FLS), and Machine Learning

(ML) algorithms, which can efficiently handle nonlinearities, uncertainty, and large-scale data typical of modern power networks

shown in Fig. 1. Machine learning-based VSA models, in particular, have gained significant attention due to their ability to learn

from historical data and predict voltage instability conditions in real-time. These models leverage pattern recognition and data-

driven decision-making to identify precursors to voltage collapse before they escalate into critical conditions. Similarly, hybrid

techniques that combine conventional analytical methods with CI-based models have demonstrated improved prediction accuracy

and faster computation times. Such intelligent systems enhance operator situational awareness and enable proactive voltage

control actions, such as optimal placement of reactive power compensators, load shedding, and generation rescheduling. The

deployment of Phasor Measurement Units (PMUs) and Wide Area Measurement Systems (WAMS) has further revolutionized the

www.ijltemas.in

Page 1024

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue X, October 2025

monitoring of voltage stability by providing real-time synchronized data for dynamic assessment. Furthermore, the transition

toward smart grids and sustainable energy systems necessitates the evolution of voltage stability assessment techniques that can

accommodate distributed and renewable-rich environments.

Fig. 1. Modern Voltage Stability Assessment Model

The integration of demand response programs, energy storage systems, and advanced control schemes offers new opportunities to

enhance voltage support and mitigate instability risks. However, this integration also introduces operational complexities that

demand more sophisticated analytical and computational tools. Hence, the development of robust, scalable, and adaptive VSA

techniques remains a key research priority for power system engineers and researchers. In this paper, various voltage stability

assessment methods are reviewed and analysed, emphasizing their applicability, computational efficiency, and suitability for

different grid configurations. The comparative evaluation of traditional and modern approaches highlights the strengths and

limitations of each technique in addressing voltage instability challenges. The study also explores the incorporation of intelligent

algorithms for predictive voltage stability analysis, offering a pathway toward resilient and adaptive power systems capable of

withstanding future uncertainties. Ultimately, the paper aims to contribute to the ongoing efforts in developing effective strategies

for maintaining voltage stability, ensuring reliable and efficient operation of power systems in an increasingly dynamic and

complex energy landscape.

II. Literature Review

Recent advancements in intelligent power systems have driven a paradigm shift in how stability, reliability, and security are

managed through artificial intelligence (AI), optimization, and smart grid technologies. Researchers have explored multiple aspects

of machine learning (ML), distributed generation (DG), and grid-forming controls to address challenges in transient stability,

voltage regulation, and intrusion detection in smart energy systems. Song et al. [1] presented a machine learning-based approach

for enhancing power system stability using Support Vector Machines (SVM), Random Forest, and deep learning models trained on

wide-area measurement data. Their study emphasized the predictive accuracy of AI techniques in identifying early instability

patterns. Complementing this, Chavan et al. [2] conducted a transient stability analysis on IEEE test systems to understand the

dynamic response of generators under disturbances. Zhang et al. [3] expanded this scope by studying the influence of Virtual

Synchronous Generators (VSGs) on transient stability, demonstrating that virtual inertia can significantly improve grid resilience

against frequency fluctuations. In continuation, Ćosić and Vokony [4] explored AI-driven approaches for grid stability monitoring,

focusing on predictive models for real-time assessment of system reliability. Similarly, Ali et al. [5] investigated the stability of

inverter-based resources (IBRs) through grid-forming inverter control within load frequency control (LFC) systems, showing that

grid-forming techniques enhance synchronization and reduce oscillations. Beyond traditional stability assessment, Sharma and

Kumar [6] discussed how AI contributes to enhancing data security and privacy in smart city infrastructures. Their findings

underscore the importance of intelligent systems not only for operational efficiency but also for safeguarding information within

interconnected grids. This aligns with the work of Vikas et al. [7], who developed a hybrid Deep Belief Network (DBN) combined

with the Harris Hawks Optimizer (HHO) for intrusion detection in wireless sensor networks, improving anomaly detection

accuracy in energy communication systems. From a sustainability standpoint, Sungheetha et al. [8] proposed an AI-driven

neuromorphic system for integrating sustainable marine energy into power grids, addressing both stability and environmental goals.

Parallel to this, recent work on optimizing Graph Neural Networks (GNNs) [9] has demonstrated the potential for real-time

intrusion detection in dynamic mobile ad-hoc networks, which can be applied to decentralized power communication frameworks.

In the domain of distributed generation (DG), Gupta et al. [10] assessed the technical impact of integrating multiple DG types into

distribution systems, revealing the improvements in voltage profiles and reduction in losses. Kiran and Devaraju [11] introduced

adaptive power system security enhancement using machine learning and soft computing, showcasing intelligent adaptability in

www.ijltemas.in

Page 1025

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue X, October 2025

operational conditions. Similarly, Alanzi et al. [12] optimized power system performance using an Optimal Power Flow (OPF)

framework considering voltage-dependent load models and distributed generators, improving efficiency and load balancing.

Rukonuzzaman and Mahboob [13] introduced a novel approach for zero-crossing voltage detection, enabling precise

synchronization in distributed power systems. Jeeva et al. [14] applied the Harris Hawks Optimizer to minimize power losses

through the integration of biomass-based renewable distributed generators (RDGs) in radial systems, demonstrating AI’s potential

in green energy management. On the cybersecurity front, studies such as [15] have comprehensively analysed threat

characterization and security mechanisms in mobile ad hoc networks (MANETs), contributing insights applicable to smart grid

communication layers. Finally, Bais et al. [16] explored advanced techniques for high voltage detection to enhance operational

safety in extra-high voltage systems, emphasizing sensor-based and AI-assisted detection mechanisms for improved fault

prevention. Collectively, these studies reveal that integrating AI, machine learning, and optimization algorithms has revolutionized

the assessment and enhancement of power system stability, distributed generation control, and security. The convergence of

intelligent analytics, renewable integration, and cyber-resilient designs lays a strong foundation for the next generation of smart and

sustainable power networks.

III. Proposed Methodology

The proposed methodology aims to develop a comprehensive Voltage Stability Assessment (VSA) framework that enhances the

stability and reliability of modern power systems under dynamic and uncertain conditions. This framework integrates traditional

analytical techniques with advanced computational intelligence models to provide accurate, real-time predictions of voltage

instability. The hybrid design leverages Continuation Power Flow (CPF), Modal Analysis, and Machine Learning (ML) to assess

system behavior, identify weak buses, and recommend corrective actions before voltage collapse occurs. The hardware

requirements for implementing the proposed methodology include a high-performance computing environment equipped with at

least an Intel Core i7 or higher processor, 16 GB or more RAM, and a 512 GB SSD for efficient data handling and simulation.

Although a GPU is optional, it can significantly accelerate training and prediction processes in machine learning-based models.

The system should operate on a stable platform such as Windows 10 or Linux Ubuntu 20.04, both of which support the necessary

simulation and programming tools. The software requirements comprise specialized tools and environments for power system

simulation, data analysis, and model development. MATLAB/Simulink is utilized for power flow and dynamic stability

simulations, while Power World Simulator or PSAT (Power System Analysis Toolbox) assists in network modeling and

visualization. For machine learning implementation, Python is used with essential libraries like Scikit-learn, TensorFlow,

and PyTorch for algorithm training and validation. Additionally, Microsoft Excel or CSV-based data logs are employed for data

preprocessing and feature extraction. These requirements ensure seamless integration between analytical and AI-driven modules

in the hybrid voltage stability framework. To validate the proposed approach, the framework is tested on standard IEEE

benchmark systems, which serve as representative models for practical grid conditions. A sample test case is conducted on

the IEEE 14-bus test system, a well-known network used for voltage stability studies. In this scenario, the load at Bus 4 is

increased by 20%, while the reactive power limit at Generator Bus 2 is constrained to 40 MVAR, simulating a high-stress

condition within the network. The line impedance between Bus 4 and Bus 5 is set at 0.02 + j0.06 pu to represent realistic

transmission constraints. Upon executing the simulation, the proposed model identifies Bus 4 and Bus 5 as weak nodes,

indicating their critical role in voltage instability. The minimum eigenvalue (λ_min) derived from modal analysis is found to

be 0.045, signaling a system operating close to instability. The voltage magnitude at Bus 4 drops to 0.89 pu, which falls below the

acceptable voltage threshold, confirming the potential risk of collapse. The integrated machine learning model, trained on

historical stability data, predicts a “Voltage Instability Likely” condition, validating the analytical findings. As a corrective

measure, the system suggests installing a Static VAR Compensator (SVC) at Bus 5 with a 50 MVAR capacity to restore voltage

levels and enhance the stability margin.

The proposed VSA framework consists of the following major stages:

1. Data Acquisition and Preprocessing:

The process begins with collecting real-time and historical data from the power system network. Essential parameters include bus

voltages, power flows, load levels, reactive power generation, and system topology. Data are acquired through Supervisory

Control and Data Acquisition (SCADA) systems, Phasor Measurement Units (PMUs), or simulation environments such as

MATLAB/Simulink or Power World Simulator.

2. Power Flow Analysis and Voltage Profile Evaluation:

Load flow analysis is performed using the Newton–Raphson or Fast Decoupled Power Flow method to determine the steady-state

voltage profile across all buses. This step identifies weak nodes with low voltage magnitudes or poor reactive power support.

The Continuation Power Flow (CPF) technique is then applied to trace the system’s load-voltage curve and determine the

maximum loading point (nose point) beyond which voltage collapse occurs.

3. Modal Analysis for Critical Bus Identification: In this stage, the system’s Jacobian matrix is linearized, and eigenvalue

analysis is conducted to identify critical modes associated with voltage instability. The participation factors corresponding to each

mode are analysed to determine which buses or areas contribute most to instability. This step helps in prioritizing locations for

reactive power compensation or voltage control devices.

www.ijltemas.in

Page 1026

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue X, October 2025

4. Machine Learning-Based Predictive Modeling:

To enhance the prediction and monitoring capabilities, a Machine Learning (ML) model such as Artificial Neural Network

(ANN), Support Vector Machine (SVM), or Random Forest (RF) is integrated into the framework. The ML model is trained

using labelled datasets that include input parameters (e.g., voltage magnitudes, active/reactive power, line impedances) and output

labels (stable/unstable). The trained model can predict voltage instability conditions in real-time, reducing computation time

compared to iterative numerical methods.

5. Hybrid Optimization and Control Strategy:

Once instability-prone regions are detected, the framework applies optimization techniques (such as Particle Swarm Optimization

(PSO) or Genetic Algorithm (GA)) to determine the optimal placement and sizing of reactive power compensators like Static

VAR Compensators (SVC), STATCOMs, or capacitor banks.

6. Validation and Performance Evaluation:

The proposed system is validated using standard IEEE test systems such as IEEE 14-bus, IEEE 30-bus, and IEEE 57-

bus networks. Performance metrics such as voltage deviation, voltage stability margin (VSM), and computation time are used to

compare the hybrid approach with conventional techniques. The results demonstrate improved prediction accuracy, faster

convergence, and enhanced robustness under varying system disturbances and load conditions.

IV. Result & Analysis

The proposed hybrid Voltage Stability Assessment (VSA) framework was tested and evaluated using standard IEEE test systems

(IEEE 14-bus, IEEE 30-bus, and IEEE 57-bus) to analyze its performance in identifying and mitigating voltage instability. The

results demonstrate that the integration of analytical methods (CPF and Modal Analysis) with Machine Learning-based predictive

modeling significantly enhances accuracy, reduces computational time, and improves the overall voltage stability margin (VSM).

1. Comparative Analysis of VSM across Test Systems: The Voltage Stability Margin was computed for three IEEE systems

under both traditional CPF-based assessment and the proposed hybrid model.

Comparison of Voltage Stability Margin

Test System

Traditional CPF-Based

VSM (pu)

Proposed Hybrid

VSM (pu)

Improvement (%)

29.12%

IEEE 14-Bus

0.182

0.235

0.214

0.198

IEEE 30-Bus

IEEE 57-Bus

0.156

0.141

37.17%

40.42%

Table I. shows the results reveal that the proposed model significantly improves the Voltage Stability Margin for all test systems.

The improvement ranges from 29% to 40%, proving the efficiency of integrating computational intelligence with traditional

assessment techniques.

Fig. 2. Comparison of Voltage Stability Margin

Fig. 2. comparing the Voltage Stability Margin (VSM) of traditional CPF-based methods and the proposed hybrid model across

IEEE 14, 30, and 57-bus systems, showing higher VSM for the hybrid model.

2. Voltage Deviation Reduction Analysis: Voltage deviation was assessed before and after applying the optimized reactive

power compensation strategy.

www.ijltemas.in

Page 1027

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue X, October 2025

Comparison of Average Voltage Deviation (VD) Before and After Reactive Power Compensation

Bus System

Average VD Before

Compensation (pu)

Average VD After

Compensation (pu)

Reduction (%)

IEEE 14-Bus

0.092

0.046

50.00%

IEEE 30-Bus

IEEE 57-Bus

0.085

0.078

0.041

0.037

51.76%

52.56%

Table II. shows a considerable reduction in voltage deviation, indicating improved voltage regulation across the grid. The hybrid

model’s optimization algorithm effectively allocates reactive power resources to critical buses, enhancing voltage uniformity.

Fig. 3. Comparison of Average Voltage Deviation Before and After Reactive Power Compensation

Fig. 3. showing the reduction in average voltage deviation before and after reactive power compensation across IEEE 14, 30, and

57-bus systems, highlighting improved stability.

3. Machine Learning Model Performance: The performance of the ML-based predictive model (using Random Forest and

ANN) was evaluated using key classification metrics:

Performance Comparison of Different Machine Learning Models for Voltage Stability Prediction

Model

Accuracy (%)

Precision (%)

95.8

Recall (%)

94.7

F1-Score (%)

95.2

RMSE

0.024

Random Forest 96.2

Artificial NN

SVM

94.6

91.8

93.5

90.2

93.1

89.6

93.3

89.9

0.028

0.032

The Random Forest model achieved the highest prediction accuracy (96.2%), outperforming ANN, and SVM shown in TABLE

III. This demonstrates the proposed model’s robustness in predicting potential voltage instability scenarios with minimal error,

ensuring faster and more reliable decision-making.

Fig. 4. Performance Comparison of Different Machine Learning Models for Voltage Stability Prediction

www.ijltemas.in

Page 1028

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue X, October 2025

Fig. 4. comparing prediction accuracy, precision, recall, and F1-score of Random Forest, ANN, and SVM models, showing

Random Forest achieving the highest overall performance.

4. Computation Time Comparison: The hybrid model was also evaluated for computational efficiency against traditional CPF

methods.

Comparative Analysis of Computation Time between CPF and Proposed Hybrid Methods

Test System

IEEE 14-Bus

CPF Method (sec)

Proposed Hybrid (sec)

Reduction (%)

41.93%

12.4

18.9

26.5

7.2

IEEE 30-Bus

IEEE 57-Bus

10.1

14.3

46.56%

46.03%

The computation time was reduced by approximately 40–46% across all systems due to the incorporation of ML models that

eliminate repetitive power flow iterations is illustrated in TABLE IV. This improvement makes the framework suitable for real-

time monitoring and control in smart grids.

Fig. 5. Comparative Analysis of Computation Time Between CPF and Proposed Hybrid Methods

Fig. 5. illustrating computation time comparison between traditional CPF and proposed hybrid models across different IEEE test

systems, highlighting substantial time reduction in the hybrid model.

5. Reactive Power Compensation Efficiency: Reactive Power Compensation Efficiency (RPCE) measures how effectively the

compensators maintain voltage levels under increased load conditions.

Reactive Power Control Effectiveness (RPCE)

Test System

IEEE 14-Bus

RPCE (%)

93.6

92.8

91.4

IEEE 30-Bus

IEEE 57-Bus

High RPCE values across all systems indicate that the optimized placement of devices like SVC and STATCOM significantly

improved voltage levels and system reliability shown in TABLE V.

Fig. 6. Reactive Power Control Effectiveness (RPCE)

www.ijltemas.in

Page 1029

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue X, October 2025

Fig. 6. showing Reactive Power Compensation Efficiency (RPCE) for IEEE 14, 30, and 57-bus systems, with all values above

90%, indicating strong compensation performance.

V. Conclusion

This study provides a comprehensive analysis of voltage stability assessment techniques that enhance the reliability and resilience

of modern power systems. By comparing traditional methods such as continuation power flow, modal analysis, and time-domain

simulation with advanced computational intelligence approaches like Artificial Neural Networks, Fuzzy Logic, and Machine

Learning, the research demonstrates that hybrid assessment models significantly improve predictive accuracy, reduce

computation time, and optimize reactive power compensation. The proposed framework effectively identifies weak buses, critical

voltage margins, and instability precursors, leading to improved voltage stability margins and higher reactive power control

effectiveness. The results emphasize that integrating artificial intelligence with classical stability assessment offers a robust and

adaptive approach for maintaining system stability in increasingly complex and renewable-integrated grids. Future research can

focus on extending these hybrid models for real-time stability monitoring, incorporating edge computing and IoT-based sensing,

and developing self-learning algorithms that can autonomously predict and mitigate voltage instability in large-scale smart grid

environments.

References

1. C. Song, M. Tan, M. Chu, C. Zhou, G. Tian and L. Mu, "Enhancing Power System Stability: A Machine Learning

Approach with SVM, Random Forest and Deep Learning Utilizing Wide Area Measurements," 2024 IEEE 7th Student

Conference on Electric Machines and Systems (SCEMS), Macao, Macao, 2024, pp. 1-5, doi:

10.1109/SCEMS63294.2024.10756409.

2. K. Chavan, G. B. Patil and R. More, "Transient Stability Analysis of IEEE Test System," 2024 IEEE International

Conference for Women in Innovation, Technology & Entrepreneurship (ICWITE), Bangalore, India, 2024, pp. 691-695,

doi: 10.1109/ICWITE59797.2024.10502535.

3. H. Zhang, Y. Xu and Z. Dong, "Impact Study of Virtual Synchronous Generators on Power System Transient

Stability," 2024 IEEE Power & Energy Society General Meeting (PESGM), Seattle, WA, USA, 2024, pp. 1-5, doi:

10.1109/PESGM51994.2024.10688515.

4. S. Ćosić and I. Vokony, "Advancements in AI-Driven Approaches for Grid Stability Monitoring," 2025 10th

International Youth Conference on Energy (IYCE), Budapest, Hungary, 2025, pp. 1-7, doi:

10.1109/IYCE66046.2025.11155020.

5. M. Ali, A. Rahman and S. Sharif, "Stability Assessment of an IBR-based LFC System Using Grid-Forming (GFM)

Inverter Control," 2025 IEEE North-East India International Energy Conversion Conference and Exhibition (NE-

IECCE), Silchar, India, 2025, pp. 1-6, doi: 10.1109/NE-IECCE64154.2025.11183312.

6. V. Sharma and S. Kumar, "Role of Artificial Intelligence (AI) to Enhance the Security and Privacy of Data in Smart

Cities," 2023 3rd International Conference on Advance Computing and Innovative Technologies in Engineering

(ICACITE), Greater Noida, India, 2023, pp. 596-599, doi: 10.1109/ICACITE57410.2023.10182455.

7. Vikas, R. P. Daund, D. Kumar, P. Charan, R. S. K. Ingilela and R. Rastogi, "Intrusion Detection in Wireless Sensor

Networks using Hybrid Deep Belief Networks and Harris Hawks Optimizer," 2023 4th International Conference on

Electronics and Sustainable Communication Systems (ICESC), Coimbatore, India, 2023, pp. 1631-1636, doi:

10.1109/ICESC57686.2023.10193270.

8. A. Sungheetha, R. S. R., S. Mahapatra, N. Agrawal, G. S. P. Ghantasala and T. Singh, "AI-Driven Neuromorphic

System for Sustainable Marine Energy Integration and Power System Stability Enhancement," 2025 12th International

Conference on Computing for Sustainable Global Development (INDIACom), Delhi, India, 2025, pp. 1-6, doi:

10.23919/INDIACom66777.2025.11115445.

9. Optimization of Graph Neural Networks for Real-Time Intrusion Detection in Dynamic Mobile Ad-Hoc Networks”, Int.

J. Environ. Sci., vol. 11, no. 11s, pp. 740–748, Jun. 2025, doi: 10.64252/79452g17.

10. B. Gupta, S. K. Sudabattula, S. Mishra and N. Dharavat, "Techno Assessment of Distribution System with Integration of

Different Types of Distributed Generators," 2024 International Conference on Sustainable Power & Energy (ICSPE),

Raigarh, India, 2024, pp. 1-6, doi: 10.1109/ICSPE62629.2024.10924378.

11. K. Kiran and T. Devaraju, "Adaptive Power System Security Enhancement Using Machine Learning and Soft

Computing," 2025 International Conference on Computing Technologies (ICOCT), Bengaluru, India, 2025, pp. 1-7, doi:

10.1109/ICOCT64433.2025.11118437.

12. S. S. Alanzi, R. M. Kamel and M. Hashem, "Optimal Performance of Power System Using an Optimal Power Flow

Along with Optimal Inclusion of Distributed Generators Considering Voltage-Dependent Load Models," 2024 IEEE

Sustainable Power and Energy Conference (iSPEC), Kuching, Sarawak, Malaysia, 2024, pp. 209-214, doi:

10.1109/iSPEC59716.2024.10892481.

13. M. Rukonuzzaman and M. Mahboob, "A Simple Approach to Zero Crossing Detection of Voltage and its Application in

Distributed Power Supply," 2025 4th International Conference on Robotics, Electrical and Signal Processing Techniques

(ICREST), Dhaka, Bangladesh, 2025, pp. 117-122, doi: 10.1109/ICREST63960.2025.10914435.

www.ijltemas.in

Page 1030