Controlling networks with safety bounded and interpretable machine learning – SAFE

During the last decade, Software Defined Networking introduced the idea of decoupling control and data planes. From the system side, the key advances include compute-intensive control planes, network virtualisation, data plane programmability, in-network processing with AI accelerators which enable more agility and intelligence inside networks. The long-term vision is that of self-driving networks where automation and intelligence are two essential ingredients. Powerful and programmable devices are fostering the use of advanced Machine Learning (ML) and optimisation techniques to intelligently control networks, for a better user experience and utilisation of resources.
Network and service providers are facing increasing network complexity combined with a need to support an ever-increasing variety of traffic and applications. Thus, there is a need for agile, flexible and fully autonomous networks to accommodate them. Networks should largely self-manage themselves and deal with issues such as routing, resource allocation, QoE and traffic engineering. This requires new algorithms for decision-making and control.
Traditional approaches for control and decision-making in networks require a comprehensive knowledge of infrastructure and traffic, which is unrealistic in practice. Data-driven ML approaches do not have this drawback, but offer no safety bounds and are difficult to interpret. Control and decision-making algorithms are critical for the operation of networks, hence we believe that the solutions should be safety bounded and interpretable. We believe that networking knowledge-based and data-driven approaches should work in synergy. Networking knowledge-based models can guide and control the learning of data-driven ML approaches, which in turn, can learn about new situations from new data.
This opens up many new directions. Our project SAFE (Controlling Networks with SAFety bounded and IntErpretable Machine Learning) focuses on designing safety bounded and interpretable ML solutions for controlling networks. SAFE has following scientific objectives with an open source strategy:
1) Hierarchical architecture: Assuming modern network architectures, we will design a ML architecture based on global AI (running at central controller level) and local AI (running at edge device level) for decision-making in partially as well as fully observable and controllable environments. Global AI will be able to control, configure and install policies on local AI.
2) Algorithms for partially observable environments: We will design new safety bounded and interpretable algorithms for self-adaptive traffic engineering, automatic scheduling algorithms for partially observable and controllable environments. These methods find use cases in SD-WAN (Software-Defined Wide Area Networks), where edge devices present at customer premises need to collaboratively operate in overlay on top of partially observable core networks.
3) Algorithms for fully observable environments: We will investigate the application of the global and local AI architecture for fully observable and controllable environments. Specifically, we will design new safety bounded and interpretable algorithms for software-defined routing and traffic engineering, which find use cases in data centers as well as private WANs connecting multiple sites.