In the broad scientific field of time series forecasting, the ARIMA models and their variants have been widely applied for half a century now due to their mathematical simplicity and flexibility in application. However, with the recent advances in the development and efficient deployment of artificial intelligence models and techniques, the view is rapidly changing, with a shift towards machine and deep learning approaches becoming apparent, even without a complete evaluation of the superiority of the new approach over the classic statistical algorithms. Our work constitutes an extensive review of the published scientific literature regarding the comparison of ARIMA and machine learning algorithms applied to time series forecasting problems, as well as the combination of these two approaches in hybrid statistical-AI models in a wide variety of data applications (finance, health, weather, utilities, and network traffic prediction). Our review has shown that the AI algorithms display better prediction performance in most applications, with a few notable exceptions analyzed in our Discussion and Conclusions sections, while the hybrid statistical-AI models steadily outperform their individual parts, utilizing the best algorithmic features of both worlds.

The present article carries out a review of MIMO-based techniques that have been recently proposed for satellite communications. Due to the plethora of MIMO interpretations in terrestrial systems and the particularities of satellite communications, this review is built on two pillars, namely fixed satellite and mobile satellite. Special attention is given to the characteristics of the satellite channel, which will ultimately determine the viability of MIMO over satellite. Finally, some future research directions are identified.

The increasing demand for high-speed multimedia services and the underutilization of scarce satellite spectral resources have recently led the researchers to propose the concept of cognitive satellite terrestrial networks. Considering this novel architecture, we propose an efficient resource management mechanism for the terrestrial network that acts as the secondary system. We introduce a new power allocation algorithm that optimizes the effective capacity of the terrestrial link for given Quality of Service (QoS) requirements while guaranteeing a specified outage probability for the satellite link. Both perfect and imperfect channel estimation cases are considered in the power allocation scheme and analytical results are presented. Numerical calculations evaluate the performance of the proposed scheme.

Summary: The space environment is still challenging but is becoming more and more attractive for an increasing number of entities. In the second half of the 20th century, a huge amount of funds was required to build satellites and gain access to space. Nowadays, it is no longer so. The advancement of technologies allows producing very small hardware components able to survive the strict conditions of the outer space. Consequently, small satellites can be designed for a wide set of missions keeping low design times, production costs, and deployment costs. One widely used type of small satellite is the CubeSat, whose different aspects are surveyed in the following: mission goals, hardware subsystems and components, possible network topologies, channel models, and suitable communication protocols. We also show some future challenges related to the employment of CubeSat networks.