Abstract 5G and beyond communication technologies have started to spread around the world. Higher frequencies lead 5G base stations to have small coverage areas. Besides, the wireless network users have mobility and may move fast among the base stations. Software‐defined networking (SDN) is a promising network solution for dynamic and dense networks such as 5G networks. The handover process defines the transfer of mobile users' connections among the base stations and the handover has to happen frequently in ultra‐dense networks. In this study, we aim to construct a more robust handover based on long short‐term memory (LSTM) with SDN in terms of the number of handover and handover failures. LSTM, linear regression, support vector machine, and tree algorithms performances have been investigated for handover. According to the R2 values of LSTM, SVM, tree, linear regression results are obtained as 0.998, 0.980, 0.980, and 0.75, respectively. Root mean square error, coefficient of determination (R), mean squared error, and mean absolute deviation statistics prove the improvement of the handover mechanism. In the proposed approach, approximately 30% reduction in the HO failure ratio and 22.22% reduction number of handover have been observed.

Summary The Internet of Things (IoT) concept increases the spectrum demands of mobile users in wireless communications because of the intensive and heterogeneous structure of IoT. Various devices are joining IoT networks every day, and spectrum scarcity may be a crucial issue for IoT environments in the near future. Cognitive radio (CR) is capable of sensing and detecting spectrum holes. With the aim of CR, more powerful IoT devices will be constructed in such crowded wireless environments. Also, dynamic and ad‐hoc CR networks have not a fixed base station. Therefore, CR capable IoT (CR‐based IoT) device approach with routing capabilities will be a solution for future IoT environments. In this study, spectrum aware Ad hoc on‐demand distance vector routing protocol is proposed for CR‐based IoT devices in IoT environments. For the performance analysis of the proposed method, various network scenarios with different idle probability have been performed and throughput and delay results for different offered loads have been analyzed.

Abstract In this article, the Internet of Medical Things (IoMT) framework based on Apache Spark big data processing technology is proposed for real‐time analysis of health data obtained from wireless body area networks (WBANs), which is one of the most important components of IoMT. The proposed framework consists of four layers: data source, data collection, data analytics and visualization. In addition, the proposed IoMT framework is presented with two different disease prediction scenarios, diabetes and heart disease. Diabetes and heart disease prediction processes are carried out using the random forest (RF), logistic regression (LR) and support vector machine (SVM) algorithms belonging to the Apache Spark machine learning library (MLlib). The analysis of health data generated in WBANs takes place in real‐time in the Apache Spark‐based data analytics layer. In this study, the performances of MLlib algorithms in the real‐time model developed for heart and diabetes disease are examined. The SVM algorithm with an accuracy rate of 93.33% for heart disease and the LR algorithm with an accuracy rate of 78.89% for diabetes are found to provide the best performances.

Internet of Medical Things (IoMT) as a next-generation network requires heterogeneous services, technologies, and equipment infrastructure management resulting in more complex systems. The software-defined networking (SDN) approach has emerged as a promising solution to reduce this complexity by proposing a vendor-independent structure that disaggregates the control and data planes. In this study, an architecture based on the SDN is proposed for such heterogeneous and complex IoMT networks. A new controller that supports different wireless communication protocols has been developed for the control plane. We propose machine learning (ML)-based load balancing and time-sensitive prioritization (MLA) algorithms for dense and dynamic networks. An SDN-based IoMT network that consists of IEEE 802.15.6, TDMA, and IEEE 802.11 protocols is analyzed in a simulation program simultaneously using various scenarios in terms of throughput, delay, packet loss ratio, bit error rate, and user density parameters. In addition, in this study, a new data set is created for load balancing. The performances of support vector machine (SVM), ensemble of decision trees, k-NN, and Naive Bayes ML algorithms are compared, and SVM gives the best result with 95.1% accuracy.

In this study, a new network architecture based on the software‐defined networking (SDN) approach is proposed for cognitive radio networks (CRNs). The proposed network architecture [software‐defined cognitive radio (SDCR)] assumes the responsibilities of network resource management for CRNs and provides a dynamic spectrum management mechanism with an SDN controller. In this way, the dependency of network users on base stations is reduced in dynamic cognitive radio environments, and network performance is improved by delegating some of the management responsibilities to the controller. The performance analysis of the SDCR is carried out through the RIVERBED MODELER simulation software. End‐to‐end delays and packet loss rates for the primary network are investigated by selecting different offered loads for secondary users. In addition, for the equal and different packet sizes, primary network and SDCR throughput are examined and network performance is improved by using channel bonding technique. The results indicate that the SDCR outperforms the traditional CRN architecture, in terms of the throughput, and the proposed architecture can provide effective performance. Bit error rate parameter is investigated in the study and the energy consumption parameter of the SDCR is also compared with the cognitive radio wireless network.