The rapid development of Industrial Internet of Things (IIoT) requires industrial production towards digitalization to improve network efficiency. Digital Twin is a promising technology to empower the digital transformation of IIoT by creating virtual models of physical objects. However, the provision of network efficiency in IIoT is very challenging due to resource-constrained devices, stochastic tasks, and resources heterogeneity. Distributed resources in IIoT networks can be efficiently exploited through computation offloading to reduce energy consumption while enhancing data processing efficiency. In this paper, we first propose a new paradigm Digital Twin Networks (DTN) to build network topology and the stochastic task arrival model in IIoT systems. Then, we formulate the stochastic computation offloading and resource allocation problem to minimize the long-term energy efficiency. As the formulated problem is a stochastic programming problem, we leverage Lyapunov optimization technique to transform the original problem into a deterministic per-time slot problem. Finally, we present Asynchronous Actor-Critic (AAC) algorithm to find the optimal stochastic computation offloading policy. Illustrative results demonstrate that our proposed scheme is able to significantly outperforms the benchmarks.

The weather is hot, the trees brimming with life … " So begins the baritone voice-over in a video shot in the summer of 2018 by the Chinese telecommunications giant Huawei and posted to YouTube. It chronicles a corporate event in the slightly corny style of a 1960s educational film, starting with aerial drone footage of Huawei's campus--an island of lush greenery surrounded by the high-rise buildings of the city known as China's Silicon Valley. A spirited orchestral version of Beethoven's "Turkish March" plays as a town car wends its way through the campus, pulling up to a stately white structure mixing classical Greek architecture and the wide overhanging rooftops of China's great pagodas. There's a bit of the White House tossed in too. This feature appears in the December 2020/January 2021 issue.

Due to the high variability of the traffic in the radio access network (RAN), fixed network configurations are not flexible to achieve the optimal performance. Our vendors provide several settings of the eNodeB to optimize the RAN performance, such as media access control scheduler, loading balance, etc. But the detailed mechanisms of the eNodeB configurations are usually very complicated and not disclosed, not to mention the large KPIs space needed to be considered. We aim to build an intelligent controller without strong assumption or domain knowledge about the RAN and can run for 24/7 without supervision. To achieve this goal, we first build a closed-loop control testbed RAN in a lab environment with one eNodeB provided by one of the largest wireless vendors and four smartphones. Next, we build a double Q network agent that is trained with the live feedbacks of the key performance indicators from the RAN.

At this Startup School, participants will familiarize with the specialized training courses needed for the development of business in the field of Artificial Intelligence (AI).

Huawei's Rotating Chairman Guo Ping kicked off this year's Huawei Connect event with his keynote Creating New Value with synergy across five tech domains, where these domains are Connectivity, Computing, Cloud, AI and Applications. It is not a secret that Huawei excels in these fields and Guo Ping could of course have showcased all these accomplishments and shine a bright light on all the exciting new tech coming up. But he did not for a very clear reason. This has always been an important factor in the success story of Huawei, but it has not been as clearly expressed before as in Guo Ping's keynote. The way I experienced the keynote is that there is a very clear and much needed commitment from Huawei to its partners: we will continue to drive innovation to bring value to us all. "Us" and "we" are very common words in the communication of Huawei, and Guo Ping showed that this is not just a marketing thing.

Federated learning enables training a global model from data located at the client nodes, without data sharing and moving client data to a centralized server. Performance of federated learning in a multi-access edge computing (MEC) network suffers from slow convergence due to heterogeneity and stochastic fluctuations in compute power and communication link qualities across clients. We propose a novel coded computing framework, CodedFedL, that injects structured coding redundancy into federated learning for mitigating stragglers and speeding up the training procedure. CodedFedL enables coded computing for non-linear federated learning by efficiently exploiting distributed kernel embedding via random Fourier features that transforms the training task into computationally favourable distributed linear regression. Furthermore, clients generate local parity datasets by coding over their local datasets, while the server combines them to obtain the global parity dataset. Gradient from the global parity dataset compensates for straggling gradients during training, and thereby speeds up convergence. For minimizing the epoch deadline time at the MEC server, we provide a tractable approach for finding the amount of coding redundancy and the number of local data points that a client processes during training, by exploiting the statistical properties of compute as well as communication delays. We also characterize the leakage in data privacy when clients share their local parity datasets with the server. We analyze the convergence rate and iteration complexity of CodedFedL under simplifying assumptions, by treating CodedFedL as a stochastic gradient descent algorithm. Furthermore, we conduct numerical experiments using practical network parameters and benchmark datasets, where CodedFedL speeds up the overall training time by up to $15\times$ in comparison to the benchmark schemes.

SoftBank Group Corp. is in talks to sell robot maker Boston Dynamics Inc. to Hyundai Motor Co., people familiar with the matter said. Proposed terms of the deal would give the South Korean automaker control of the robotics company in a transaction valued at as much as $1 billion, said one of the people, all of whom asked not to be identified because the discussions are private. The terms have yet to be finalized, and the deal could fall apart, said the people. Representatives for Boston Dynamics, Hyundai and SoftBank declined to comment on the deal talks. In emailed statements, Hyundai said it's "continuously exploring various investment and partnership opportunities." Boston Dynamics said its work "continues to excite partners interested in exploring a deeper commercial relationship with our company."

Due to the high variability of the traffic in the radio access network (RAN), fixed network configurations are not flexible to achieve the optimal performance. Our vendors provide several settings of the eNodeB to optimize the RAN performance, such as media access control scheduler, loading balance, etc. But the detailed mechanisms of the eNodeB configurations are usually very complicated and not disclosed, not to mention the large KPIs space needed to be considered. These make constructing simulator, offline tuning, or rule-based solutions difficult. We aim to build an intelligent controller without strong assumption or domain knowledge about the RAN and can run for 24/7 without supervision. To achieve this goal, we first build a closed-loop control testbed RAN in a lab environment with one eNodeB provided by one of the largest wireless vendors and four smartphones. Next, we build a double Q network agent that is trained with the live feedbacks of the key performance indicators from the RAN. Our work proved the effectiveness of applying deep reinforcement learning to improve network performance in a real RAN network environment.

Networks are evolving to meet user demands. Main qualities which make conventional internet successful are heterogeneity and generality combining with user transparency and rich functionality for end-to-end systems. In today's world networks display characteristics of unstable convoluted systems. Till date most networks are murky to its applications and providing only best effort delivery of packets with little or zero information about the reliability and performance characteristics of different paths. Granting, this design works well for simple server-client model, many emerging technologies such as: NFV (Network Function Virtualization [8], IoT (Internet of Things) [9], Software Defined Networking [10], CDN (Content Delivery Networks) [11] and LTE (Long-Term Evolution) [12] and 5G Cellular Networks [13] heavily depend on affluent information about the state of the network. For example, author in [14] described, if VNFs (Virtual Network Functions) [15] are not aware of the traffic on virtio interfaces assisting hypervisor, then this might result in a bottleneck in NFV infrastructure. In other words, VNFs should know the state of the network (in terms of traffic) to accelerate applications hosted across VNFs in NFV infrastrucutre. Authors in [16] explained the need of the data storage as the number of connected IoT devices are increasing on unprecedented level [17]. In order to optimize the data storage, it is imperative for IoT nodes to know about the other nodes and their transportation method of moving data among networks.

Applications of intelligent reflecting surfaces (IRSs) in wireless networks have attracted significant attention recently. Most of the relevant literature is focused on the single cell setting where a single IRS is deployed, while static and perfect channel state information (CSI) is assumed. In this work, we develop a novel methodology for multi-IRS-assisted multi-cell networks in the uplink. We formulate the sum-rate maximization problem aiming to jointly optimize the IRS reflect beamformers, base station (BS) combiners, and user equipment (UE) transmit powers. In this optimization, we consider the scenario in which (i) channels are dynamic and (ii) only partial CSI is available at each BS; specifically, scalar effective channels of local UEs and some of the interfering UEs. In casting this as a sequential decision making problem, we propose a multi-agent deep reinforcement learning algorithm to solve it, where each BS acts as an independent agent in charge of tuning the local UEs transmit powers, the local IRS reflect beamformer, and its combiners. We introduce an efficient message passing scheme that requires limited information exchange among the neighboring BSs to cope with the non-stationarity caused by the coupling of actions taken by multiple BSs. Our numerical simulations show that our method obtains substantial improvement in average data rate compared to several baseline approaches, e.g., fixed UEs transmit power and maximum ratio combining.