Fast, reliable, and low-latency data services are essential deliverables from telecom operators today. Realizing them is pushing operators to enhance infrastructure, expand network capacity and mitigate service degradation. Unlike other industries, though, telecom networks are vast monoliths comprising fiber optic cables, proprietary components, and legacy hardware. Because of this, there is less enhancing--and more shoring up the creaking infrastructure. Radio access networks (RAN) are the backbone of the telecommunications industry. However, the industry's propensity to incubate and evolve newer, cost-effective, and energy-efficient technologies has been slow due to monopolization by RAN component manufacturers.
If there is to be a "6G Wireless," its proponents will need to learn some significant lessons from the era of 5G. Already, 5G Wireless as a market strategy is four years old. The R&D divisions of telecommunications firms whose 5G rollouts are well under way, are now looking ahead to whatever the next version of wireless may be. . . So far, what they're seeing may be a bit far out. It's a capital improvement project the size of the entire planet, replacing one wireless architecture created this century with another one that aims to lower energy consumption and maintenance costs. "6G must deliver an outcome that is aligned with real needs," remarked David Lister, Head of 6G Research and Development Technology at Europe's Vodafone Group, "and deliver outcomes that are sustainable and commercially driven." Lister was speaking at an annual conference called the 6G Symposium. Yes, there is already an annual 6G Symposium. Back in 1998, the leading stakeholders in global telecommunications formed the 3GPP consortium, to officially designate which technologies belong to a "G" and which don't.
Vivaldi has released a major update for its eponymous web browser for privacy-minded power users. Version 4.0 bring with it a translation tool, along with beta versions of Vivaldi Mail, Calendar, and Feed Reader. The update is available now on Windows, Mac and Linux and Android devices. Vivaldi built its translation feature into its browser. The tool is powered by Lingvanex, a Cyprus-based company that makes translator's for a wider range of platforms including voice calls and smartwatches. As part of its focus on privacy, Vivaldi says that all your translation activity will be kept away from third-parties on its servers in Iceland.
Hip-hop artist TheHxliday is 19 years old and determined to have true creative control of his visuals as he makes his way up the music business. He's looking to a cell-phone company to achieve that. The Baltimore native, real name Noah Malik Lee, signed a deal with Motown Records last year and released his first major-label EP last week. To commemorate the occasion, he performed in a 20-minute "virtual world" hosted by Verizon on Friday (May 14th), appearing on fans' screens from an unreal landscape. Virtual effects swam around him -- but TheHxliday didn't pop up as an avatar inside a game, the way Travis Scott did with his Astroworld concert inside Fortnite, and the show wasn't meant to reproduce a concert the way Billie Eilish staged her full-length quarantine show.
IT equipment consists of products such as Personal computers (PCs), servers, monitors, storage devices etc. Software comprises of computer programs, firmware and applications. The IT & business services segment is further classified into consulting, custom solutions development, outsourcing services etc. The telecommunication equipment segment consists of telecom equipments such as switches, routers etc. The carrier services segment comprises of operations related revenue spent by telecom service provider on acquiring telecom capacity, primarily from overseas carrier. How Important Is Machine Learning as a Service (MLaaS)?
There are numerous potential use cases for ML in telecommunications networks (see Figure 1). In the area of system monitoring, anomaly detection systems are crucial for identifying performance issues and problematic network behavior. Proactively predicting the degradation of key performance indicators, and identifying the likely root cause, can help reduce and prevent outages. In the area of managed services, ML models can improve trouble ticket management by effectively classifying, prioritizing, and escalating incidents. Capacity planning and customer retention can be improved through explainable churn prediction.
Last year Qualcomm started rolling out its first chips for Android phones that supported upgradeable GPU drivers to optimize performance, so now it's doing a similar thing for on-device AI and machine learning. Droid-Life points out that during Google I/O, Google and Qualcomm have announced updatable neural network API drivers, representing a new model that will roll out along with Android 12. While NN API drivers have usually been updated along with major OS updates, now the companies say they can roll out quickly via Google Play Services. Even better, the updates will be available for older chipsets and multiple versions of Android. In an I/O presentation about advancements in machine learning, Google developers said the NN API could boost performance as though the phone had two additional CPU cores, while using less power and creating less heat.
Qualcomm has officially launched the Snapdragon 778G 5G processor, which will power the Honor 50 series and other upcoming mid-to-high-end devices. It joins the Snapdragon 780G, which Qualcomm introduced in March, as one of the company's options for upper mid-range phones. The 778G SoC uses Kryo 670 CPU, which Qualcomm says can enhance overall CPU performance by 40 percent. Meanwhile, its Adreno 642L GPU is designed to deliver up to 40 percent faster graphics rendering compared to the previous generation. The chipset comes with the latest (6th generation) Qualcomm AI Engine, as well.
Federated learning has attracted attention in recent years for collaboratively training data on distributed devices with privacy-preservation. The limited network capacity of mobile and IoT devices has been seen as one of the major challenges for cross-device federated learning. Recent solutions have been focusing on threshold-based client selection schemes to guarantee the communication efficiency. However, we find this approach can cause biased client selection and results in deteriorated performance. Moreover, we find that the challenge of network limit may be overstated in some cases and the packet loss is not always harmful. In this paper, we explore the loss tolerant federated learning (LT-FL) in terms of aggregation, fairness, and personalization. We use ThrowRightAway (TRA) to accelerate the data uploading for low-bandwidth-devices by intentionally ignoring some packet losses. The results suggest that, with proper integration, TRA and other algorithms can together guarantee the personalization and fairness performance in the face of packet loss below a certain fraction (10%-30%).
Alarm root cause analysis is a significant component in the day-to-day telecommunication network maintenance, and it is critical for efficient and accurate fault localization and failure recovery. In practice, accurate and self-adjustable alarm root cause analysis is a great challenge due to network complexity and vast amounts of alarms. A popular approach for failure root cause identification is to construct a graph with approximate edges, commonly based on either event co-occurrences or conditional independence tests. However, considerable expert knowledge is typically required for edge pruning. We propose a novel data-driven framework for root cause alarm localization, combining both causal inference and network embedding techniques. In this framework, we design a hybrid causal graph learning method (HPCI), which combines Hawkes Process with Conditional Independence tests, as well as propose a novel Causal Propagation-Based Embedding algorithm (CPBE) to infer edge weights. We subsequently discover root cause alarms in a real-time data stream by applying an influence maximization algorithm on the weighted graph. We evaluate our method on artificial data and real-world telecom data, showing a significant improvement over the best baselines.