Software Defined Coalitions Controller Synchronization
Military / Coalition Issue
Military missions require the use of infrastructure assets including communication links, computational servers, data storage, databases, sensors and other resources. Dynamicity and agility of military operations demand near real-time configuration, re-configuration and provisioning of these resources, while supporting efficient and robust sharing of assets across armed forces or coalition partners. State-of-the-art techniques cannot currently achieve this.
Core idea and key achievements
A new architecture called Software Defined Coalitions (SDC) has been developed, which extends the existing Software Defined Networking (SDN), to address the above issue. An SDC is composed of multiple domains, each of which contains a set of infrastructure resources. Each domain has one domain controller and the controllers are connected through the control plane to exchange control information. As SDC is a logical (virtual) architecture, multiple SDCs can run simultaneously on the same set of physical resources. The software control logic implemented in controllers is programmable to enable rapid configuration for mission objectives, although controllers must synchronize status information of resources in their own domains with each other at times for proper operations and efficiency. Resources can be shared across domains among coalition partners and system control can be enhanced by reinforcement learning (RL); see the related DAIS Key Outcomes on “Resource Sharing in SDC” and “RL for Network Control,” respectively.
Key achievements include the development of:
- Fundamental understanding of benefits of controller synchronisation for various network structures and synchronisation levels
- Development of mechanisms/policies for controller synchronisation
- Algorithm for placing controllers to balance control delay & overheads
- Emulations on practical controller platforms showing the impact of adaptive synchronization for routing and load balancing applications
- Testbed experiments with real SDN-enabled mobile devices showing the traffic overheads of controller operation and dynamic placement.
Implications for Defence
The collection of new techniques will enable defence to realise the concept of SDC for dynamic, agile and robust configuration, provisioning and sharing of infrastructure assets among armed forces or coalition partners, which are unmatched by our adversaries.
Readiness & alternative Defence uses - Fix URLs
TRL 2/3. Many of the SDC techniques have been prototyped in practical systems or environments, including the demos of controller placement and controller synchronization. Further work will enhance the readiness of the new techniques for practical defence systems.
Resources and references
Samples of SDC related publications include:
- Controller synchronisation - Zhang, Ziyao, et al. “How advantageous is it? An analytical study of controller-assisted path construction in distributed SDN.” IEEE/ACM Transactions on Networking 27.4 (2019): 1643-1656.
- Synchronization policy - Poularakis, Konstantinos, et al. “Learning the optimal synchronization rates in distributed SDN control architectures.” IEEE INFOCOM 2019-IEEE Conference on Computer Communications. IEEE, 2019.
- Synchronization policy based on deep RL - Zhang, Ziyao, et al. “DQ scheduler: Deep reinforcement learning based controller synchronization in distributed SDN.” ICC 2019-2019 IEEE International Conference on Communications (ICC). IEEE, 2019.
- Efficient deep RL architecture - Zhang, Ziyao, et al. “Macs: Deep reinforcement learning based sdn controller synchronization policy design.” 2019 IEEE 27th International Conference on Network Protocols (ICNP). IEEE, 2019.
- Controller placement - Qin, Qiaofeng, et al. “SDN controller placement at the edge: Optimizing delay and overheads.” IEEE INFOCOM 2018-IEEE Conference on Computer Communications. IEEE, 2018.
Organisations
Yale University, Imperial College, IBM US, ARL, Dstl