Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM63950
Volume:
10 |
5 |
May 2026
Pages:
1-8
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Department of Computer Science and Engineering
Bharatiya Vidya Bhavan's Sardar Patel Institute of Technology (SPIT)

Department of Computer Science and Engineering
Bharatiya Vidya Bhavan's Sardar Patel Institute of Technology (SPIT)

Department of Computer Science and Engineering
Bharatiya Vidya Bhavan's Sardar Patel Institute of Technology (SPIT)

Department of Computer Science and Engineering
Bharatiya Vidya Bhavan's Sardar Patel Institute of Technology (SPIT)
Horizontal scaling forms the backbone of modern cloud infrastructure, but traditional load balancing systems relying on a single master proxy introduce a critical single point of failure and performance bottleneck. This paper proposes a novel framework for Peer-to-Peer (P2P) Load Balancing coupled with Machine Learning (ML) based Adaptive Scaling to enhance service resilience and efficiency. Our P2P approach replaces the centralized proxy by distributing request routing responsibility among service instances (peers), eliminating the single point of failure. A key challenge in P2P systems is managing the excessive overhead of full connectivity; thus, we investigate how limiting peer-to-peer connection valencies affects network topology, specifically noting the tendency for low valencies to form inefficient, chain-like structures. Additionally, we integrate an ML-based CPU utilization forecasting model to predict load spikes and trigger unit spawning preemptively, mitigating crash risks associated with reactive scaling. We analyze various P2P configurations based on valency limits and their impact on load distribution, networking overhead, and latency, demonstrating a highly resilient and performance-optimized solution for high- concurrency environments.
KEYWORDS
This paper presented a novel decentralized architecture for horizontal scaling...
[1] G. Eason, B. Noble, and I. N. Sneddon, “On certain integrals of Lipschitz-Hankel type involving products of Bessel functions,” Phil. Trans. Roy. Soc. London, vol. A247, pp. 529–551, April 1955. [2] J. Clerk Maxwell, A Treatise on Electricity and Magnetism, 3rd ed., vol. 2. Oxford: Clarendon, 1892, pp.68–73. [3] W. Zhang, ”Linux Virtual Server for Scalable Network Services,” in Proc. Ottawa Linux Symp., 2000, pp. 212–221. [4] I. Stoica, R. Morris, D. Karger, M. Kaashoek, and H. Balakrishnan, ”Chord: A scalable peer-to-peer lookup service for internet applications,” IEEE/ACM Trans. Netw., vol. 11, no. 1, pp. 17-32, Feb. 2003. [5] A. Rowstron and P. Druschel, ”Pastry: Scalable, decentralized object location and routing for large-scale peer-to-peer systems,” in Proc. IFIP/ACM Int. Conf. on Distributed Systems Platforms, 2001, pp. 329–350. [6] P. S. Senthil Kumar, C. S. Shajitha, and V. R. Sarma, ”Gossip-based load balancing strategy for virtual machines in cloud computing,” in Proc. IEEE Int. Conf. on Computational Intelligence and Computing Research, 2013, pp. 1–6. [7] D. J. Watts and S. H. Strogatz, ”Collective dynamics of ’small-world’ networks,” Nature, vol. 393, no. 6684, pp. 440–442, Jun. 1998. [8] J. Wang, M. H. Li, B. B. Chen, and Y. Wang, ”Cloud resource prediction based on LSTM-RNN,” in Proc. IEEE Int. Conf. on Cloud Computing and Big Data Analytics, 2017, pp. 248–253. [9] P. Maymounkov and D. Mazieres, ”Kademlia: A Peer-to-Peer Informa- tion System Based on the XOR Metric,” in Proc. IPTPS ’02, Springer, 2002, pp. 53-65. [10] S. Ratnasamy, P. Francis, M. Handley, R. Karp, and S. Shenker, ”A Scalable Content-Addressable Network,” in Proc. ACM SIGCOMM, 2001, pp. 161–172.
Publication Date
5/25/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
4
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...