DLJSF: Data-Locality Aware Job Scheduling IoT tasks in fog-cloud computing environments

• DOI: 10.1016/j.rineng.2024.101780
• Publication Date: 2024-01-17T08:52:15Z
• Authors: Edris Khezri; Rebaz Othman Yahya; Hiwa Hassanzadeh; Mohsen Mohaidat; Sina Ahmadi; Mohammad Trik
• Keywords: Fog Computing

Nowadays, devices generate copious quantities of high-speed data streams due to Internet Things (IoT) applications. For the most part, cloud computing platforms handle and manage all these requests. However, for certain applications, transmission delay that comes with transferring from edge could be unbearable. When there are a lot connected internet, public network actually becomes bottleneck transfer. In this setting, power management, storage, resource service management necessitate more robust infrastructure complex processes. More efficient use resources is achievable fog computing's "intelligent gateway" capability. Planning managing one important factors affecting system performance (especially latency) in fog-cloud environment. an environment clouds NP-hard problem. This paper delves into optimisation difficulty longevity data-intensive job scheduling cloud-based IoT systems. The issue initially expressed as model integer linear programming (ILP). Next, we provide heuristic algorithm known DLJSF (Data-Locality Aware Job Scheduling Fog-Cloud) based on suggested formulation. results tests showed proposed close by average 87 %. Also, average, it 99.16 % better than LP obtained optimal solution solver processed locally. To check efficiency simulation solution, was repeated tasks different entry rates sizes. According documents, transfer approach can valuable has not lost its conditions.