The future is fast, according to the experts. But it feels like it is arriving a little slowly. Phone and network experts have spent the week trying to make the world excited about 5G and the possibilities it offers for data connections – though when the promised 10 times faster speed will arrive, and how, is a little more complicated than they would like to make it sound. The Mobile World Congress is the annual event where the phone and carrier industry gather together in a huge Barcelona conference centre and talk about the future. And everything they had to say about that future sounded mostly the same: 5G, the new data connections that are about to disrupt just about every industry, according to its proponents.

Wireless communication systems operate in complex time-varying environments. Therefore, selecting the optimal configuration parameters in these systems is a challenging problem. For wireless links, rate selection is used to select the optimal data transmission rate that maximizes the link throughput subject to an application-defined latency constraint. We model rate selection as a stochastic multi-armed bandit (MAB) problem, where a finite set of transmission rates are modeled as independent bandit arms. For this setup, we propose Con-TS, a novel constrained version of the Thompson sampling algorithm, where the latency requirement is modeled by a linear constraint on arm selection probabilities. Since our algorithm learns a Bayesian model of the wireless link, it can be adapted to exploit prior knowledge often available in practical wireless networks. Through numerical results from simulated experiments, we demonstrate that Con-TS significantly outperforms state-of-the-art bandit algorithms proposed in the literature. Further, we compare Con-TS with the outer loop link adaptation (OLLA) scheme, which is the state-of-the-art in practical wireless networks and relies on carefully tuned offline link models. We show that Con-TS outperforms OLLA in simulations, further, it can elegantly incorporate information from the offline link models to substantially improve performance.

Washington says Huawei could be compelled by Beijing to spy on or disable foreign telecom networks that use its equipment. The Trump administration has been particularly focused on dissuading allies from using Huawei gear in their rollout of 5G--the next-generation mobile networks that promise to connect more things, including self-driving cars and factory components, to the internet. In a sign of the challenges ahead for U.S. officials, though, the trade show here has offered Huawei the opportunity to tout new deals with America's friends. It used this week's Mobile World Congress, rebranded this year as MWC Barcelona, to announce a high-profile agreement with the biggest carrier in the United Arab Emirates, one of America's closest Mideast allies, to build that country's first 5G network. Despite facing off on European soil, Huawei is benefiting from the sense of a home-court advantage here.

We consider the band assignment (BA) problem in dual-band systems, where the basestation (BS) chooses one of the two available frequency bands (centimeter-wave and millimeter-wave bands) to communicate with the user equipment (UE). While the millimeter-wave band might offer higher data rate, there is a significant probability of outage during which the communication should be carried on the (more reliable) centimeter-wave band. We consider two variations of the BA problem, one-shot and sequential BA. For the former the BS uses only the currently observed information to decide whether to switch to the other frequency band, for the sequential BA, the BS uses a window of previously observed information to predict the best band for a future time step. We provide two approaches to solve the BA problem, (i) a deep learning approach that is based on Long Short Term Memory and/or multi-layer Neural Networks, and (ii) a Gaussian Process based approach, which relies on the assumption that the channel states are jointly Gaussian. We compare the achieved performances to several benchmarks in two environments: (i) a stochastic environment, and (ii) microcellular outdoor channels obtained by ray-tracing. In general, the deep learning solution shows superior performance in both environments.

In this paper, the distributed edge caching problem in fog radio access networks (F-RANs) is investigated. By considering the unknown spatio-temporal content popularity and user preference, a user request model based on hidden Markov process is proposed to characterize the fluctuant spatio-temporal traffic demands in F-RANs. Then, the Q-learning method based on the reinforcement learning (RL) framework is put forth to seek the optimal caching policy in a distributed manner, which enables fog access points (F-APs) to learn and track the potential dynamic process without extra communications cost. Furthermore, we propose a more efficient Q-learning method with value function approximation (Q-VFA-learning) to reduce complexity and accelerate convergence. Simulation results show that the performance of our proposed method is superior to those of the traditional methods.

At $3,500 apiece, Microsoft's HoloLens 2 may not be the transformational consumer device we were all hoping to buy. But the company addressed many of the shortcomings of the original HoloLens at the Mobile World Congress launch of the second generation, holding out hope that we may one day see a more consumer-oriented product. As Microsoft has signaled for several years now, HoloLens 2 is designed to work with its Azure cloud and business customers, complete with an intriguing new Remote Rendering technology that implies Microsoft's using the power of its Azure cloud to boost the HoloLens headset's image processing capabilities. Epic chief Tim Sweeney appeared on stage to endorse HoloLens and bring the Unreal engine to HoloLens beginning in May. He did not announce a HoloLens-specific game, though.

I almost missed out on the vanguard of the 5G robot revolution because I don't drink coffee. The near miss occurred on Monday at mobile network trade association GSMA's booth at MWC Barcelona (formerly called Mobile World Congress), where Dal.Komm Coffee was demonstrating a coffee-serving robot. Thankfully for non-coffee drinking weirdos like me, hot chocolate was also available. After placing an order via a smartphone nearby, a robotic arm behind a glass panel juggled cups, operated coffee makers, and gently placed drinks on trays so they could be collected by waiting humans. According to a representative of Dal.Komm, the robot's precise movement was only possible with a 5G network provided by the KT Corporation, the Korean teleco.

Sébastien is passionate about artificial intelligence, which inspired him to build Loud ML -- software that enables engineers to implement AI-driven applications 10 times faster. After gaining expertise in building embedded Linux software for telecommunications and Internet service providers, he launched Loud ML in 2018. He joined the Rockstart AI accelerator program in the Netherlands later the same year. In his spare time, Sébastien runs workshops to motivate others to enter the AI arena. He enjoys blues music and artists such as John Mayer.

BARCELONA, SPAIN - A global battle between the U.S. government and Chinese tech company Huawei over allegations that it is a cybersecurity risk overshadowed the opening Monday of the world's biggest mobile industry trade fair. Huawei has an outsize presence at MWC Barcelona, from its displays in three separate show halls down to its red sponsorship logo adorning visitor pass lanyards. The focus at this year's meeting is new 5G networks due to roll out in the coming years. But the dispute over Huawei, the world's biggest maker of networking gear, is casting a pall. The United States government dispatched a big delegation to press its case with telecom executives and government officials that they should not use Huawei as a supplier over national security concerns.

The telecoms industry is gearing up for 5G, the next generation wireless networks which could enable new technologies such as self-driving cars and robot surgeons. But it may be raising expectations too early. As industry leaders gather at the Mobile World Congress trade fair in Barcelona this week, some warn consumers risk disappointment because the benefits 5G's much faster speeds and vast data capacity can provide are still a long way from becoming reality. For example while 5G will bring near-instantaneous connectivity for smartphones and can virtually eliminate latency -- the lag-time when data is sent or received -- this'will only be a reality in 2023-2025', said Yannick Sadowy, the director for telecoms and media and consulting firm Accenture. The telecoms industry is gearing up for 5G, the next generation wireless networks which could enable new technologies such as self-driving cars and robot surgeons.