Periodic Reporting for period 2 - AICHAIN (A platform for privacy-preserving Federated Machine Learning using Blockchain to enable Operational Improvements in ATM)
Okres sprawozdawczy: 2021-07-01 do 2022-12-31
PROJECT SUMMARY
This project proposes an innovative Digital Information Management (DIM) concept, i.e. the AICHAIN solution, that aims at enabling the cyber-secured exploitation of large private data sets that belong to different stakeholders and that contain valuable information that is valuable for ATM operations. To overcome the stakeholders’ reluctance to share sensitive data, the exploitation of such data will not be performed by exchanging the data itself but by articulating an advanced privacy-preserving federated machine learning architecture in which neither the training data nor the training model need to be exposed. This will be possible thanks to the innovative combination of two emerging DIM technologies: Federated Machine Learning (FedML) and Blockchain technologies.
The potential benefits of the new proposed DIM concept will be explored through ATM research use cases related to advanced Demand Capacity Balancing (DCB) predictive models of the Network Manager (NM), whose prediction performance is expected to significantly improve thanks to the exploitation of relevant operational private data from Airspace Users. The accuracy of the new DCB predictive models augmented with real operational data accessed through the AICHAIN solution will be benchmarked against the machine learning models for DCB that are currently in use or under research by NM.
The project will also address the exploration of governance and incentives mechanisms as part of the AICHAIN solution concept architecture, to facilitate the “buy-in”/adoption of the concept and the alignment of interests of the key stakeholders (especially of the data owners). The design of advanced governance & incentives mechanisms, which could be implemented using the mechanism of “smart contracts” available in the toolset of Blockchain, will be complemented with a qualitative identification of data exploitation benefits and with discussions in workshops participated by external experts.
GENERAL OBJECTIVE
The goal of the AICHAIN solution is to enhance –by enabling the secured exploitation of private data with relevant operational value– the performance of the artificial intelligence and machine learning models that are researched and/or used today in the context of air traffic management (ATM) system. In this sense it is expected that, if the access to private data is unlocked to enable its exploitation by current artificial intelligence algorithms, then the network operations and the ATM performance could be significantly improved. In addition, the proposed AICHAIN solution could also potentially enable the design of new SESAR operational improvements (OIs) that could take advantage of the new capabilities to exploit private data that was unavailable in the past.
The ambition of this project is to help in determining –after the project ending and results delivering– whether the proposed AICHAIN solution should be included or not as a potential new SESAR technology enabler to solve the technical and motivational problems identified in the call for projects (topic 04 – DIM) related to the secured exploitation of private data in ATM operations. Therefore, the research of this project has been planned to generate the due qualitative and quantitative evidence required to make such a decision.
The project is positioned as a fundamental oriented (FO) research towards application-oriented (AO) research, targeting the FO/AO maturity gate (TRL1) as defined in the SESAR JU maturity assessment methodology, with the overall expected outcome of delivering a “concept outline and identification of potential benefits and risks”.
SPECIFIC OBJECTIVES
The specific objectives of the research have been structured in three areas of research that will be covered with different levels of deepness: i) the DIM technological solution, ii) the operational value of the DIM solution, and iii) the governance & incentives aspects.
OBJECTIVE #1 (O1): In the technological dimension, to define the AICHAIN Solution architecture as a potential SESAR technology enabler for the exploitation of private data value, and to implement a functional small-scale prototype for user validation and operational value experimentation.
OBJECTIVE #2 (O2): In the operational dimension, to demonstrate and quantify the operational value of the AICHAIN concept with an ATM use case in the area of Advanced Demand Capacity Balancing (A-DCB) services.
OBJECTIVE #3 (O3): In the governance dimension, to develop an incentive mechanism that addresses the motivational aspects of the data owners in order to facilitate the adoption and the effective utilisation of the AICHAIN concept.
This project proposes an innovative Digital Information Management (DIM) concept, i.e. the AICHAIN solution, that aims at enabling the cyber-secured exploitation of large private data sets that belong to different stakeholders and that contain valuable information that is valuable for ATM operations. To overcome the stakeholders’ reluctance to share sensitive data, the exploitation of such data will not be performed by exchanging the data itself but by articulating an advanced privacy-preserving federated machine learning architecture in which neither the training data nor the training model need to be exposed. This will be possible thanks to the innovative combination of two emerging DIM technologies: Federated Machine Learning (FedML) and Blockchain technologies.
The potential benefits of the new proposed DIM concept will be explored through ATM research use cases related to advanced Demand Capacity Balancing (DCB) predictive models of the Network Manager (NM), whose prediction performance is expected to significantly improve thanks to the exploitation of relevant operational private data from Airspace Users. The accuracy of the new DCB predictive models augmented with real operational data accessed through the AICHAIN solution will be benchmarked against the machine learning models for DCB that are currently in use or under research by NM.
The project will also address the exploration of governance and incentives mechanisms as part of the AICHAIN solution concept architecture, to facilitate the “buy-in”/adoption of the concept and the alignment of interests of the key stakeholders (especially of the data owners). The design of advanced governance & incentives mechanisms, which could be implemented using the mechanism of “smart contracts” available in the toolset of Blockchain, will be complemented with a qualitative identification of data exploitation benefits and with discussions in workshops participated by external experts.
GENERAL OBJECTIVE
The goal of the AICHAIN solution is to enhance –by enabling the secured exploitation of private data with relevant operational value– the performance of the artificial intelligence and machine learning models that are researched and/or used today in the context of air traffic management (ATM) system. In this sense it is expected that, if the access to private data is unlocked to enable its exploitation by current artificial intelligence algorithms, then the network operations and the ATM performance could be significantly improved. In addition, the proposed AICHAIN solution could also potentially enable the design of new SESAR operational improvements (OIs) that could take advantage of the new capabilities to exploit private data that was unavailable in the past.
The ambition of this project is to help in determining –after the project ending and results delivering– whether the proposed AICHAIN solution should be included or not as a potential new SESAR technology enabler to solve the technical and motivational problems identified in the call for projects (topic 04 – DIM) related to the secured exploitation of private data in ATM operations. Therefore, the research of this project has been planned to generate the due qualitative and quantitative evidence required to make such a decision.
The project is positioned as a fundamental oriented (FO) research towards application-oriented (AO) research, targeting the FO/AO maturity gate (TRL1) as defined in the SESAR JU maturity assessment methodology, with the overall expected outcome of delivering a “concept outline and identification of potential benefits and risks”.
SPECIFIC OBJECTIVES
The specific objectives of the research have been structured in three areas of research that will be covered with different levels of deepness: i) the DIM technological solution, ii) the operational value of the DIM solution, and iii) the governance & incentives aspects.
OBJECTIVE #1 (O1): In the technological dimension, to define the AICHAIN Solution architecture as a potential SESAR technology enabler for the exploitation of private data value, and to implement a functional small-scale prototype for user validation and operational value experimentation.
OBJECTIVE #2 (O2): In the operational dimension, to demonstrate and quantify the operational value of the AICHAIN concept with an ATM use case in the area of Advanced Demand Capacity Balancing (A-DCB) services.
OBJECTIVE #3 (O3): In the governance dimension, to develop an incentive mechanism that addresses the motivational aspects of the data owners in order to facilitate the adoption and the effective utilisation of the AICHAIN concept.
Each of these three objectives is linked to a research area and question (RQ1, RQ2, RQ3) and has a focussed work-package (WP2, WP3, WP4), for the respective research dimensions of technology, operational-value and governance. The three WP2/3/4 have run concurrently along the project. Progress towards the objectives in Period 1 was provided in the intermediate deliverables D2.1/D3.1/D4.1 and progress towards the objectives in Period2 has been provided in the final deliverable reports D2.2/D3.2/D4.2 and consolidated in the D1.6 Final Results consolidation, which also includes the maturity assessment outcomes, final lessons learn, conclusions, and impact.
The main tangible impact of the project has been the proposal of AICHAIN as a novel solution of type Enabler (a.k.a. Technological Solution) in the ATM Master plan. Resulting from the project outcomes and final maturity assessment, the solution, referred in SESAR ER program terms as SOL-AICHAIN, has gone from the “pre-TRL-1” level at project start to a “TRL-2 on-going” maturity level. The AICHAIN Solution and its potential use cases in ATM was discussed along the project and in the final dissemination workshop with ATM stakeholders. The main conclusions are twofold, first, that there are many application use cases of interest for the ATM, and second, to obtain the buy-in of operational stakeholders to further develop and apply the solution it is convenient to focus the discussion and next steps on specific use case, i.e. considering each use case application as a project in its own, since the deployment architecture of federated learning technologies can have be substantially different, with a large number of components involved and complexities. Figure 1 4 and Figure 1 5 illustrates the transversal enabler nature of the AICHAIN concept and shows some of the application use cases discussed.