An Efficient Clustering and Deep Learning Based Resource Scheduling for Edge Computing to Integrate Cloud-IoT

Vijayasekaran, G.; Duraipandian, M.

doi:10.1007/s11277-021-09442-8

Cited by 14 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The existing model results are obtained from our previous research work, which schedules resources based on the LSTM and BRNN models. 31 Benchmark data from Intel's Berkeley research laboratory has been used for the analysis. The dataset comprises sensor readings from voltage, light, temperature, and humidity sensors.…”

Section: Resultsmentioning

confidence: 99%

“…An extensive simulation analysis is done to validate the proposed implemented concatenated DL model and compared with existing scheduling algorithms based on GA, IPSO, LSTM, and BRNN. The existing model results are obtained from our previous research work, which schedules resources based on the LSTM and BRNN models 31 . Benchmark data from Intel's Berkeley research laboratory has been used for the analysis.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

An improved resource scheduling strategy through concatenated deep learning model for edge computing IoT networks

Vijayasekaran,

Duraipandian

2024

Int J Communication

View full text Add to dashboard Cite

SummaryWith increasing challenges and research in edge‐assisted IoT models, an improved resource scheduling approach exploiting deep learning concepts is proposed in this research work. Improvement in performance in the proposed work is achieved primarily by addressing the response time and waiting time. This could be achieved if the optimal resources are scheduled without any delay. The presented concatenated deep learning technique considers the time series IoT network source requirements and allocates optimal resources from the resource pool, considering resource availability, workload, and computation time. Two deep learning techniques, namely, CNN and GRU, are utilized for the concatenation process, while resource characteristics are considered as features that are extracted and classified to schedule optimal resources. Novelty in the proposed work is exhibited in the form of the concatenation process proposed. The proposed resource scheduling performance metrics are compared with the performance of the existing scheduling model through simulation analysis for better validation. The proposed model selects the optimal resources from the resource pool using concatenated features and schedules for respective requests with minimum delay and waiting time, which increases the overall efficiency of the edge computing IoT networks.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

An improved resource scheduling strategy through concatenated deep learning model for edge computing IoT networks

Vijayasekaran,

Duraipandian

2024

Int J Communication

View full text Add to dashboard Cite

show abstract

“…The fuzzy logic assures that the task scheduler does not get stuck in local minima. Vijayasekaran et al [110] proposed a two-phase solution. In the first phase, they incorporated the spectral clustering algorithm, an efficient clustering approach, to reduce data overlap and computational complexities within the edge computing framework.…”

Section: ) Existing Solutions For Ai-based Resource Schedulingmentioning

confidence: 99%

AI-Empowered Fog/Edge Resource Management for IoT Applications: A Comprehensive Review, Research Challenges, and Future Perspectives

Walia,

Kumar,

Gill

2024

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

The proliferation of ubiquitous Internet of Things (IoT) sensors and smart devices in several domains embracing healthcare, Industry 4.0, transportation and agriculture are giving rise to a prodigious amount of data requiring everincreasing computations and services from cloud to the edge of the network. Fog/Edge computing is a promising and distributed computing paradigm that has drawn extensive attention from both industry and academia. The infrastructural efficiency of these computing paradigms necessitates adaptive resource management mechanisms for offloading decisions and efficient scheduling. Resource Management (RM) is a non-trivial issue whose complexity is the result of heterogeneous resources, incoming transactional workload, edge node discovery, and Quality of Service (QoS) parameters at the same time, which makes the efficacy of resources even more challenging. Hence, the researchers have adopted Artificial Intelligence (AI)-based techniques to resolve the abovementioned issues. This paper offers a comprehensive review of resource management issues and challenges in Fog/Edge paradigm by categorizing them into provisioning of computing resources, task offloading, resource scheduling, service placement, and load balancing. In addition, existing AI and non-AI based state-of-the-art solutions have been discussed, along with their QoS metrics, datasets analysed, limitations and challenges. The survey provides mathematical formulation corresponding to each categorized resource management issue. Our work sheds light on promising research directions on cutting-edge technologies such as Serverless computing, 5G, Industrial IoT (IIoT), blockchain, digital twins, quantum computing, and Software-Defined Networking (SDN), which can be integrated with the existing frameworks of fog/edge-of-things paradigms to improve business intelligence and analytics amongst IoT-based applications.

show abstract

“…Botta et al (2016) [9] performed a survey and analysed the issues of integrating IoT and Cloud computing. IoT devices access data from the cloud for making decisions on their own, which is collected periodically through various sensors [10]. The periodic data collection mechanism leads to unnecessary energy consumption.…”

Section: Identification Of Cloudiot Issuesmentioning

confidence: 99%

Interpretive Structural Modeling Based Assessment and Optimization of Cloud with Internet of Things (CloudIoT) Issues Through Effective Scheduling

Shukla¹,

Khan²,

Kumar³

et al. 2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Integrated CloudIoT is an emerging field of study that integrates the Cloud and the Internet of Things (IoT) to make machines smarter and deal with real-world objects in a distributed manner. It collects data from various devices and analyses it to increase efficiency and productivity. Because Cloud and IoT are complementary technologies with distinct areas of application, integrating them is difficult. This paper identifies various CloudIoT issues and analyzes them to make a relational model. The Interpretive Structural Modeling (ISM) approach establishes the interrelationship among the problems identified. The issues are categorised based on driving and dependent power, and a hierarchical model is presented. The ISM analysis shows that scheduling is an important aspect and has both (driving and dependence) power to improve the performance of the CloudIoT model. Therefore, existing CloudIoT job scheduling algorithms are analysed, and a cloud-centric scheduling mechanism is proposed to execute IoT jobs on a suitable cloud. The cloud implementation using an open-source framework to simulate Cloud Computing (CloudSim), based on the job's workload, is presented. Simulation results of the proposed scheduling model indicate better performance in terms of Average Waiting Time (AWT) and makespan than existing cloud-based scheduling approaches.

show abstract

An Efficient Clustering and Deep Learning Based Resource Scheduling for Edge Computing to Integrate Cloud-IoT

Cited by 14 publications

References 24 publications

An improved resource scheduling strategy through concatenated deep learning model for edge computing IoT networks

An improved resource scheduling strategy through concatenated deep learning model for edge computing IoT networks

AI-Empowered Fog/Edge Resource Management for IoT Applications: A Comprehensive Review, Research Challenges, and Future Perspectives

Interpretive Structural Modeling Based Assessment and Optimization of Cloud with Internet of Things (CloudIoT) Issues Through Effective Scheduling

Contact Info

Product

Resources

About