A novel hybrid arithmetic optimization algorithm and salp swarm algorithm for data placement in cloud computing

Abstract

In recent years, the Internet of Things (IoT) has led to the spread of cloud computing devices in all commercial, industrial and agricultural sectors. The use of cloud computing environment services is increasing exponentially with all technology applications based on IoT. Fog computing has led to addressing issues in cloud computing environments. Fog computing reduces load balancing, processing, bandwidth, and storage as data file replication from the cloud to the network closest to sensors in different geographic locations. Traditional cloud computing leads to an increase in response time and processing time, and processing in the performance of data replication. We need replication strategies to meet users' requirements across different geographic locations while effectively harnessing fog computing capabilities to optimally select and place data replication of IoT services on cloud resources. In this strategy, the identification and mode of the data replication problem are designed as a multi-objective optimization problem that considers the heterogeneity of resources, least cost path, distance, and applications based on replication requirements. Firstly, a new hybrid metaheuristic method, using the Arithmetic Optimization Algorithm (AOA) and the salp swarm algorithm (SSA), is proposed to handle the problem of selection and placement data replication in fog computing. This strategy, called AOASSA, depends on using fog computing to optimally select and place data replication of IoT services on cloud resources. Secondly, the Floyd algorithm is used to strategy the least cost path, distance, and data transmission in different geographic locations. To validate the AOASSA strategy a set of experiments was carried out to validate the proposed strategy AOASSA. The performance of AOASSA is tested and compared with other swarm intelligence. Experiment results show the superiority of AOASSA over its competitors in terms of performance measures, such as least cost path, distance, and bandwidth.

Earth Video Cube: A Geospatial Data Cube for Multisource Earth Observation Video Management and Analysis

“…[39] introduces the Continuous Media File System and proposes a hybrid database management approach employing SQL and NoSQL databases, aiming at scalable storage architecture and distributed scheduling. [40] introduces a new hybrid metaheuristic method for data placement in fog computing, showing improved performance in terms of selection and placement data replication. [41] uses videolike lossless compression (VLLC) and designs an algorithm for organizing and storing these VLLC data cubes in cloud servers, which supports cost-effective big data query with parallel processing.…”

Network Optimization of Carbon Monoxide Sensor Nodes in the Metropolitan Region of São Paulo

“…In [24], the employs and mode of the data replication problem are designed as a multi-objective optimization problem that considers the heterogeneity of resources, least cost path, distance, and applications based on replication requirements. Firstly, a new hybrid meta-heuristic method, using the arithmetic optimization algorithm (AOA) and the salp swarm algorithm (SSA), is proposed to handle the problem of selection and placement data replication in fog computing.…”

Enhancing Global Optimization Performance of Arithmetic Optimization Algorithm with a Modified Population Initialization Scheme

“…Like other MSAs, achieving a proper balance between exploration and exploitation is crucial for enhancing AOA's performance. Consequently, several enhancement schemes, including hybridization [15], [16], [17], the introduction of new learning mechanisms [18], [19], [20] and others, have been developed to improve the balance in AOA variants. Since its introduction, both the original AOA and its enhanced variants have been successfully applied to a wide array of engineering optimization problems [15], [16], [19], [21], [22], [23], [24], [25].…”