Project

Space development is becoming more relevant than ever. The number of satellite launches (of various applications) is very rapidly growing. The size of the space data acquired daily from the objects indicated above is enormous, and growing at an exponential rate. Many customers might be interested in combining the data from two or more satellite data providers. Expected data might also be in two or more different localizations, which increases the complexity of the collecting process and possibly the costs since the customer might end up having more data than necessary. Moreover, it should be emphasized that these data are of a very different nature (images, recordings, analysis, raw data, etc.). The huge amount of collected data requires appropriate storage, classification, and further processing for final use. The relative initial maturity of the space data market shows many aspects that can be dramatically improved to achieve much better end benefits - and for all parties to the transaction.

A comprehensive and novel framework as a satellite/space data and multi-agent brokering system that provides a convenient environment for both providers and customers. This framework will adopt a dynamically adjusting offers and prices based on the supply/demand conditions of the market, compromise conflicting objectives between the customers (minimizing the purchase cost) and the providers (maximizing the profits), and fulfilling the market orders with minimal latency.

Challenging open problems

To achieve it's objectives to design and develop a brokering system dedicated to space data that brings optimised costs/revenues and QoS, SERENITY aims to solved these challeging open problems classified in four main categories:

Space Data Brokering

A space data (satellite images, recordings, analyses, raw data) marketplace as the first of its kind.
Space data exchange between providers and customers with a timely pricing scheme.
Optimised multi-conflicting objectives such as cost/profit and deliverables/latency.

Data Lakes

Specialized space data lake architecture for multipurpose space data.
Efficient storage topology and architecture for space data.
Fault tolerance and robustness of large-scale data in data lakes.

High-Performance Computing

A parallel modern complex heterogeneous architecture implementation as the first of its kind.
Application acceleration saves time and energy, which could be achieved through energy-efficient parallel architecture.
HPC facilitates deeper exploration and understanding of the space technology/application.

Brokering Optimization

Novel formulation of the space brokering problem with proof of the complexity.
Novel optimization algorithms to tackle the space brokering problem.
Opening the broad space data market to completely new, previously unseen opportunities for very wide optimization from different perspectives.
Strong foundations for further scientific work related to space data brokering.

SERENITY approach

Methodically, the SERENITY project will provide a dedicated marketplace for space data as a whole. The data providers and data consumers will interact through an online platform to optimize crucial aspects of this market flow.

Data Lake-Based Marketplace Topology and Architecture

Data Lake as a single repository with several distinguished layers.
Components ensuring Security, Governance, Archive, Offload, and Orchestration + ELT processes of data lake.
Topology and architecture flexibility.

Space Data Brokering Problem Modelling and Algorithms Design

Formulation of several vaiants of the Space Data Brokering Problem.
Appropriate mathematical models will be developed.
Development and evaluation of high-quality and efficient algorithms driving the optimization process.

High-Performance Computing and Portability

Performance optimization and portability on the modern accelerators and processors.
Performance optimization and portability on the modern embedded and heterogeneous architectures.

Brokering Optimization System

Design, implementation, customization, and validation of a simulator considering various usage scenarios.
Benchmarking and validation of independent components of the simulator.