Digital Twin (DT) technology has recently emerged as a powerful tool with the potential to revolutionize wireless systems as it enables accurate simulations, better decision-making, and tangible operational improvements. Prior studies on DT within the context of next generation wireless technologies has primarily focused on identifying potential use cases, application scenarios, and standardization challenges. However, the existing research lacks translating theoretical ideas into real-world applications. Our research, in this paper, contributes to the practical realization of DT technology in the context of 6G wireless networks, demonstrating its potential impact on network planning, performance, and user experience. In particular, we explore the construction, validation, and applications of DTs utilizing an indoor over-the-air (OTA) testbed powered by an in-house developed Next Generation Radio Access Network (NGRAN) that is fully compliant with 3rd Generation Partnership Project (3GPP) and Open RAN standards. First, we describe the steps that were followed to construct and validate a high-fidelity DT of our OTA testbed modeling both Radio Frequency (RF) environment and system components. Then, we demonstrate two pre-deployment use cases by explaining our extensive coverage estimation and network capacity planning OTA tests. Lastly, we also explore how DT enables practical machine learning solutions for post-deployment use cases and share our comprehensive OTA performance results, highlighting that our proposed mobility technique outperforms the classical approaches in terms of throughput and number of undesired handovers.

Modern large-scale online service providers typically deploy microservices into containers to achieve flexible service management. One critical problem in such container-based microservice architectures is to control the arrival rate of requests in the containers to avoid containers from being overloaded. In this article, we present our experience of rate limit for the containers in Alibaba, one of the largest e-commerce services in the world. Given the highly diverse characteristics of containers in Alibaba, we point out that the existing rate limit mechanisms cannot meet our demand. Thus, we design Noah, a dynamic rate limiter that can automatically adapt to the specific characteristic of each container without human efforts. The key idea of Noah is to use deep reinforcement learning (DRL) that automatically infers the most suitable configuration for each container. To fully embrace the advantages of DRL in our context, Noah addresses two technical challenges. First, Noah uses a lightweight system monitoring mechanism to collect container status. In this way, it minimizes the monitoring overhead while ensuring a timely reaction to system load changes. Second, Noah injects synthetic extreme data when training its models. Thus, its model gains knowledge on unseen special events and hence remains highly available in extreme scenarios. To guarantee model convergence with the injected training data, Noah adopts task-specific curriculum learning to train the model from normal data to extreme data gradually. Noah has been deployed in the production of Alibaba for two years, serving more than 50000 containers and around 300 types of microservice applications. Experimental results show that Noah can well adapt to three common scenarios in the production environment. It effectively achieves better system availability and shorter request response time compared with four state-of-the-art rate limiters.

We report XLINK, a multi-path QUIC video transport solution with experiments in Taobao short videos. XLINK is designed to meet two operational challenges at the same time: (1) Optimized user-perceived quality of experience (QoE) in terms of robustness, smoothness, responsiveness, and mobility and (2) Minimized cost overhead for service providers (typically CDNs). The core of XLINK is to take the opportunity of QUIC as a user-space protocol and directly capture user-perceived video QoE intent to control multi-path scheduling and management. We overcome major hurdles such as multi-path head-of-line blocking, network heterogeneity, and rapid link variations and balance cost and performance.

Through surveys of 1,673 students, 1,685 parents, 1,013 teachers, 9,693 principals, and 1,865 superintendents across the United States, this study explores perceptions, access, and barriers to computer science education at the K-12 level. We found most respondents were unable to distinguish computer literacy activities from computer science, with female, Black, or Hispanic respondents even less likely to do so. Perceptions of who does computer science were narrow and stereotypical (White, male, smart), but there was high value and demand for computer science across all populations, particularly among parents. Results indicate discrepancies in access to technology and computer science. Over 75% of principals reported their school did not offer computer science with programming/coding, but Hispanic students reported lower exposure to computers at home and in school and Black students and lower income students reported less access to computer science learning in school. Hispanic students and female students were also less likely to have learned computer science or have confidence to learn computer science compared to their counterparts. Finally, we explored barriers to access and identified a harsh disconnect: parent and student demand for computer science education was high while administrators' perceptions of this demand was low. Additionally, the most common barriers to offering computer science cited by principals and superintendents were the need to dedicate time to other courses and testing requirements and the lack of qualified teachers, with technology less common of a barrier.

Increasing women's participation in computer science is a critical workforce and equity concern. The technology industry has committed to reversing negative trends for women in computer science as well as engineering and information technology "computing" fields. Building on previously published research, this paper identifies factors that influence young women's decisions to pursue computer science-related degrees and the ways in which these factors differ for young men. It is based on a survey of 1,739 high school students and recent college graduates. Results identified encouragement and exposure as the leading factors influencing this critical choice for women, while the influence of these factors is different for men. In particular, the influence of family is found to play a critical role in encouragement and exposure, and outreach efforts should focus on ways to engage parents.

Increasing women's participation in Computer Science (CS) is a critical workforce and equity concern. The technology industry has committed to reversing negative trends for women in CS, engineering, and related fields. Building on previous research, we surveyed 1,739 high school students and recent college graduates to understand factors influencing decisions to pursue CS-related college degrees. Results indicate social encouragement, career perception, academic exposure, and self perception are the leading factors for women, while the influence of these factors is different for men. These factors are actionable, and understanding differences in their influence on men and women will inform our approaches to achieving gender parity in tech.