Page 767

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue III, March 2026

Improving Network Efficiency Through an Energy-Aware

Geographic Routing Protocol

Rohitendra Kushwah

, Savan Payasi

, Akhilesh A. Waoo

Rohitendra Kushwah Department of Computer Science, AKS University, SATNA, M.P., India

Savan Payasi

Department of Computer Science, AKS University, SATNA, M.P., India

Akhilesh A. Waoo Department of Computer Science, AKS University, SATNA, M.P., India

DOI:

https://doi.org/10.51583/IJLTEMAS.2026.150300063

Received: 26 March 2026; Accepted: 31 March 2026; Published: 14 April 2026

ABSTRACT

Although wireless sensor networks (WSNs) are crucial parts of modern communication systems, their energy

consumption and network longevity are severely constrained. Enhancements to the geographic and energy-

efficient routing protocol (GF-EERP) are suggested in this study. This we do by use of precise node location

info which in turn improves routing decisions.

The protocol will also incorporate reinforcement learning algorithms. To make adaptive routing techniques

possible, which improve network efficiency and accomplish balanced traffic distribution. On a number of

performance metrics, including latency, packet delivery ratio, network lifetime, and energy consumption, the

suggested approach will be carefully contrasted and examined with alternative routing methods. The simulation

results will demonstrate that, in a variety of network circumstances, the enhanced GF-EERP will offer superior

scalability and reliability compared to the current protocols. In order to enhance energy-efficient

communications in WSNs and, consequently, guarantee dependable and sustainable network deployment, this

study will highlight the significance of combining geographic routing with machine learning techniques.

Keywords: Energy Efficiency, GF-EERP, Geographic Routing Protocol, Network Lifetime, Node Localization,

Reinforcement Learning, Traffic Balancing, Wireless Sensor Networks.

INTRODUCTION

WSNs are used for real-time data collection in many fields. That energy is the great issue [1]. Geographic and

Energy-Aware Routing Protocols, such as GF-EERP, have been developed to use remaining energy and node

location to achieve optimum energy efficiency [2]. Unfortunately, load imbalance and wasteful route discovery

plague current methods. Traffic balance and responsiveness to shifting network conditions can be effectively

addressed by using Reinforcement Learning (RL) [3]. By way of less redundant transmissions and better energy

conservation, Reinforcement Learning based routing develops smart paths [4]. An enhanced GF-EERP protocol

is presented in this study, which uses RL mechanisms and node location to guarantee effective routing. In order

to address some of the shortcomings of current models, the suggested protocol seeks to increase the network

lifetime and overall performance [5].

Objective And Related Work

Recent research focusing on enhancing routing protocol effectiveness in wireless sensor networks through the

utilization of node location to save energy and extend network lifetime is comparable. In addition, they include

research employing reinforcement learning algorithms to balance network traffic, make more effective routing

decisions, and react to changing situations. Also, recent research involves testing and comparing various

Page 768

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue III, March 2026

protocols on the basis of key performance factors such as energy consumption, latency, throughput, and packet

delivery ratio to establish a benchmark for measuring innovative approaches.

LITERATURE REVIEW

To improve overall performance and network lifetime, which in turn mitigates some of the drawbacks of present

solutions [5]. The performance will be compared to current protocols using criteria such as energy usage, packet

delivery ratio, and network lifetime. (Bairagi et al., 2024). For large-scale WSNs, Karthigeya S.'s paper suggests

a hybrid wireless sensor network communication protocol that will increase the network's lifespan and energy

efficiency. Optimal control packet sizes and improved cluster head (CH) selection metrics can further optimize

the protocol, which compromises practicality and performance. (Karthigeyan et al., 2025).

Wireless Sensor Networks (WSNs), as reported by Al-Healy, are a revolutionary technology for the perception

and interaction of the physical world. In terms of performance, AODV is dynamic, GPSR is very scalable, and

PEGASIS and LEACH are energy efficient. (Al-Healy and Ibrahim, 2025). Yajadda, which presents a routing

that dynamically deals with network congestion via the use of shortest path algorithms along with reinforcement

and Q-learning. It is fit for what is to come in network administration and also puts forth itself in many network

settings. (Yajadda and Safaei, 2023).

Arunkumar et al. (2022) outline an energy-efficient and secure routing algorithm in their patent for Mobile Ad-

hoc Networks (MANETs) by integrating Artificial Intelligence (AI) with Internet of Things (IoT) technologies.

It focuses on optimizing data paths to minimize power consumption while ensuring the network remains

protected against potential security threats.

Abujassar is that due to resource and connection reliability issues, effective data management is a must in the

age of Internet of Things and Low Power and Lossy Networks (LLNs). (Abujassar, 2024). (Abujassar, 2024).

Alhihi reports that WSNs are made up of low-cost, low-power nodes that collect and forward environmental data

for health care, disaster monitoring, and other uses. (Alhihi, 2017).

The presented Taylor C-SSA algorithm, which puts together the Taylor series, Cat Swarm Optimization, and

Salp Swarm Algorithm, forms the base of the security-focused multi-hop routing. (Vinitha and Rukmini, 2022).

In the field of Person Re-Identification, which is a great computer vision issue for smart cities and security in

Boujou, there are barriers to this, including the change in lighting, busy background settings, and people who

are covered by others, who also have similar looks and dynamic settings. (Boujou et al., 2024). As for the

Mustafa report, the routing protocols that are put forth are useful for network communication as they do the job

of path selection and data delivery. (Mustafa and Abaker, 2024).

IoT-based Quantum Wireless Sensor Networks (Q-WSNs), according to Ramkumar, integrate IoT and quantum

computing to provide end-to-end communication and information processing capabilities. (Ramkumar et al.,

2024). Wang and Xing say the proposed QTGrid (quad tree grid) protocol enhances the network by partitioning

the area to be sensed into clusters, using the least energy possible, and using spatial queries to the best effect.

(Wang et al., 2019).

An energy-efficient geographic routing protocol (GRP) uses position sensing to determine the shortest path for

data transfer, improving network performance. (Sharma and Agarwal, 2023). By using the coordinates of nearby

nodes to the base station (BS), Redjimi, and the recommended geographical routing algorithm for Wireless

Sensor Networks (WSNs), maximizes network efficiency and minimizes energy waste during data transmission.

(Redjimi et al., 2021). Luo reported that the GEBOR protocol, which they put forth, used geographic location

and energy as parameters to achieve a balance between energy use and throughput, which in turn maximized

network efficiency. (Luo and Wang, 2018).

Sridhar reports on the use of a dynamic cluster-based duty cycle in the novel geographic routing protocol, which

puts forth a clustering approach that guarantees the lowest energy use during data transmission. (Sridhar and

Pankajavalli, 2023). Wang aims to enhance wireless sensor networks' performance; the study combines a routing

Page 769

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue III, March 2026

protocol with coverage control techniques. A node collaborative scheduling method alleviates the latency and

lowers the energy consumption in the network by minimizing the active nodes and the created packets. (Wang

et al., 2024).

Venkatesh, the THGOR routing protocol selects the two-hop geographic opportunistic routing (THGOR)

protocol. THGOR improves packet delivery, energy utilization, and packet transmit delays metrics when

compared to efficient QoS-aware geographic opportunistic (EQGOR) and traditional geographic opportunistic

routing (GOR) in wireless sensor networks. This maximizes overall network performance. (Venkatesh et al.,

2019)

According to the EA-TPGF-SS protocol, the addition of energy awareness and a sleep schedule to idle relay

nodes increases the efficiency of the network. This method promotes the conservation of energy by allowing

nodes to remain sufficiently available for routing. (Alafeef et al., 2017).

To improve network lifetime, focus on energy-efficient routing in Wireless Sensor Networks with a comparison

of homogeneous and heterogeneous systems. In regard to time-sensitive applications, the focus is directed at

lower energy consumption with accurate data collection. (Patheja et al., 2012).

Waoo and Sharma in 2018 report on the development of energy-efficient routing protocols for Wireless Sensor

Networks (WSNs), which in turn put stress on extending network lifetime and reducing power usage. (Waoo

and Sharma, 2018).

Ghaffari et al. put forth the EQGR protocol, which does what it does to improve network efficiency by way of

energy-efficient routing. From simulation studies, the EQGR maximizes network performance via reliable data

delivery, reduced end-to-end latency, and improved on-time packet delivery. (Ghaffari et al., 2011). Yuan, the

proposed Geography and Energy Cluster Algorithm (GECA) improves network efficiency by addressing energy

waste in the traditional LEACH protocol through non-uniform clustering. (Yuan et al., 2014).

Chang et al. (2014) discuss energy-efficient geographic routing, proposing a cross-road routing approach that

integrates node distance, density, and direction to significantly enhance network performance. Vahabi reported

that a mobile sink in combination with hierarchical and geographic routing algorithms is put forth as a method

that improves the energy efficiency of WSNs. (Vahabi et al., 2019).

Akende indicates that the study introduced the Wireless Sensor Network Energy Reduction Routing Coordinate

Algorithm (WSNERRCA) that optimizes energy usage via geographical routing to improve the performance of

the network. (Akende, et al., 2022). Huang states that the EMGR protocol enhances network efficiency by using

energy-aware multipath global routing to avoid routing holes in Wireless Sensor Networks (WSNs). Energy-

aware forwarders and the optimized traffic distribution achieved with EMGR enhance energy saving and

network lifetime, correspondingly leading to enhanced network communication efficiency in a resource-

constrained network. (Huang et al., 2017).

As noted by Wang G., the proposed energy-aware geo-routing system in the paper incorporates a modified

transmission power model, thereby improving network performance and enabling energy-efficient route

selection. (Wang, 2010) Li, The proposed energy-efficient cooperative geographic routing (ECGR) approach

leverages geographic routing and cooperative diversity to maximize the network efficiency. As a comprehensive

approach to energy economy in wireless sensor networks, it also considers circuit energy usage, which reduces

interference and needless energy expenditure. (Li et al., 2013).

METHODOLOGY

A hybrid clustering and routing system is employed with a node location-based approach for energy-efficient

multi-hop transmission to enhance the GF-EERP protocol [1]. Nodes are put into energy level categories, which

achieve full energy play, and also have a dynamic selection of region heads with grid and semicircular clustering

Page 770

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue III, March 2026

methods in place of that [2]. By applying residual energy, node centrality, and congestion, routing routes are

controlled adaptively through Reinforcement Learning (RL) or Q-learning [3].

The routing process of GRP is shown in Figure 1.

The improved protocol is modeled and compared with comparative protocols such as LEACH, PEGASIS, and

AODV under different network conditions [5]. The performance metrics are energy expenditure, delivery ratio,

latency, and throughput [3].

Figure 2: The Complete GD-EERP system

Yes No

Start

Network Init

Energy Check

K-means Clustering

Less Congestion?

RL-GFEERP

Check Traffic

Forward data

Low energy model

Increase Lifetime

Re-evaluate Route

Find node Location

Low energy model

Cluster Formation

Select route

Select Cluster head

Geo Forwarding

End

Eliminate dead nodes

RL GFEERP protocol applies

Figure 1: Routing Process of GRP

Page 771

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue III, March 2026

I. Research Gap

Geographic routing protocols for Wireless Sensor Networks (WSNs) tend to sacrifice energy consumption

optimization and network lifetime. Current protocols, such as GF-EERP, utilize node location for routing but do

not incorporate adaptive mechanisms to dynamically balance network load. They also do not support efficient

traffic balancing as it tends to cause premature node depletion and decreased network efficiency. In this paper,

we improve the GF-EERP protocol by incorporating node location and Reinforcement Learning (RL) to facilitate

smart, energy-efficient routing decisions. The new method will improve energy consumption, traffic load

balancing, and network lifetime. The enhanced protocol will be analyzed and compared with current methods

using metrics such as energy consumption, network lifetime, packet delivery ratio, and latency. This paper fills

an essential gap by combining geographic routing with machine learning to create smarter and more sustainable

WSNs.

Table 5: Comparison of Reviewed Work with their Methodology and Limitations.

Author/s

Methodology

Limitations

Bairagi et al., 2024

GF-EERP, a Multi-hop,

Geographic energy-aware

routing protocol that adds

node classification, region

head selection, multi-hop

communication, and dead

node removal

Research will be focused on developing

an improved and efficient route discovery

process to enable better energy efficiency

in wireless sensor networks in mobile

environments.

Karthigeyan et al., 2025

A dual-phase approach

combining grid-based and

rectangular semi-circular

clustering techniques to

enhance the effectiveness of

data communication through

wireless sensor networks

and extend network

longevity through selective

replacement of nodes.

Follow-up studies need to focus on

increasing network life by node migration

further from the base station when nearby

nodes drain their power. A shortcoming of

the current algorithm is that it presumes

nodes are spatially aware, something that

would necessitate the development of

methods to infer location upon

deployment.

Al-Healy and Ibrahim, 2025

Employs comparative and

performance evaluation

methods to analyze and

optimize resource-limited

Wireless Sensor Networks

and ODV, LEACH, GPSR,

DSDV, and PEGASIS

algorithms employed.

Researchers must ensure that IoT

platforms work in real-life situations to

maximize routing protocols for real-time,

large-scale, and security-critical WSN

applications.

Yajadda and Safaei, 2023

The proposed approach

enhances the GF-EERP

protocol by incorporating

node location information

using a Reinforcement

Learning algorithm to make

energy-efficient routing

decisions.

This paper does not address resource

allocation problems such as buffer and

link management, which are of significant

importance under heavy traffic scenarios.

Additionally, the effects of self-similar or

Poisson-like traffic models on network

performance and congestion management

have not been studied, and there is scope

for future work.

Abujassar, 2024

QoS, Packet Delivery Ratio

(PDR), Traffic Overhead

(ToH), Energy Consumption

QoS routing mechanisms like nPSIR may

struggle to adjust dynamically fast enough

to high network topology changes and

Page 772

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue III, March 2026

CONCLUSION

This paper introduces an improved Geographic Forwarding Energy-Efficient Routing Protocol (GF-EERP)

designed to boost energy efficiency and prolong the lifespan of Wireless Sensor Networks. By combining

accurate node location data with adaptive routing based on reinforcement learning, the method allows for smart,

context-sensitive decisions in data forwarding. The hybrid clustering and geographic routing strategy efficiently

cuts down on unnecessary transmissions, balances the traffic load, and reduces early node failures.

Reinforcement learning further improves routing performance by dynamically responding to network changes,

traffic congestion, and remaining energy levels. A simulation-based comparison shows that the enhanced GF-

EERP consistently performs better than traditional protocols like LEACH, GPSR, GEAR, and M-GEAR in terms

of energy usage, packet delivery rate, latency, and overall network longevity. The findings confirm better

scalability, reliability, and resilience in various network situations. By merging geographic routing with machine

learning capabilities, the proposed protocol tackles major shortcomings of current energy-aware routing

approaches. This research underlines the effectiveness of learning-based geographic routing for long-lasting

WSN implementations. Future studies could explore real-time applications, mobility support, and deep

reinforcement learning to further improve adaptability and performance in large-scale IoT environments.

REFERENCES

1. Bairagi, P.P.; Dutta, M.; Babulal, K.S. An energy-efficient protocol based on recursive geographic

forwarding mechanisms for improving routing performance in WSN. IETE Journal of Research 70(3),

2212–2224 (2024).

2. Karthigeyan, S.; Bhol, S.; Jain, A.; Yadav, K.; Sinha, A. An energy-efficient hybrid communication

protocol for large area wireless sensor networks. Procedia Computer Science 252, 985–994 (2025).

3. Al-Healy, A.A.; Ibrahim, Q. Evaluation metrics and optimization strategies for routing protocols in

resource-constrained wireless sensor networks (2025).

4. Yajadda, S.H.; Safaei, F. A novel reinforcement learning routing algorithm for congestion control in

complex networks. arXiv preprint, arXiv:2401.00297 (2023).

5. Abujassar, R.S. A multi-path routing protocol with efficient energy consumption in IoT applications for

real-time traffic. EURASIP Journal on Wireless Communications and Networking 2024(1), 46 (2024).

6. Alhihi, M. Practical routing protocol models for improving network performance and adequacy. Journal

of Computer and Communications 5(6), 114–124 (2017).

7. Vinitha, A.; Rukmini, M.S.S. Multi-hop routing protocol using Taylor-based hybrid optimization

algorithm in WSNs. Journal of King Saud University–Computer and Information Sciences 34(5), 1857–

1868 (2022).

8. Boujou, M.; Iguernaissi, R.; Nicod, L.; Merad, D.; Dubuisson, S. In-depth analysis of GAF-Net:

Comparative fusion approaches in video-based person re-identification. Algorithms 17(8), 352 (2024).

9. Mustafa, M.E.; Abaker, A.A. Evaluation of OSPF and EIGRP based on route table size and dropped traffic

using different topologies (2024).

(EC), distance directly to the

base station, and latency,

using simulations with NS2

to improve the performance

of the network.

high mobility in VANETs, and thus may

cause interruption of data transmission

and high delay.

Vinitha and Rukmini, 2022

This paper employs a

security-aware multi-hop

routing protocol with a trust

scheme and a combined

Taylor C-SSA strategy to

optimize CH selection and

data transmission in a multi-

hop network.

Design a multi-hop routing system to

achieve high performance.

Page 773

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue III, March 2026

10. Wang, X.; Liu, X.; Wang, M.; Nie, Y.; Bian, Y. Energy-efficient spatial query-centric geographic routing

protocol in wireless sensor networks. Sensors 19(10), 2363 (2019).

11. Waoo, A.A.; Sharma, S. Comparative analysis of energy-efficient coverage and prolonging the lifetime

of homogeneous and heterogeneous WSNs. In ICACAT 2018, 1–4. IEEE (2018).

12. Sharma, M.; Agarwal, V. Maximizing network throughput by an efficient geographic routing protocol for

IoT-based sensor networks. In IEEE INDISCON 2023, 1–8. IEEE (2023).

13. Redjimi, K.; Redjimi, M.; Boulaiche, M. Improved geographic routing protocol for wireless sensor

networks. In International Conference on Digital Technologies and Applications, 1135–1145. Springer

(2021).

14. Vahabi, S.; Lahabi, M.; Eslaminejad, M.; Dashti, S.E. Geographic and clustering routing for energy saving

in wireless sensor networks. Journal of Communication Engineering 8(1), 146–157 (2019).

15. Luo, H.; Wang, L. Opportunistic routing protocol based on geographical location and energy balance. In

CECS 2018, 340–346. Atlantis Press (2018).

16. Sridhar, M.; Pankajavalli, P.B. Energy-efficient routing and scheduling using clustering in the geographic

routing protocol. Journal of Intelligent & Fuzzy Systems 44(1), 951–961 (2023).

17. Wang, M.; Zhu, Z.; Wang, Y.; Xie, S. Energy-efficient and highly reliable geographic routing based on

link detection and node collaborative scheduling in WSN. Sensors 24(11), 3263 (2024).

18. Venkatesh, A.; Achar, L.A.; Kushal, P.; Venugopal, K.R. Geographic opportunistic routing protocol based

on two-hop information for wireless sensor networks. International Journal of Communication Networks

and Distributed Systems 23(1), 93–116 (2019).

19. Alafeef, I.; Awad, F.; Al-Madi, N. Energy-aware geographic routing protocol with sleep scheduling for

wireless multimedia sensor networks. In HONET-ICT, 93–97. IEEE (2017).

20. Huang, H.; Yin, H.; Min, G.; Zhang, J.; Wu, Y.; Zhang, X. Energy-aware dual-path geographic routing to

bypass routing holes in wireless sensor networks. IEEE Transactions on Mobile Computing 17(6), 1339–

1352 (2017).

21. Ghaffari, A.; Rahmani, A.; Khademzadeh, A. Energy-efficient and QoS-aware geographic routing

protocol for wireless sensor networks. IEICE Electronics Express 8(8), 582–588 (2011).

22. Yuan, Z.H.; Li, B.; Wang, N. A novel geographical and energy-based clustering algorithm for wireless

sensor networks routing protocols. Advanced Materials Research 971, 1966–1969 (2014).

23. Kodesia, S.; Arya, P. Energy-efficient geographical routing protocol with location awareness in MANET.

International Journal of Computing 1(1) (2012).

24. Chang, J.M.; Lai, C.F.; Chao, H.C.; Zhu. An energy-efficient geographic routing protocol design in

vehicular ad hoc networks. Computing 96(2), 119–131 (2014).

25. Vahabi, S.; Eslaminejad, M.; Dashti, S.E. Integration of geographic and hierarchical routing protocols for

energy saving in WSNs with a mobile sink. Wireless Networks 25(5), 2953–2961 (2019).

26. Akende, S.S.; Ahaneku, M.A.; Nwawelu, U.N.; Amazue, U.C.; Amoke, D.A. Improving energy efficiency

of wireless sensor networks through topology optimization. International Journal of Emerging

Technology and Advanced Engineering 12(12), 107–116 (2022).

27. Wang, G. An energy-aware geographic routing protocol for mobile ad hoc networks. International Journal

of Software and Informatics 4(2), 183–196 (2010).

28. Patheja, P.S.; Waoo, A.; Shrivastava, P. Fault-tolerant, energy-saving method for reliable information

propagation in sensor networks. International Journal of Smart Sensor and Adhoc Network (2012).

29. Ramkumar, J.; Senthilkumar, A.; Lingaraj, M.; Karthikeyan, R.; Santhi, L. Optimal approach for

minimizing delays in IoT-based quantum wireless sensor networks using Nm-LEACH routing protocol

(2024).

30. Li, B.; Wang, W.; Yin, Q.; Li, H.; Yang, R. An energy-efficient geographic routing based on cooperative

transmission in WSNs. Science China Information Sciences 56(7), 1–10 (2013).

31. Akinola, O.I. Adaptive location-based routing protocols for dynamic wireless sensor networks in urban

cyber-physical systems. Journal of Engineering Research and Reports 26(7), 424–443 (2024).

32. Xu, Y.; Heidemann, J.; Estrin, D. Geography-informed energy conservation for ad hoc routing. In

Proceedings of the 7

Annual International Conference on Mobile Computing and Networking, 70–84

(2001).

Page 774

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue III, March 2026

33. Singh, S.; Woo, M.; Raghavendra, C.S. Power-aware routing in mobile ad hoc networks. In Proceedings

of the 4

Annual ACM/IEEE International Conference on Mobile Computing and Networking, 181–190

(1998).

34. Heinzelman, W.B.; Chandrakasan, A.P.; Balakrishnan, H. An application-specific protocol architecture

for wireless microsensor networks. IEEE Transactions on Wireless Communications 1(4), 660–670

(2002).

35. Watkins, C.J.C.H.; Dayan, P. Q-learning. Machine Learning 8(3–4), 279–292 (1992).

36. Stützle, T.; Dorigo, M. Ant colony optimization. In International Conference on Evolutionary Multi-

Criterion Optimization, 1–20. Springer (2009).

37. Chaudhary, P., & Waoo, A. A. “Wireless sensor network”. International Journal of Research Publication

and Reviews, 4(11), 46–49 (2023).

38. Jain, J.K.; Waoo, A.A.; Chauhan, D. A literature review on machine learning for cybersecurity issues.

International Journal of Scientific Research in Computer Science, Engineering and Information

Technology, 374–385 (2022).

39. Rao, D.D.; Waoo, A.A.; Singh, M.P.; Pareek, P.K.; Kamal, S.; Pandit, S.V. Strategizing IoT network layer

security through advanced intrusion detection systems and AI-driven threat analysis. Full Length Article

12(2), 195 (2024).

40. Soni, S.; Soni, R.; Waoo, A.A. RFID-based digital door locking system. Indian Journal of

Microprocessors and Microcontroller 1(2), 17–21 (2021).

41. Shukla, P., & Waoo, A. A. A research paper on an algorithm for mobility of a wireless sensor network.

International Journal of Creative Research Thoughts (IJCRT), 11(12), e257 (2023).

42. Waoo, A.A.; Sharma, S. Analysis of energy-efficient coverage and prolonging lifetime by comparing

homogeneous and heterogeneous wireless sensor networks. In ICACAT 2018, 1–4. IEEE (2018).

43. Bhartiya, P.; Bhatele, M.; Waoo, A.A. A machine learning approach for predictive analysis of traffic flow.

ShodhKosh Journal of Visual and Performing Arts 5, 422–430 (2024).

44. Waoo, A. A. A novel attack detection technique to find attacks in watermarked images with PSNR and

RGB intensity. International Journal of Electronics and Communication Engineering Research and

Development (IJECERD), 3(1), 11–21(2013).

45. Arunkumar, T. R., Toomula, S., Kumar, C. S. S., Yadav, G. H. K., Patil, B. V., Mandal, A., Waoo, A. A.,

Mondal, M. K. H., Roy, M. K., Vimalnath, S., Karthik, A., & Pallathadka, H. (2022). AI and the Internet

of Things (IoT) are used together to make a safe routing algorithm for mobile ad-hoc networks that saves

energy (Indian Patent No. 202241064060). Indian Patent Office.