Serverless computing, with its ease of management, auto-scaling, and cost-effectiveness, is widely adopted by deep learning (DL) applications. DL workloads, especially with large language models, require substantial GPU resources to ensure QoS. However, it is prone to produce GPU fragments (e.g., 15%-94%) in serverless DL systems due to the dynamicity of workloads and coarse-grained static GPU allocation mechanisms, gradually eroding the profits offered by serverless elasticity. Different from classical serverless systems that only scale horizontally, we present introspective elasticity (IE), a fine-grained and adaptive two-dimensional co-scaling mechanism to support GPU resourcing-on-demand for serverless DL tasks. Based on this insight, we build Dilu, a cross-layer and GPU-based serverless DL system with IE support. First, Dilu provides multi-factor profiling for DL tasks with efficient pruning search methods. Second, Dilu adheres to the resourcing-complementary principles in scheduling to improve GPU utilization with QoS guarantees. Third, Dilu adopts an adaptive 2D co-scaling method to enhance the elasticity of GPU provisioning in real time. Evaluations show that it can dynamically adjust the resourcing of various DL functions with low GPU fragmentation (10%-46% GPU defragmentation), high throughput (up to 1.8× inference and 1.1× training throughput increment) and QoS guarantees (11%-71% violation rate reduction), compared to the SOTA baselines.

Using NLP to analyze ESG reports has gained a lot of attention. However, existing supervised learning approaches rely on high-level and predetermined ESG topics (as used by reporting standards/rating agencies), which often fail to capture specific, latest trends and impactful issues in specific industries, while fully unsupervised approaches yield generic topics that are not useful for practical analysis. We proposed a novel data-driven and dynamic approach that base on the report contents to identify important and trendy issues that cannot be revealed by previous approaches. Technically speaking, our approach combines supervised text classification on industry-specific material topics with unsupervised topic modeling. The identified issues can be ranked using a simple word counting method. To illustrate the usefulness of our methodology, we apply it to a set of ESG reports from the banking industry. The identified issues, representing the trendy issues, can also be used to show the different priorities of focuses between banks from different regions. Time-series analysis can be done as well to see the changes in priority of issues over time. We are able to validate (indirectly and intuitively) that some of the issues should be correct, which show that our approach is promising.

The downlink capacity performance of distributed antenna systems (DAS) with antennas selection is investigated in a composite fading channel which takes path loss, Rayleigh fading and lognormal shadowing into account. According to the performance analysis, and using log-normal distribution approximation, the tightly approximate closed-form expressions of cumulative distribution function (CDF) and probability density function (PDF) of the effective SNR are obtained, respectively. Based on these results, the outage capacity performance of DAS is analyzed. By utilizing the Gaussian distribution approximation, a simple approximate outage capacity is derived. As a result, the closed-form expression is achieved. All these expressions will provide good theoretical performance evaluation for DAS. Simulation results show that the derived outage capacity is effective, and can match the corresponding simulation well.