Big Data Based Self-Optimization Networking in Next Generation Mobile Networks

• Published in: Wireless personal communications Vol. 101; no. 3; pp. 1499 - 1518
• Main Authors: Mirzaei Somarin, Abbas, Barari, Morteza, Zarrabi, Houman
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.08.2018; Springer Nature B.V
• Subjects: Big Data; Communications Engineering; Computer Communication Networks; Data analysis; Data management; Decision analysis; Decision making; Efficiency; Engineering; Expert systems; Feature extraction; Machine learning; Mathematical models; Networks; Optimization; Optimization techniques; Parameters; Resource allocation; Response time; Signal,Image and Speech Processing; Support vector machines; Wireless networks; Next generation mobile networks; Big data; Quality of service (QoS); Load-balanced gradient power allocation; Self-optimization networking
• ISSN: 0929-6212; 1572-834X
• DOI: 10.1007/s11277-018-5774-6

Using self-optimization techniques is the only viable solution for increasing the efficiency in next generation mobile networks. The goal of proposing a self-optimization model is to maximize the network efficiency and increase the quality of services provided to microcell and femto-cell users, considering the limited resources in radio access networks. To increase the model efficiency, we applied the big data technique for analyzing data and increasing the accuracy of the decision-making process. Based on the meaningful extracted information, the SON decision maker will be able to adjust network parameters and resource allocation factors in a more intelligent manner. The experimental results show that despite the tremendous volume of the analyzed data—which is hundreds of times bigger than usual methods—it is possible to improve the KPIs, such as throughput, up to 30% by optimal resource allocation and reducing the signaling load. Also, the presence of feature extraction and parameter selection modules will reduce the response time of the self-optimization model up to 25% when the number of parameters is too high. Moreover, numerical results indicate the superiority of using support vector machine learning algorithm. It improves the accuracy level of decision making based on the rule-based expert system. Finally, uplink quality improvement and 15% increment of the coverage area under satisfied SINR conditions can be considered as outcome of the proposed scheme.