Mobile devices increasingly rely on deep neural networks (DNNs) for complex inference tasks, but running entire models locally drains the device battery quickly. Offloading computation entirely to cloud or edge servers reduces processing load at devices but poses privacy risks and can incur high network bandwidth consumption and long delays. Split computing (SC) mitigates these challenges by partitioning DNNs between user equipment (UE) and edge servers. However, 5G wireless channels are time-varying and a fixed splitting scheme can lead to sub-optimal solutions. This paper addresses the limitations of fixed model partitioning in privacy-focused image processing and explores trade-offs in key performance metrics, including end-to-end (E2E) latency, energy consumption, and privacy, by developing an adaptive ML partitioning scheme based on realtime AI-powered throughput estimation. Evaluation in multiple scenarios demonstrates significant performance gains of our scheme.

Open Radio Access Networks (O-RAN) are expected to revolutionize the telecommunications industry with benefits like cost reduction, vendor diversity, and improved network performance through AI optimization. Supporting the O-RAN ALLIANCE’s mission to achieve more intelligent, open, virtualized and fully interoperable mobile networks, O-RAN Open Testing and Integration Centers (OTICs) play a key role in accelerating the adoption of O-RAN specifications based on rigorous testing and validation. One theme in the recent O-RAN Global PlugFest Spring 2024 focused on demonstrating consistent and repeatable Open Fronthaul testing in multiple labs. To respond to this topic, in this paper, we present a detailed analysis of the testing methodologies and results for O-RAN Distributed Unit (O-DU) in O-RAN across two OTICs. We identify key differences in testing setups, share challenges encountered, and propose best practices for achieving repeatable and consistent testing results. Our findings highlight the impact of different deployment technologies and testing environments on performance and conformance testing outcomes, providing valuable insights for future O-RAN implementations.

Open Radio Access Networks (RAN) aim to bring a paradigm shift to telecommunications industry, by enabling an open, intelligent, virtualized, and multi-vendor interoperable RAN ecosystem. At the center of this movement, O-RAN ALLIANCE defines the O-RAN architecture and standards, so that companies around the globe can use these specifications to create innovative and interoperable solutions. To accelerate the adoption of O-RAN products, rigorous testing of O-RAN Radio Unit (O-RU) and other O-RAN products plays a key role. O-RAN ALLIANCE has approved around 20 Open Testing and Integration Centres (OTICs) globally. OTICs serve as vendor-neutral platforms for providing the testing and integration services, with the vision that an O-RAN product certified in any OTIC is accepted in other parts of the world. To demonstrate the viability of such a certified-once-and-use-everywhere approach, one theme in the O-RAN Global PlugFest Spring 2024 is to demonstrate consistent and repeatable testing for the open fronthaul interface across multiple labs. Towards this, Japan OTIC and Asia Pacific OTIC in Singapore have teamed up together with an O-RU vendor and Keysight Technology. Our international team successfully completed all test cases defined by O-RAN ALLIANCE for O-RU conformance testing. In this paper, we share our journey in achieving this outcome, focusing on the challenges we have overcome and the lessons we have learned through this process.

The advances in deep neural networks (DNN) have significantly enhanced real-time detection of anomalous data in IoT applications. However, the complexity-accuracy-delay dilemma persists: Complex DNN models offer higher accuracy, but typical IoT devices can barely afford the computation load, and the remedy of offloading the load to the cloud incurs long delay. In this article, we address this challenge by proposing an adaptive anomaly detection scheme with hierarchical edge computing (HEC). Specifically, we first construct multiple anomaly detection DNN models with increasing complexity and associate each of them to a corresponding HEC layer. Then, we design an adaptive model selection scheme that is formulated as a contextual-bandit problem and solved by using a reinforcement learning policy network . We also incorporate a parallelism policy training method to accelerate the training process by taking advantage of distributed models. We build an HEC testbed using real IoT devices and implement and evaluate our contextual-bandit approach with both univariate and multivariate IoT datasets. In comparison with both baseline and state-of-the-art schemes, our adaptive approach strikes the best accuracy-delay tradeoff on the univariate dataset and achieves the best accuracy and F1-score on the multivariate dataset with only negligibly longer delay than the best (but inflexible) scheme.

Offloading computationally intensive tasks from mobile users (MUs) to a virtualized environment such as containers on a nearby edge server, can significantly reduce processing time and hence end-to-end (E2E) delay. However, when users are mobile, such containers need to be migrated to other edge servers located closer to the MUs to keep the E2E delay low. Meanwhile, the mobility of MUs necessitates handover among base stations in order to keep the wireless connections between MUs and base stations uninterrupted. In this paper, we address the joint problem of container migration and base-station handover by proposing a coordinated migration-handover mechanism, with the objective of achieving low E2E delay and minimizing service interruption. The mechanism determines the optimal destinations and time for migration and handover in a coordinated manner, along with a delta checkpoint technique that we propose. We implement a testbed edge computing system with our proposed coordinated migration-handover mechanism, and evaluate the performance using real-world applications implemented with Docker container (an industry-standard). The results demonstrate that our mechanism achieves 30%-40% lower service downtime and 13%-22% lower E2E delay as compared to other mechanisms. Our work is instrumental in offering smooth user experience in mobile edge computing.

Advances in deep neural networks (DNN) greatly bolster real-time detection of anomalous IoT data. However, IoT devices can hardly afford complex DNN models, and offloading anomaly detection tasks to the cloud incurs long delay. In this paper, we propose and build a demo for an adaptive anomaly detection approach for distributed hierarchical edge computing (HEC) systems to solve this problem, for both univariate and multivariate IoT data. First, we construct multiple anomaly detection DNN models with increasing complexity, and associate each model with a layer in HEC from bottom to top. Then, we design an adaptive scheme to select one of these models on the fly, based on the contextual information extracted from each input data. The model selection is formulated as a contextual bandit problem characterized by a single-step Markov decision process, and is solved using a reinforcement learning policy network. We build an HEC testbed, implement our proposed approach, and evaluate it using real IoT datasets. The demo shows that our proposed approach significantly reduces detection delay (e.g., by 71.4% for univariate dataset) without sacrificing accuracy, as compared to offloading detection tasks to the cloud. We also compare it with other baseline schemes and demonstrate that it achieves the best accuracy-delay tradeoff1.

In wireless body area network (BAN) applications such as wearable computing, healthcare and sports, Bluetooth Low Energy (BLE) is a new and promising technology, which uses the unlicensed 2.4-GHz spectrum band for data transmission. Since there exist many wireless technologies operating in this frequency band, the issues of cross-technology interference and coexistence present a major challenge. In this work, we develop a testbed to conduct our experimental studies, focusing on BLE and its coexistence capabilities when being deployed in a dense environment, under possible interference from WiFi and ZigBee/IEEE 802.15.4. One scenario of interest is a network of several co-located BLE-based BANs, each of which is designed in a star topology with one gateway and multiple BLE sensor nodes. The second scenario represents a highly heterogeneous network where each BAN now carries both BLE and ZigBee sensors, while being exposed to interference from external WiFi transmission. Our results show that the performance of BLE is relatively robust to interference from other BLE transmission as well as those from nearby ZigBee and WiFi devices.

We propose a new framework combining dynamic sampling rates for healthcare sensors driven by user behavior, and an adaptive MAC scheduling scheme applied to the time-slotted channel hopping (TSCH) protocol in IEEE 802.15.4, which provides high throughput and reliable communications. First, we introduce a system software architecture for machine-learning-assisted healthcare monitoring that detects the user's behavior using edge computing and adjusts the sampling rates of the healthcare sensors accordingly. Second, we propose an adaptive MAC scheduling scheme for TSCH based on a state machine model that reacts to the dynamic traffic generated by the healthcare sensors. In case of an urgent state, the MAC scheduler automatically allocates extra timeslots to the appropriate sensors so as to enable the reliable transfer of high-resolution sensor data for further analysis. Experimental results from our testbed, implemented in Contiki-OS on the OpenMote-CC2538 platform, show that the proposed adaptive scheduling scheme can respond quickly to changes in user behavior and ensure the reliable transfer of sensor data in emergency situations.