Dynamic Resource Allocation in cloud computing infrastructure using machine learning techniques

The communication sector is advancing and its dependency on resource allocation, data centers, switching centers and 5G connectivity in respect to piconets requires updated solutions. Similarly, with the increasing number of users in cloud computing, users will face problems like Quality of services

2025-06-28 16:26:53 - Adil Khan

Project Title

Dynamic Resource Allocation in cloud computing infrastructure using machine learning techniques

Project Area of Specialization Artificial IntelligenceProject Summary

The communication sector is advancing and its dependency on resource allocation, data centers, switching centers and 5G connectivity in respect to piconets requires updated solutions. Similarly, with the increasing number of users in cloud computing, users will face problems like Quality of services, degradation of performance and security issues. Some users may use more software and hardware and other may use lesser, so providing all users same resources will be wastage of resources. In order to save resources there is a need to allocate resources to user as per there their requirments. The servers have to put its certain components on standby because the extent of the request is unknown, causing extra consumption of power. On the other hand, if the standby resource is not sufficient for entertaining the request, this causes a delay in allocating the resources to a specific client.

Project Objectives

The aim of this project is to devise a ANN model based on machine learning technique (MLT) that can estimate the number of users, accessing to the cloud resources for requesting various types of services. The main objectives of which are given below;

Project Implementation Method

The model will be first implemented and tested in Matlab. We will use an ANN  model to predict the future resources of the cloud requests based in the previous data.. Then after this the system will allocate resources to the clients in an optimized manner. We are using the data of Microsoft Azure to train the model. We have a big data bank through which we will train our model and it is verry difficult for normal processors. We will need two GPU's to increase our processing power. It will increase the efficiency of proposed model and will allocate resources dynamically. One microcontroller will be used in the project for the the system management and for the allocation of resources.

Benefits of the Project Technical Details of Final Deliverable

The proposed model will predict future requests of the clients to the cloud services provider. Based on the prediction it will take dicission to scale up and scale down the resources with respect to user needs. Then it will allocate resources dynamically to the clinets. Extra servers will be kep't on stand by position untill the model predict its need and then will be turned on automatically to deliver services.

Final Deliverable of the Project HW/SW integrated systemCore Industry ITOther Industries Others , Telecommunication Core Technology Artificial Intelligence(AI)Other Technologies Cloud InfrastructureSustainable Development Goals Industry, Innovation and InfrastructureRequired Resources
Item Name Type No. of Units Per Unit Cost (in Rs) Total (in Rs)
Total in (Rs) 69760
VisionTek Radeon RX 560 4GB GDDR5 4M 4K Graphics Card. Equipment23024060480
Raspberry Pi AD/DA Expansion Shield Board Onboard ADS1256 DAC8552 Equipment152805280
Order charge + printing Equipment140004000

More Posts