# Why (and How) Networks Should Run Themselves

arXiv: https://arxiv.org/abs/1710.11583 · HTML: https://mlsanity.com/paper/1710.11583/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2017.

## Built on by (most cited first, 13 of 13)

- [netFound: Principled Design for Network Foundation Models](https://mlsanity.com/paper/2310.17025/) (2023)
- [Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective](https://mlsanity.com/paper/2404.06492/) (2024)
- [MAGNNETO: A Graph Neural Network-based Multi-Agent system for Traffic Engineering](https://mlsanity.com/paper/2303.18157/) (2023)
- [NetAgentBench: A State-Centric Benchmark for Evaluating Agentic Network Configuration](https://mlsanity.com/paper/2604.09678/) (2026)
- [Graph Neural Modeling of Network Flows](https://mlsanity.com/paper/2209.05208/) (2022)
- [Accelerating Deep Learning Classification with Error-controlled Approximate-key Caching](https://mlsanity.com/paper/2112.06671/) (2021)
- [Landing AI on Networks: An equipment vendor viewpoint on Autonomous Driving Networks](https://mlsanity.com/paper/2205.08347/) (2022)
- [NetBurst: Event-Centric Forecasting of Bursty, Intermittent Time Series](https://mlsanity.com/paper/2510.22397/) (2025)
- [AI-driven Intent-Based Networking Approach for Self-configuration of Next Generation Networks](https://mlsanity.com/paper/2603.23772/) (2026)
- [Attention-Based Model and Deep Reinforcement Learning for Distribution of Event Processing Tasks](https://mlsanity.com/paper/2112.03835/) (2021)
- [Learning QoE from Packet-Level Measurements in Encrypted Video Conferencing Traffic](https://mlsanity.com/paper/2601.06862/) (2026)
- [Defining AI-Native Systems: Autonomy as Revision Authority](https://mlsanity.com/paper/2607.21659/) (2026)
- [Untangling Co-Drift: Proactive Multi-Intent Failure Prediction and Root-Cause Disambiguation for Self-Driving Networks](https://mlsanity.com/paper/2607.25989/) (2026)

## Abstract (arXiv)

The proliferation of networked devices, systems, and applications that we depend on every day makes managing networks more important than ever. The increasing security, availability, and performance demands of these applications suggest that these increasingly difficult network management problems be solved in real time, across a complex web of interacting protocols and systems. Alas, just as the importance of network management has increased, the network has grown so complex that it is seemingly unmanageable. In this new era, network management requires a fundamentally new approach. Instead of optimizations based on closed-form analysis of individual protocols, network operators need data-driven, machine-learning-based models of end-to-end and application performance based on high-level policy goals and a holistic view of the underlying components. Instead of anomaly detection algorithms that operate on offline analysis of network traces, operators need classification and detection algorithms that can make real-time, closed-loop decisions. Networks should learn to drive themselves. This paper explores this concept, discussing how we might attain this ambitious goal by more closely coupling measurement with real-time control and by relying on learning for inference and prediction about a networked application or system, as opposed to closed-form analysis of individual protocols.