This paper analyzes a month-long trace of 85 billion user requests and 11.9 million cold starts from Huawei's serverless cloud platform. Our analysis spans workloads from five data centers. We focus on cold starts and provide a comprehensive examination of the underlying factors influencing the number and duration of cold starts. These factors include trigger types, request synchronicity, runtime languages, and function resource allocations. We investigate components of cold starts, including pod allocation time, code and dependency deployment time, and scheduling delays, and examine their relationships with runtime languages, trigger types, and resource allocation. We introduce pod utility ratio to measure the pod's useful lifetime relative to its cold start time, giving a more complete picture of cold starts, and see that some pods with long cold start times have longer useful lifetimes. Our findings reveal the complexity and multifaceted origins of the number, duration, and characteristics of cold starts, driven by differences in trigger types, runtime languages, and function resource allocations. For example, cold starts in Region 1 take up to 7 seconds, dominated by dependency deployment time and scheduling. In Region 2, cold starts take up to 3 seconds and are dominated by pod allocation time. Based on this, we identify opportunities to reduce the number and duration of cold starts using strategies for multi-region scheduling. Finally, we suggest directions for future research to address these challenges and enhance the performance of serverless cloud platforms.

Foundation models (FMs) have emerged as a promising approach for time series forecasting. While effective, FMs typically remain fixed during deployment due to the high computational costs of learning them online. Consequently, deployed FMs fail to adapt their forecasts to current data characteristics, despite the availability of online feedback from newly arriving data. This raises the question of whether FM performance can be enhanced by the efficient usage of this feedback. We propose ELF to answer this question. ELF is a lightweight mechanism for the online adaption of FM forecasts in response to online feedback. ELF consists of two parts: a) the ELF-Forecaster which is used to learn the current data distribution; and b) the ELF-Weighter which is used to combine the forecasts of the FM and the ELF-Forecaster. We evaluate the performance of ELF in conjunction with several recent FMs across a suite of standard time series datasets. In all of our experiments we find that using ELF improves performance. This work demonstrates how efficient usage of online feedback can be used to improve FM forecasts.

It is challenging to scale time series forecasting models such that they forecast accurately for multiple distinct domains and datasets, all with potentially different underlying collection procedures (e.g., sample resolution), patterns (e.g., periodicity), and prediction requirements (e.g., reconstruction vs. forecasting). We call this general task universal forecasting. Existing methods usually assume that input data is regularly sampled, and they forecast to pre-determined horizons, resulting in failure to generalise outside of the scope of their training. We propose the DAM -- a neural model that takes randomly sampled histories and outputs an adjustable basis composition as a continuous function of time for forecasting to non-fixed horizons. It involves three key components: (1) a flexible approach for using randomly sampled histories from a long-tail distribution, that enables an efficient global perspective of the underlying temporal dynamics while retaining focus on the recent history; (2) a transformer backbone that is trained on these actively sampled histories to produce, as representational output, (3) the basis coefficients of a continuous function of time. We show that a single univariate DAM, trained on 25 time series datasets, either outperformed or closely matched existing SoTA models at multivariate long-term forecasting across 18 datasets, including 8 held-out for zero-shot transfer, even though these models were trained to specialise for each dataset-horizon combination. This single DAM excels at zero-shot transfer and very-long-term forecasting, performs well at imputation, is interpretable via basis function composition and attention, can be tuned for different inference-cost requirements, is robust to missing and irregularly sampled data by design.

This paper releases and analyzes two new Huawei cloud serverless traces. The traces span a period of over 7 months with over 1.4 trillion function invocations combined. The first trace is derived from Huawei's internal workloads and contains detailed per-second statistics for 200 functions running across multiple Huawei cloud data centers. The second trace is a representative workload from Huawei's public FaaS platform. This trace contains per-minute arrival rates for over 5000 functions running in a single Huawei data center. We present the internals of a production FaaS platform by characterizing resource consumption, cold-start times, programming languages used, periodicity, per-second versus per-minute burstiness, correlations, and popularity. Our findings show that there is considerable diversity in how serverless functions behave: requests vary by up to 9 orders of magnitude across functions, with some functions executed over 1 billion times per day; scheduling time, execution time and cold-start distributions vary across 2 to 4 orders of magnitude and have very long tails; and function invocation counts demonstrate strong periodicity for many individual functions and on an aggregate level. Our analysis also highlights the need for further research in estimating resource reservations and time-series prediction to account for the huge diversity in how serverless functions behave.

Mobile network traffic data offers unprecedented opportunities for innovative studies within and beyond networking. However, progress is hindered by the very limited access that the research community at large has to the real-world mobile network data that is needed to develop and dependably test mobile traffic data-driven solutions. As a contribution to overcome this barrier, we propose CartaGenie, a generator of realistic mobile traffic snapshots at city scale. Taking a deep generative modeling approach and through a tailored conditional generator design, CartaGenie can synthesize high-fidelity and artifact-free spatial traffic snapshots using only contextual information about the target geographical region that is easily found in public repositories. Hence, CartaGenie allows researchers to create their own realistic datasets of spatial traffic from open data about their region of interest. Experiments with real-world mobile traffic measurements collected in multiple metropolitan areas show that CartaGenie can produce dependable network traffic loads for areas where no prior traffic information is available, significantly outperforming a comprehensive set of benchmarks. Moreover, tests with practical case studies demonstrate that the synthetic data generated by CartaGenie is as good as real data in supporting diverse research-oriented mobile traffic data-driven applications.

City-scale spatiotemporal mobile network traffic data can support numerous applications in and beyond networking. However, operators are very reluctant to share their data, which is curbing innovation and research reproducibility. To remedy this status quo, we propose SpectraGAN, a novel deep generative model that, upon training with real-world network traffic measurements, can produce high-fidelity synthetic mobile traffic data for new, arbitrary sized geographical regions over long periods. To this end, the model only requires publicly available context information about the target region, such as population census data. SpectraGAN is an original conditional GAN design with the defining feature of generating spectra of mobile traffic at all locations of the target region based on their contextual features. Evaluations with mobile traffic measurement datasets collected by different operators in 13 cities across two European countries demonstrate that SpectraGAN can synthesize more dependable traffic than a range of representative baselines from the literature. We also show that synthetic data generated with SpectraGAN yield similar results to that with real data when used in applications like radio access network infrastructure power savings and resource allocation, or dynamic population mapping.

RAN energy consumption is a major OPEX source for mobile telecom operators, and 5G is expected to increase these costs by several folds. Moreover, paradigm-shifting aspects of the 5G RAN architecture like RAN disaggregation, virtualization and cloudification introduce new traffic-dependent resource management decisions that make the problem of energy-efficient 5G RAN orchestration harder. To address such a challenge, we present a first comprehensive virtualized RAN (vRAN) system model aligned with 5G RAN specifications, which embeds realistic and dynamic models for computational load and energy consumption costs. We then formulate the vRAN energy consumption optimization as an integer quadratic programming problem, whose NP-hard nature leads us to develop GreenRAN, a novel, computationally efficient and distributed solution that leverages Lagrangian decomposition and simulated annealing. Evaluations with real-world mobile traffic data for a large metropolitan area are another novel aspect of this work, and show that our approach yields energy efficiency gains up to 25% and 42%, over state-of-the-art and baseline traditional RAN approaches, respectively.

We investigate spatial patterns in mobile service consumption that emerge at national scale. Our investigation focuses on a representative case study, i.e., France, where we find that: (i) the demand for popular mobile services is fairly uniform across the whole country, and only a reduced set of peculiar services (mainly operating system updates and long-lived video streaming) yields geographic diversity; (ii) even for such distinguishing services, the spatial heterogeneity of demands is limited, and a small set of consumption behaviors is sufficient to characterize most of the mobile service usage across the country; (iii) the spatial distribution of these behaviors correlates well with the urbanization level, ultimately suggesting that the adoption of geographically-diverse mobile applications is linked to a dichotomy of cities and rural areas. We derive our results through the analysis of substantial measurement data collected by a major mobile network operator, leveraging an approach rooted in information theory that can be readily applied to other scenarios.

With the evolution of various new types of application services for mobile devices, cellular operators have started providing multiple subscription plans to the mobile users. The plan subscribed determines the Quality of Service (QoS) to be provided to the user, and operators distinguish users as priority users and non-priority users, accordingly. To ensure better QoS to the priority users, necessary resources must be reserved at the base station. This demands analyzing the network traffic to predict future traffic pattern. This paper pioneers the use of machine learning methods to forecast mobile user traffic pattern for providing better QoS to the priority users. We analyze two different supervised learning methods, Naive Bayes Classifier and Logistic Regression, used for prediction of probable times when a priority user would be active. The prediction results are applied to the user scheduling strategies for efficient bandwidth management, thus improving system capacity and reduce blocking. Simulations on multiple real-life datasets validate the model and predict the mobile user pattern with very high accuracy, along with significant reduction in priority user service blocking ratio and improvement in their capacity.

In Heterogeneous cellular networks (HetNets), co-channel interference is a major concern due to the co-existence of multiple base stations with overlaid regions. Edge users are typically the victims because of high interference exposure. To counter this high interference, picocells communicate with the edge users in protected subframes (PSF). The severity of the problem intensifies in case of hotspot deployment, where picocells cannot provide coverage to the entire hotspot, thus forming a dense ring of macrocell users around picocells. We argue that these macrocell users are also victims, constituting a significant victim user population in hotspot deployment. We propose that, along with the macrocell muting during PSF, picocells should also be operated in cooperative manner with macrocell, and be barred from transmission during some of the subframes for protection of these macrocell victim users. We define a utility function to find the optimal values of PSF density for both macrocell and picocells, which would increase victim user throughput thereby enhancing system fairness. Exhaustive simulations illustrate that the proposed scheme improves victim user throughput significantly, while maintaining the overall system capacity.