The NexusStreets dataset contains human and autonomous driving scenes. They are collected by monitoring a target vehicle that can be either autonomous or controlled by a human driver. Data is presented in the shape of: sequences of JPEG images, one image per timestamp target vehicle state information for each timestamp The dataset has been built on CARLA Simulator, thanks to Baidu Apollo and a Logitech G29 steering wheel for the autonomous and human drivings, respectively. The dataset consists of 520 scenes (260 pairs of mirrored scenarios) of 60 seconds each. The folders are organized as follows: . ├── ... ├── │ ├── │ │ ├── │ │ │ └── ... │ │ └── ... │ └── ... └── ... driving mode: corresponds to the control modality of the target vehicle under test and can be either Baidu Apollo or manual driving; town: one of the five default maps in CARLA (e.g., Town01, Town02, etc); trial: 60 different trials per map, they differ in traffic and weather conditions (except Town04). Each trial records 60 seconds of simulation, logging 120 frames per video and an equal number of rows per CSV. In particular, each trial includes: video: this folder groups the JPEG images; state_features.csv: reports the state information of the target vehicle for each frame; detection_features.csv: reports the 2D bounding box detections obtained from a pre-trained YOLOv3 detector.
Next-generation mobile networks are expected to flaunt highly (if not fully) automated management. To achieve such a vision, Artificial Intelligence (AI) and Machine Learning (ML) techniques will be key enablers to craft the required intelligence for networking, i.e., Network Intelligence (NI), empowering myriad of orchestrators and controllers across network domains. In this paper, we elaborate on the DAEMON architectural model, which proposes introducing a NI Orchestration layer for the effective end-to-end coordination of NI instances deployed across the whole mobile network infrastructure. Specifically, we first outline requirements and specifications for NI design that stem from data management, control timescales, and network technology characteristics. Then, we build on such analysis to derive initial principles for the design of the NI Orchestration layer, focusing on (i) proposals for the interaction loop between NI instances and the NI Orchestrator, and (ii) a unified representation of NI algorithms based on an extended MAPE-K model. Our work contributes to the definition of the interfaces and operation of a NI Orchestration layer that foster a native integration of NI in mobile network architectures.
While there is a clear trend towards network automation through the usage of Artificial Intelligence (AI) and Machine Learning (ML) solutions, the major reference network architectures are still not natively including all the mechanisms needed to handle Network Intelligence (NI). This paper introduces a novel architecture proposed within the EU-funded DAEMON project, which includes a Network Intelligence Plane (NIP) that natively integrates NI into the network operation, management, and orchestration procedures. We do so by analyzing the gaps in current reference architectures and designing a Network Intelligence Orchestration (NIO) that handles the most important NI-related mechanisms such as lifecycle management, coordination, and data management.
While monitoring system behavior to detect anomalies and failures is important, existing methods based on log-analysis can only be as good as the information contained in the logs, and other approaches that look at the OS-level software state introduce high overheads. We tackle the problem with syslrn, a system that first builds an understanding of a target system offline, and then tailors the online monitoring instrumentation based on the learned identifiers of normal behavior. While our syslrn prototype is still preliminary and lacks many features, we show in a case study for the monitoring of OpenStack failures that it can outperform state-of-the-art log-analysis systems with little overhead.
RAN virtualization will become a key technology for the last mile of next-generation mobile networks driven by initiatives such as the O-RAN alliance. However, due to the computing fluctuations inherent to wireless dynamics and resource contention in shared computing infrastructure, the price to migrate from dedicated to shared platforms may be too high. Indeed, we show in this paper that the baseline architecture of a base station's distributed unit (DU) collapses upon moments of deficit in computing capacity. Recent solutions to accelerate some signal processing tasks certainly help but do not tackle the core problem: a DU pipeline that requires predictable computing to provide carrier-grade reliability. We present Nuberu, a novel pipeline architecture for 4G/5G DUs specifically engineered for non-deterministic computing platforms. Our design has one key objective to attain reliability: to guarantee a minimum set of signals that preserve synchronization between the DU and its users during computing capacity shortages and, provided this, maximize network throughput. To this end, we use techniques such as tight deadline control, jitter-absorbing buffers, predictive HARQ, and congestion control. Using an experimental prototype, we show that Nuberu attains >95% of the theoretical spectrum efficiency in hostile environments, where state-of-art approaches lose connectivity, and at least 80% resource savings.
