Distributed Learning and Cooperative Optimization for Multi-agent Autonomous Wireless Access Points

DISCO will design a new generation of decentralized Machine Learning (ML)-based methods for distributed learning and cooperative optimization over large-scale autonomous cooperative wireless Access Points (APs), representing intelligent agents. Wi-Fi networks are the primary medium for global internet traffic, however, they are not operating optimally because of the lack of coordination between the different interfering Wi-Fi Networks. Nowadays, these networks are bringing new features not previously present, which has created a very large amount of configuration parameters for resource allocation, making them extremely complex to optimize dynamically. Current solutions are typically based on theoretical models and heuristics, without exploiting network measurement data, and can not find efficiently the optimal configuration parameters jointly across all the APs, due to the enormous search space. The few existing ML-based algorithms assume a single centralized controller, which is not possible in practice for managing separately owned Wi-Fi networks, implying also a privacy threat. Main novelties of DISCO: 1) novel distributed online ML algorithms to learn and track an interference graph representing the overall dynamics of the interfering Wi-Fi networks, by using the multiple data time-series from APs & clients, finding also communities of interfering Wi-Fi networks, detecting anomalies and predicting future behavior; 2) a fully distributed Multi-Agent Reinforcement Learning (MARL) algorithm for resource allocation to maximize network performance (e.g. throughput), exploiting the interference graph state; 3) optimization of the protocol connecting the APs through the backhaul network to maximize the efficiency of the distributed MARL algorithms and enforce privacy. The solutions will be implemented using portable containerized software modules and demonstrated in collaboration with key leading national and international stakeholders (Altibox, Multinett, Bell Labs).

DISCO investigates the design of a new generation of decentralized Machine Learning (ML)-based methods for distributed learning and cooperative optimization over large-scale autonomous cooperative wireless Access Points (APs), representing intelligent agents. Even though Wi-Fi networks are the primary medium for global internet traffic, their operation is far from optimal because of the lack of coordination between the different interfering Wi-Fi Networks. They have evolved tremendously, bringing new features not previously present, however, they come together with a very large plethora of configuration parameters, which makes them extremely complex to optimize dynamically. Most of solutions proposed for network resource allocation are based on models and heuristics, not data-driven, and can not find efficiently the optimal configuration of all the parameters jointly across all the APs, due to the enormous search space. The few existing ML-based algorithms assume a centralized controller, which is not possible in practice for managing separately owned Wi-Fi networks, implying also a privacy threat. DISCO novelties: 1) novel distributed online ML algorithms to learn a multi-layer and multi-modal time-varying graph representing the overall dynamics of the interfering Wi-Fi networks, by using multivariate data time-series from APs & clients, detecting clusters of interfering Wi-Fi networks, allowing also to detect anomalies and predict variables; 2) a fully distributed Graph-Time Neural Network-based Multi-Agent Reinforcement Learning (MARL) algorithm for resource allocation, which operates directly on the learned graph, 3) optimization of interplay between the protocol connecting the APs (while enforcing privacy), and the efficiency of the distributed MARL algorithm. The solutions will be implemented using portable containerized software modules and demonstrated in collaboration with key leading national and international stakeholders (Altibox, Multinett, Bell Labs).