Traffic prediction with shared causal inference in ORAN computing continuum

Guo, WeisiCordiez, Theophile2025-03-312025-03-312024-12-08Guo W, Cordiez T. (2024) Traffic prediction with shared causal inference in ORAN computing continuum. In: GLOBECOM 2024 - 2024 IEEE Global Communications Conference, 8-12 December 2024, Cape Town, South Africa979-8-3503-5126-21930-529Xhttps://doi.org/10.1109/globecom52923.2024.10901631https://dspace.lib.cranfield.ac.uk/handle/1826/23692Data Availability: Most of the raw data used is available in a previous data release on Dryad: https://doi.org/10.5061/dryad.35m1f4qData-driven proactive network optimisation is critical for 5G advanced and 6G, allowing operators to dynamically allocate cellular spectrum reuse in anticipating for demand surges. Current approaches to traffic prediction are largely temporal correlation based. We know causal inference of key factors can help to improve prediction accuracy for spike traffic events and identify pathways to improve services. Current causal inference identify stationary independent variables, but real environments have open challenges: (i) dynamic and heterogeneous causal maps, (ii) cascade partially observable variables, and/or (iii) have coupled / confounding relationships. Currently there is no research that dynamically configures the causal relationship according to emerging real-time data and shares inference outcomes across the data sharing and computing continuum of Open-RAN (ORAN) architecture. Here, we use both real cellular network traffic and social event triggers to perform nonlinear causal inference as an rApp: Predictability Improvement (PI), Conditional Mutual Information (CMI), and Convergent Cross Map (CCM). This causal knowledge is then shared across the ORAN to be embedded in traffic prediction xApps: hard causal embedding to Recurrent Neural Network (RNN) and soft causal feature embedding to a Gaussian Processes (GP). The results show a significant accuracy improvement (93-99%) over baseline non-causal correlated prediction (76-94%) and blind multi-variate approaches (87-95%). This work paves the way to causal proactive network optimisation.pp. 855-860enAttribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/3509 Transportation, Logistics and Supply Chains46 Information and Computing Sciences40 Engineering35 Commerce, Management, Tourism and Servicescausalitymachine learningtraffic predictionsocial mediaTraffic prediction with shared causal inference in ORAN computing continuumConference paper979-8-3503-5125-52576-6813567338