By: Aditi Bansal, CSE, Chandigarh College of Engineering and Technology, Chandigarh, India, mco22381@ccet.ac.in


This article examines how the edge computing and deep reinforcement learning (DRL) is changing routing protocols. Edge computing with data processing changes response times. Routing protocols, which is important for optimizing data transfer, face challenges when adapting to different environments. The collaboration between edge computing and DRL will create infrastructure in edge environments. This article investigates relation between edge computing and deep reinforcement learning (DRL) to address critical resource allocation and latency challenges. This ensures fast, real-time data processing, creates a good infrastructure, and opens up many possibilities in data processing.

Keywords: Edge Computing, Deep Reinforcement Learning, Data Processing, Routing Protocols.


The edge[1] computing marks a change in the field of modern computing, as it responds to the growing demand for data processing. This establishes the scene by providing an informative explanation of edge computing’s importance and highlighting its influence on data processing, communication[2] and bandwidth[3] using IoT[4] .

In the modern computing , the collaboration[5] of edge computing and deep reinforcement learning[6] represents a change and highlights[7] the need for routing protocols. This serves as a gateway to understanding the role that the intersection of edge computing and deep reinforcement learning will play in the efficiency of routing[8] protocols within the parameters of the technology[9].

1.1 Edge Computing Uses:

  1. Edge computing keeps the resources closer to the data source.
  2. It signifies a departure from traditional centralized cloud[10] infrastructures.
  3. The proximity ensures a computing experience that is more responsive.
  4. Edge computing is effective in addressing latency issues in a variety of applications.
  5. This approach offers versatility, making it applicable across a range of use cases.

In the world of edge computing [11], routing protocols play a major role in data[12] transmission optimization[13]. These protocols are essential for network because they take out the most effective pathways.

This is a very important task where latency might vary, bandwidth is restricted, and resource availability at edge nodes are many. In these environments, efficient routing is essential to ensure accurate communication between devices and applications. Traditional routing protocols have difficulty in adjusting to the constantly changing settings, which can lead to bad performance . The lack of information available for routing decisions makes these problems worse, especially in context of the needs of various Internet of Things (IoT) things.

Key Concepts

2.1 Edge Computing Fundamentals:

Fundamentally, edge computing focuses on processing[14] data locally and minimizing latency and improving response times. This innovative method restructures the distribution of computing resources and places them at the edge of the network.

The edge computing skilfully overcomes problems like latency, bandwidth limitations, and fluctuations in resource availability in different edge environments.

2.2 Overview of Deep Reinforcement Learning(DRL):

DRL, a subset of machine learning, guides algorithms to make decisions through interaction with the environment. In the field of routing protocols, DRL[15] has proven to be a powerful tool for decision making. The key components of DRL are related to routing, including agents, environments, actions, rewards, and neural networks[16].

2.3 Established Routing Protocols and Problems in Edge Environments:

Traditional routing protocols are made for centralized architectures and they face limitations when deployed in distributed environments of edge computing. The focus is on key factors such as limited information for routing decisions and the immediate risk of performance.


To optimize edge computing routing protocols, Linux stands out as an adaptable operating system that improves network efficiency. Linux’s stability makes it the first choice for providing efficient and important for good performance in edge computing. Also, wide support for Linux[17] facilitates to rapid development.

2.5 Some important points:

Optimizing edge computing routing protocols through deep reinforcement learning provides many benefits from CAD tools for tuning the delay of symmetric FPGA[18] architectures with hybrid LUT/PLA[19]. Also, optimization is a design flow for reconfigurable embedded system architectures, the importance of this LUTs/PLAs in designing efficient solutions. Using deep reinforcement learning into this increases the adaptability of the routing protocols and ensures the best performance in the edge computing environments.


The use of DRL to optimize routing protocols in edge computing has practical importance in many fields:

1. Improving efficiency in IoT networks: Internet of Things networks (IoT)[20], especially scenarios where devices operate at the network edge.

2.Advanced communications in smart cities: Improve routing protocols to increase communication efficiency between smart city devices and the infrastructure at the network edge.

3.Optimized data exchange in self-driving cars: Fine-tuning of communication paths to enable more efficient data exchange between self-driving cars and associated infrastructure in edge computing environments.

Challenges and solutions:




Training Complexity

New algorithms

Tutorials and documentation

Real-Time adaptability

Dynamic learning rate

Continuous monitoring

Resource Constraints

Useful and time-saving algorithms

Efficient resource allocation

Future Scope

To optimize edge computing routing protocols with DRL, includes new technologies. In addition to efforts towards standardization and real-time adaptation mechanisms, energy efficiency . Edge and cloud collaboration, industry-specific applications are key areas of focus. Overall, it is likely to see development of edge computing capabilities through the use of DRL.


Edge computing and Deep Reinforcement Learning (DRL) are becoming increasingly important in the field of computing, especially when it comes to tackling resource allocation problems. By cleverly processing data at its origin and harnessing DRL’s ability to make adaptive decisions, we can greatly decrease delays, enhance routing protocols, and create a smarter infrastructure. This collaboration imagines a future where computer science is transformed, unlocking new possibilities in various industries. This comprehensive approach not only leads to improvements in routing protocols but also uncovers fresh opportunities in data processing. The harmonious relationship between edge computing and DRL directly tackles the issues of distributing resources. It is worth noting that by processing data at its origin and utilizing the potential of deep reinforcement learning, not only does it guarantee real-time data processing, but it also contributes to the advancement of a more advantageous outcome. By combining edge computing and deep reinforcement learning, we expect to see significant improvements in how quickly things respond, how efficient processes are, and overall ingenuity in different areas. This endeavour holds the potential for a future where the influence goes beyond mere routing protocols, presenting a revolutionary way of handling data processing and computational abilities.


  1.  Gupta, A., Sharma, A., Singh, S. K., & Kumar, S. Cloud Computing & Fog Computing: A solution for High Performance Computing.
  2.  Vijayakumar, P., Rajkumar, S. C., & Jegatha Deborah, L. (2022). Passive-Awake Energy Conscious Power Consumption in Smart Electric Vehicles Using Cluster Type Cloud Communication. International Journal of Cloud Applications and Computing (IJCAC), 12(1), 1-14. http://doi.org/10.4018/IJCAC.297108
  3.  Teragni, M. & Pons, C. (2022). λHive: Formal Semantics of an Edge Computing Model Based on JavaScript. International Journal of Cloud Applications and Computing (IJCAC), 12(1), 1-22. http://doi.org/10.4018/IJCAC.312564
  4. Singh, R., Singh, S. K., Kumar, S., & Gill, S. S. (2022). SDN-Aided Edge Computing-Enabled AI for IoT and Smart Cities. SDN-Supported Edge-Cloud Interplay for Next Generation Internet of Things, 41-70.
  5. Iqbal, S., Hussain, I., Sharif, Z., Qureshi, K. H., & Jabeen, J. (2021). Reliable and Energy-Efficient Routing Scheme for Underwater Wireless Sensor Networks (UWSNs). International Journal of Cloud Applications and Computing (IJCAC), 11(4), 42-58. http://doi.org/10.4018/IJCAC.2021100103
  6. Sharma, A., Singh, S. K., Chhabra, A., Kumar, S., Arya, V., & Moslehpour, M. (2023). A Novel Deep Federated Learning-Based Model to Enhance Privacy in Critical Infrastructure Systems. International Journal of Software Science and Computational Intelligence (IJSSCI), 15(1), 1-23. http://doi.org/10.4018/IJSSCI.334711
  7. Kumar, S., Singh, S. K., & Aggarwal, N. (2023). Speculative Parallelism on Multicore Chip Architecture Strengthen Green Computing Concept: A Survey. In Advanced Computer Science Applications (pp. 3-16). Apple Academic Press.
  8. Kumar, R., Sinngh, S. K., & Lobiyal, D. K. (2023, April). Routing of Vehicular IoT Networks based on various routing Metrics, Characteristics, and Properties. In 2023 International Conference on Computational Intelligence, Communication Technology and Networking (CICTN) (pp. 656-662). IEEE.
  9. Sharma, A., Singh, S.K., Kumar, S., Chhabra, A., Gupta, S. (2023). Security of Android Banking Mobile Apps: Challenges and Opportunities. In: Nedjah, N., Martínez Pérez, G., Gupta, B.B. (eds) International Conference on Cyber Security, Privacy and Networking (ICSPN 2022). ICSPN 2021. Lecture Notes in Networks and Systems, vol 599. Springer, Cham. https://doi.org/10.1007/978-3-031-22018-0_39
  10. Saini, T., Kumar, S., Vats, T., & Singh, M. (2020). Edge Computing in Cloud Computing Environment: Opportunities and Challenges. In International Conference on Smart Systems and Advanced Computing (Syscom-2021).
  11. Dubey, H. A. R. S. H. I. T., Kumar, S. U. D. H. A. K. A. R., & Chhabra, A. N. U. R. E. E. T. (2022). Cyber Security Model to Secure Data Transmission using Cloud Cryptography. Cyber Secur. Insights Mag2, 9-12.
  12. Sharma, A., Singh, S. K., Badwal, E., Kumar, S., Gupta, B. B., & Arya, V. & Santaniello, D.(2023, January). Fuzzy Based Clustering of Consumers’ Big Data in Industrial Applications. In 2023 IEEE International Conference on Consumer Electronics (ICCE) (pp. 01-03).dat
  13. Madan, K., & Bhatia, R. K. (2021). Ranked Deep Web Page Detection Using Reinforcement Learning and Query Optimization. International Journal on Semantic Web and Information Systems (IJSWIS), 17(4), 99-121. http://doi.org/10.4018/IJSWIS.2021100106
  14. Srivastava, A. M., Rotte, P. A., Jain, A., & Prakash, S. (2022). Handling Data Scarcity Through Data Augmentation in Training of Deep Neural Networks for 3D Data Processing. International Journal on Semantic Web and Information Systems (IJSWIS), 18(1), 1-16. http://doi.org/10.4018/IJSWIS.297038
  15. Vijayakumar P., Jegatha Deborah L., & Rajkumar S. C. (2022). Deep Reinforcement Learning-Based Pedestrian and Independent Vehicle Safety Fortification Using Intelligent Perception. International Journal of Software Science and Computational Intelligence (IJSSCI), 14(1), 1-33. http://doi.org/10.4018/IJSSCI.291712
  16. Srivastava, D., Kumar, A., Mishra, A., Arya, V., Almomani, A., Hsu, C. H., & Santaniello, D. (2022). Performance Optimization of Multi-Hop Routing Protocols With Clustering-Based Hybrid Networking Architecture in Mobile Adhoc Cloud Networks. International Journal of Cloud Applications and Computing (IJCAC), 12(1), 1-15. http://doi.org/10.4018/IJCAC.309932
  17. Singh, S. K. (2021). Linux Yourself: Concept and Programming. CRC Press.
  18. Singh, S. K., Singh, R. K., Bhatia, M. P. S., & Singh, S. P. (2013). CAD for delay optimization of symmetrical FPGA architecture through hybrid LUTs/PLAs. In Advances in Computing and Information Technology: Proceedings of the Second International Conference on Advances in Computing and Information Technology (ACITY) July 13-15, 2012, Chennai, India-Volume 3 (pp. 581-591). Springer Berlin Heidelberg.
  19. Singh, S. K., Singh, R. K., & Bhatia, M. P. S. (2012, December). Design flow of reconfigurable embedded system architecture using LUTs/PLAs. In 2012 2nd IEEE International Conference on Parallel, Distributed and Grid Computing (pp. 385-390). IEEE.
  20. Vats, T., Singh, S. K., Kumar, S., Gupta, B. B., Gill, S. S., Arya, V., & Alhalabi, W. (2023). Explainable context-aware IoT framework using human digital twin for healthcare. Multimedia Tools and Applications, 1-25.
  21. Almomani, A., Alauthman, M., Shatnawi, M. T., Alweshah, M., Alrosan, A., Alomoush, W., & Gupta, B. B. (2022). Phishing website detection with semantic features based on machine learning classifiers: a comparative study. International Journal on Semantic Web and Information Systems (IJSWIS)18(1), 1-24.
  22. Wang, L., Li, L., Li, J., Li, J., Gupta, B. B., & Liu, X. (2018). Compressive sensing of medical images with confidentially homomorphic aggregations. IEEE Internet of Things Journal6(2), 1402-1409.
  23. Stergiou, C. L., Psannis, K. E., & Gupta, B. B. (2021). InFeMo: flexible big data management through a federated cloud system. ACM Transactions on Internet Technology (TOIT)22(2), 1-22.
  24. Gupta, B. B., Perez, G. M., Agrawal, D. P., & Gupta, D. (2020). Handbook of computer networks and cyber security. Springer10, 978-3.
  25. Bhushan, K., & Gupta, B. B. (2017). Security challenges in cloud computing: state-of-art. International Journal of Big Data Intelligence4(2), 81-107.

Cite As

Bansal A. (2024), Optimizing Edge Computing Routing Protocols Through Deep Reinforcement Learning, Insights2Techinfo, pp. 1

Share this:

Leave a Reply

Your email address will not be published.