The next-generation wireless networks are evolving into very complex systems because of the very diversified service requirements, heterogeneity in applications, devices, and networks. The network operators need to make the best use of the available resources, for example, power, spectrum, as well as infrastructures. Traditional networking approaches, i.e., reactive, centrally-managed, one-size-fits-all approaches and conventional data analysis tools that have limited capability (space and time) are not competent anymore and cannot satisfy and serve that future complex networks regarding operation and optimization cost-effectively. A novel paradigm of proactive, self-aware, selfadaptive and predictive networking is much needed. The network operators have access to large amounts of data, especially from the network and the subscribers. Systematic exploitation of the big data dramatically helps in making the system smart, intelligent, and facilitates efficient as well as cost-effective operation and optimization. We envision data-driven next-generation wireless networks, where the network operators employ advanced data analytics, machine learning and artificial intelligence. We discuss the data sources and strong drivers for the adoption of the data analytics, and the role of machine learning, artificial intelligence in making the system intelligent regarding being self-aware, selfadaptive, proactive and prescriptive. A set of network design and optimization schemes are presented concerning data analytics. The paper concludes with a discussion of challenges and benefits of adopting big data analytics, machine learning, and artificial intelligence in the next-generation communication systems.

Due to high costs and power consumptions, fully digital baseband precoding schemes are usually prohibitive in millimeter-wave massive MIMO systems. Therefore,hybrid pre-coding strategies become the promising solutions. In this paper, we present a novel real-time yet high performance precoding strategy. Speci?cally, the eigenvectors corresponding to the larger eigenvalues of the right unitary matrix after singular value decomposition (SVD) on an array response matrix are used to abstract the angle information of an analog precoding matrix. As the obtained eigenvectors correspond to the larger singular values, the major phase information of channels is captured. In this way, the iterative search process for obtaining the analog precoding vectors is avoided, and thus hybrid precoding can be realized in parallel.To further improve its spectral-ef?ciency, we enlargetheresultantvectorsetbyinvolving morerelevantvectors in termof their correlationvalues withthe unconstrained optimal precoder, and a hybrid precoder is thus produced by using the vector set. Simulation results show that our proposed scheme achieves near the same performance as the orthogonal matching pursuit (OMP) does, whereas it costs much less complexities than the OMP, and thus can be realized in parallel.

This paper presents a design procedure for wireless power transfer (WPT) systems with the load-independent class-E inverter family. The design procedure guarantees that the WPT system will achieve constant output and soft switching in response to load variations without particular control, which can apply not only single-hop single-output but multi-hop multi-output WPT system designs. It is analytically explained that a WPT-system output type is determined by properly selecting inverter, rectifier, and coupling resonant structure. As a concrete design example, we designed the three-hop three-output WPT system for installation into a robot arm. Experimental results exemplified the validity and usefulness of the established procedure.

This article proposes a novel approach to onthe- fly establishment of multihop wireless access networks (OEMAN) for disaster response. OEMAN extends Internet connectivity from surviving access points to disaster victims using their own mobile devices. OEMAN is set up on demand using wireless virtualization to create virtual access points on mobile devices. Virtual access points greedily form a tree-based topology, configured automatically for naming and addressing, which is then used to provide multihop wireless Internet access to users. Ordinary users can easily connect to the Internet through OEMAN as if they are connected through conventional access points. After connecting, users naturally contribute to the network extension, realizing the self-supporting capability of a disaster's local communities. The proposed scheme establishes a wireless access network quickly, which is essential in emergency relief situations. Furthermore, OEMAN is transparent to users and cost effective as it does not require additional hardware. Experimental evaluations on top of our preliminary prototype over Windows-based laptops confirm OEMAN's feasibility and its effectiveness for multihop paths of up to seven hops, and standard Internet services such as audio and video streaming.

The concentration of fine particulate matter (PM2.5), which represents inhalable particles with diameters of 2.5 micrometers and smaller, is a vital air quality index. Such particles can penetrate deep into the human lungs and severely affect human health. This paper studies accurate PM2.5 prediction, which can potentially contribute to reducing or avoiding the negative consequences. Our approach’s novelty is to utilize the genetic algorithm (GA) and an encoder-decoder (E-D) model for PM2.5 prediction. The GA benefits feature selection and remove outliers to enhance the prediction accuracy. The encoder-decoder model with long short-term memory (LSTM), which relaxes the restrictions between the input and output of the model, can be used to effectively predict the PM2.5 concentration. We evaluate the proposed model on air quality datasets from Hanoi and Taiwan. The evaluation results show that our model achieves excellent performance. By merely using the E-D model, we can obtain more accurate (up to 53.7%) predictions than those of previous works. Moreover, the GA in our model has the advantage of obtaining the optimal feature combination for predicting the PM2.5 concentration. By combining the GA-based feature selection algorithm and the E-D model, our proposed approach further improves the accuracy by at least 13.7%.

In this paper, we conceive an advanced small cells wireless network deployment framework within a managed space under shared spectrum access paradigm. We also conceive a complementary business model, referred to as neutral host micro operator (NH-μO), that leverages a single shared wireless infrastructure to mutually benefit μO (a third party service provider), the owner of the space/facility, and mobile network operators (MNOs). The model is composed of a μO slice, which delivers a venue with customized wireless services tailored to the its local service requirements, and an MNO slice, which facilitates improved wireless coverage to visitors/end-users with subscriptions to several different MNOs. The NH-μO is not biased to favor any specific client, which can be enforced through a concrete commercial agreement. A radio access network slicing concept is exploited to support and optimize both the slice instances (SIs) efficiently in a shared manner on a single physical network infrastructure. In addition, we devise an efficient architecture for the NH-μO small cell base station and dynamic spectrum assignment control unit, and their required functionalities supporting sustainable coexistence of different SIs in shared spectrum. We also devise both interSI and intra-SI dynamic spectrum allocation policies considering time-varying requirements of different SIs. These policies take care of application level priority by providing a proper mixture of users with guaranteed quality of service and best-effort users, while ensuring a healthy SI competition. The advantages of the proposed framework are twofold. It enables the venue owner to manage its wireless networks and consider its very specific requirements while capitalizing from the MNO slice. This, in turn, reduces the need for deployment of new infrastructure while providing improved wireless coverage and savings to MNOs. Finally, our proposed framework leverages efficient utilization of spectrum, physical infrastructure, and computational resources. The simulation results exhibit various important features of the proposed shared spectrum access policies.