Bulletin of Electrical Engineering and Informatics Vol. 14, No. 2, April 2025, pp. 1570~1578 ISSN: 2302-9285, DOI: 10.11591/eei.v14i2.9123  1570 Journal homepage: http://beei.org Hybrid algorithm for optimized clustering and load balancing using deep Q reccurent neural networks in cloud computing Nampally Vijay Kumar 1,2 , Satarupa Mohanty 1 , Prasant Kumar Pattnaik 1 1 School of Computer Engineering, KIIT Deemed to be University, Bhubaneswar, India 2 Department of Computer Science and Business System, B V Raju Institute of Technology, Narsapur, Telangana, India Article Info ABSTRACT Article history: Received Aug 9, 2024 Revised Nov 7, 2024 Accepted Nov 19, 2024 Cloud services are among the technologies that are developing the fastest. Additionally, it is acknowledged that load balancing poses a major obstacle to reaching energy efficiency. Distributing the load among several resources in order to provide the best possible services is the main purpose of load balancing. The network's accessibility and dependability are increased through the usage of fault tolerance. An approach for hybrid deep learning (DL)-based load balancing is proposed in this paper. Tasks are first distributed in a round-robin fashion to every virtual machine (VM). When assessing whether a VM is overloaded or underloaded, the deep embedding cluster (DEC) also considers the central processing unit (CPU), bandwidth, memory, processing elements, and frequency scaling factors. For cloud load balancing, the tasks completed on the overloaded VM are assigned to the underloaded VM based on their value. To balance the load depending on many aspects like supply, demand, capacity, load, resource utilization, and fault tolerance, the deep Q recurrent neural network (DQRNN) is also suggested. Additionally, load, capacity, resource consumption, and success rate are used to evaluate the efficacy of this approach; optimum values of 0.147, 0.726, 0.527, and 0.895 are attained. Keywords: Cloud computing Deep embedding clusters Deep Q network Recurrent neural networks Resource allocation This is an open access article under the CC BY-SA license. Corresponding Author: Nampally Vijay Kumar School of Computer Engineering, KIIT Deemed to be University Bhubaneswar, Odisha, India Email: 1981034@kiit.ac.in 1. INTRODUCTION The cloud platform is facing a variety of challenges in terms of resource allocation [1]-[3]. Due to the fluctuating demand, resource misallocation may result in the overloading of certain virtual machines (VM), while it is employed to servers are required to manage an extensive volume of requests as the cloud's capacity expands [4]. The primary issue is the preservation of consistent performance during breakouts. Cloud computing necessitates a diverse array of resources, including memory, storage, network, and central processing unit (CPU) [5], [6]. Furthermore, the load balancing employed a variety of strategies to optimise potential target hosts. It does not ensure superior task execution performance, although the immediate effect may lead to increased resource utilisation [7]. The development of solutions that enable the system to continuously operate at a reduced level without failing the performance of its elements is required for fault tolerance [8]. It is one of the most critical challenges for the cloud to provide dependable services. Additionally, the volume of requests that the cloud will receive will require fault tolerance to reduce the incidence of errors and malfunctions. Additionally, cloud computing automatically adjusts the VM configuration by harmonising the system burden as the workload increases or decreases [9]. Therefore, the