Jul 2026· International Journal of Creative and Open Research in Engineering and Management· Vol 02, pp. 1-14· 0 citations
TL;DR
This work proposes an Adaptive Load Balancing approach using Artificial Intelligence (AI) to dynamically distribute network traffic across multiple servers or network nodes by continuously learning from network conditions such as traffic load, response time, and bandwidth usage.
Abstract
With the rapid growth of cloud computing, data centers, and high-speed networks, efficient load balancing has become a critical requirement for ensuring optimal network performance and quality of service. Traditional load balancing techniques such as round-robin and least-connection methods rely on static rules and fail to adapt to dynamic network conditions like fluctuating traffic, node failures, and varying resource availability. This often leads to congestion, increased latency, and underutilization of network resources.
This work proposes an Adaptive Load Balancing approach using Artificial Intelligence (AI) to dynamically distribute network traffic across multiple servers or network nodes. By continuously learning from network conditions such as traffic load, response time, and bandwidth usage, the AI-based system makes intelligent routing decisions in real time. The proposed system is implemented using Python, simulating network environments and applying machine learning algorithms to achieve efficient, scalable, and self-adaptive load balancing in computer networks.
Keywords— Adaptive Load Balancing, Artificial Intelligence in Networking, AI-Based Load Balancing,Computer Network Optimization
The findings show that adaptive algorithm and hybrid algorithm is better in scalability, robustness and the overall performance of the system compared to the traditional centralized algorithms.
Farah Al-Farsi· International Journal of App...· 0 citations
Experiments show that the proposed Hybrid Framework for Joint Optimization of Resource Allocation and Load Balancing that spans two layers in heterogeneous cloud computing systems obtains 25-30% energy savings compared with ordinary methods, significantly reduces p95 latency and also achieves a relatively better Quality Of Service.
Eram Fatma, Nidhi Mishra, Mohammed Abdul Bari· Journal of Intelligent Decis...· 0 citations
This work proposes a scalable, intelligent, and resilient foundation for next-generation high-performance analytics and data-intensive applications that integrates adaptive resource management, intelligent workload scheduling, dynamic task migration, predictive analytics, and machine learning-based optimization to improve computational efficiency and responsiveness.
John Peterson, L. Martínez· International Journal of App...· 0 citations
: Multipath load balancing can effectively improve network throughput and reliability by aggregating the available bandwidth of multiple paths. However, existing load balancing schemes including Equal-Cost Multi-Path forwarding (ECMP), Weighted-Cost Multi-Path forwarding (WCMP) or LetFlow may lead to significant performance degradation due to hash conflicts and only target fixed symmetric topologies (e.g., Fattree). Flowlet switching has been proven to be a fine-grained load balancing technique, but remains elusive for widespread deployment. The emergence of network programmability including the control plane and data plane provides a new insight for the management of multipath load balancing. To achieve more effective load balancing and guarantee Quality of Service (QoS) on any network topology, we present ConFlet, a congestion-aware load balancing with Flowlet switching based on the cooperation of the data and control plane, where the control plane monitors the global network status to perform the optimized routing decision, and the data plane implements the flow splitting and path switching. Specifically, the centralized controller evaluates the reliability of nodes and links to perform multi-path routing calculations, ensuring that flows always travel along the most reliable multiple paths. The data plane can dynamically set the flowlet timeout to split flows into flowlets according to the path quality difference, and then implement path switching and congestion avoidance based on real-time congestion feedback. Experimental results show that compared to WCMP/LetFlow, ConFlet can significantly improve average service reliability and network throughput, and reduce average packet delay. Meanwhile, ConFlet can react quickly to congestion and maintain high resilience to network asymmetry
Unknown authors· Computers, Materials & C...· 0 citations
Cloud computing allows flexible and scalable computing resources. However, it is still a challenging problem how to efficiently distribute incoming workloads onto Virtual Machines (VMs). If the tasks are not well distributed, some VMs can be heavily loaded and others can be idle or lightly loaded. This can increase response time and processing time and can also reduce the overall utilization and performance of the cloud system. This paper presents a Machine Learning–Based Weighted Dynamic Load Balancing (ML-WDLB) approach for making VM selection more responsive to changing workload conditions. The approach uses both historical and current VM information, including CPU utilization, memory utilization, processing time, response time, and bandwidth. A Random Forest model is used to estimate the suitability of a VM for an incoming cloudlet or task. This prediction is combined with a weighted VM score that reflects the current condition of each VM. The VM with the highest final score, provided that it is below the specified load threshold, is selected for task execution. The performance of the approach can be assessed using response time, processing time, makespan, throughput, resource utilization, and load imbalance. The main aim of ML-WDLB is to provide a practical balance between prediction and current system information so that workload can be distributed more effectively as cloud conditions change.
Unknown authors· International journal of com...· 0 citations
The rapid growth in artificial intelligence (AI) demand has significantly increased the electricity consumption and carbon emissions of computing centers. How to schedule AI requests across computing centers to reduce carbon emissions and electricity costs while maintaining low latency is an essential research problem. Existing schedulers reduce emissions by shifting workloads or balancing resources but usually simplify power system modeling, ignore transmission-side costs and carbon emissions, or make local decisions without batch-level coordination. To better address these problems, we first develop an ILP-based scheduler to get optimized results, but it faces scalability limitations. Then, we propose RAPID, a region-aware and power-informed scheduling framework that integrates static and online heuristic schedulers for large-scale AI request scheduling. Experiments based on real-world GenAI traces and Chinese regional power profiles show that RAPID significantly reduces carbon emissions, electricity costs, and total energy consumption compared to methods from previous works while maintaining zero Service Level Agreement (SLA) violations.
Unknown authors· Sustainability· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
