A Systematic Literature Review on Deep Learning Approaches for Cloud Service Recommender Systems
Open Access
- 2 October 2025
- journal article
- review article
- Published by Universiti Pendidikan Sultan Idris in Journal Of ICT In Education
- Vol. 12 (2) , 149-162
Abstract
Deep Learning (DL) offers a promising solution for cloud service recommender systems (CSRS) by addressing data sparsity issues and helping users overcome cold-start problems while managing dynamic preferences. The study follows the PRISMA 2020 guidelines in conducting a systematic literature review (SLR) of DL-based CSRS advancements from 2019 to 2025. The research started with 412 electronic records from Scopus, ScienceDirect, Springer, Wiley, and other sources before completing thorough screenings that narrowed the search to 23 appropriate studies. The integration of hybrid neural networks, along with attention mechanisms and knowledge graph integration, demonstrates improved accuracy for implementing the multi-criteria recommendations based on the quality-of-service prediction, the resource allocation, and the personalised service selection. Real-time scalability limitations and constraints regarding explainability remain despite current developments. Future research should examine federated learning systems and edge-cloud integration elements with ethical AI frameworks in place. The review delivers a structured overview that guides researchers and practitioners who want to enhance cloud service recommendations by employing modern methodologies.Keywords
This publication has 32 references indexed in Scilit:
- Introducing an improved deep reinforcement learning algorithm for task scheduling in cloud computingThe Journal of Supercomputing, 2024
- Efficient Kalman filter based deep learning approaches for workload prediction in cloud and edge environmentsComputing, 2024
- Recommending cloud services based on social trust: An overviewConcurrency and Computation: Practice and Experience, 2024
- Virtual Machine Allocation Using Optimal Resource Management ApproachWireless Personal Communications, 2024
- Cloud-load forecasting via decomposition-aided attention recurrent neural network tuned by modified particle swarm optimizationComplex & Intelligent Systems, 2023
- Multivariate workload and resource prediction in cloud computing using CNN and GRU by attention mechanismThe Journal of Supercomputing, 2022
- Workload Time Series Cumulative Prediction Mechanism for Cloud Resources Using Neural Machine Translation TechniqueJournal of Grid Computing, 2022
- Deep knowledge-aware framework for web service recommendationThe Journal of Supercomputing, 2021
- Computation of workflow scheduling using backpropagation neural network in cloud computing: a virtual machine placement approachThe Journal of Supercomputing, 2021
- A water cycle optimized wavelet neural network algorithm for demand prediction in cloud computingCluster Computing, 2019