N221-026 TITLE: DIGITAL ENGINEERING - Automated Network Cluster Generation

OUSD (R&E) MODERNIZATION PRIORITY: Networked C3

TECHNOLOGY AREA(S): Information Systems

The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with the Announcement. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws.

OBJECTIVE: Develop an algorithm that automatically identifies clusters of nodes that should participate in specific information flows based on a combination of geographic location information type needs.

DESCRIPTION: Navy command and control networks currently implement "mass delivery", meaning data from each node is sent to all nodes. This method of delivery makes sense given the networks’ initial purpose of providing a common track picture on each node. Having all sensor data available on each node allows each node to generate the same track picture as all other nodes. Future Navy requirements will add additional data to existing networks, using the Communications as a Service (CaaS) concept, and will require existing command and control networks be expanded to a larger number of nodes. At some network size, the concept of mass delivery will drive the network to its throughput limit for a given point-to-point communication. A concept to separate network size from throughput is to prioritize sending specific data to certain clusters of nodes that need that specific data. The data need can be characterized by a combination of geographic proximity and data type. Currently no known solutions exist that can accomplish this task. The Navy seeks an algorithm that automatically identifies clusters of nodes that will participate in specific information flows based on a combination of geographic location information type needs.

The solution should automatically assign network nodes to clusters. The cluster generator will be implemented in a high-level language (such as Python, MATLAB, and so forth) to facilitate its evaluation in simulation. Metrics available in the reference by J. Yang can be used to assess the quality of the clusters [Ref 1]. The default metric will be a comparison of the network size achievable using the clusters to the network size achievable using mass delivery, assuming a constant maximum throughput. The clusters may be generated upon the node entering the network or discovered during network execution. The net entry approach is intended to avoid chokepoints (i.e., communications that exceed the point-to-point throughput limit). The discovery method is an ad-hoc method and is intended to detect and mitigate chokepoints. Both methods will be simulated. Each approach optimizes the use of the network throughput. The solution(s) will be tested in a testbed provided by the Government. Based on the cluster definitions, the scheduling concept will be demonstrated in a simulation showing increased fidelity.

Work produced in Phase II may become classified. Note: The prospective contractor(s) must be U.S. Owned and Operated with no Foreign Influence as defined by DOD 5220.22-M, National Industrial Security Program Operating Manual, unless acceptable mitigating procedures can and have been implemented and approved by the Defense Counterintelligence Security Agency (DCSA), formerly the Defense Security Service (DSS). The selected contractor must be able to acquire and maintain a secret level facility and Personnel Security Clearances, in order to perform on advanced phases of this contract as set forth by DCSA and NAVSEA in order to gain access to classified information pertaining to the national defense of the United States and its allies; this will be an inherent requirement. The selected company will be required to safeguard classified material IAW DoD 5220.22-M during the advance phases of this contract.

PHASE I: Develop a concept for an automated network cluster generator that automatically assigns network nodes to clusters. Demonstrate the concept meets the parameters of the Description. Show feasibility through analysis, modelling, simulation, and testing. The Phase I Option, if exercised, will include the initial design specifications and a capabilities description to build a prototype solution in Phase II.

PHASE II: Develop and deliver the prototype automated network cluster generator based on the results of Phase I. Demonstrate the prototype meets the required range of desired performance attributes given in the Description. System performance will be demonstrated through installation and prototype testing in a testbed. The scheduling concept, based on the cluster definitions, will be demonstrated in simulation with increased fidelity.

It is probable that the work under this effort will be classified under Phase II (see Description section for details).

PHASE III DUAL USE APPLICATIONS: Support the Navy in transitioning the technology to Navy use. The automated clustering concept will be merged with existing command and control software to assist in generating the Time-Division Multiple Access (TDMA) transmit/receive schedule. Working prototype scheduling algorithms will be delivered to the Navy Program of Record for integration into the scheduling algorithm to be deployed. Assist the Government in integrating the suite of scheduling concepts that best support the requirements of the network capability to be deployed.

This technology will benefit the commercial industry for companies or universities that use large amounts of computers to control aspects or communications within their industry.

REFERENCES:

1. J. Yang, J. McAuley and J. Leskovec, "Community Detection in Networks with Node Attributes," 2013 IEEE 13th International Conference on Data Mining, Dallas, TX, USA, 2013, pp. 1151-1156, doi: 10.1109/ICDM.2013.167. https://ieeexplore.ieee.org/document/6729613; https://www-cs.stanford.edu/~jure/pubs/cesna-icdm13.pdf.
2. Emmons S, Kobourov S, Gallant M, Börner K (2016) Analysis of Network Clustering Algorithms and Cluster Quality Metrics at Scale. PLoS ONE 11(7): e0159161. https://doi.org/10.1371/journal.pone.0159161; https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0159161.

KEYWORDS: Large networks; clusters of nodes; cluster generator; optimized throughput; information flows; ad-hoc network.