New ICT Infrastructure & Reference Architecture to Support Operations in Future PI Logistics Networks

Key Innovation

ICONET Innovation Potential - Unique Value Propositions

ICONET’s innovation is steered to becoming a market solution and features a distinctive set of Unique Value Propositions (UVPs) that are explained below:

UVP1: PI Models

To date, PI models for the Physical Internet do not exist, or are in their early infancy. ICONET changes this by catering for a number of models that optimise on multiple axes such as for throughput, speed, green/environment, utilisation, efficiency, multi-modality. These models can be interrogated, fused, optimised based on one or more parameters (e.g. optimise for time AND for environment), allowing alternate implementations of a PI model to be proposed and assessed.

UVP2: PI Simulations

ICONET facilitates multiple simulations with the end goal of recommending a number of PI models, using algorithms that are developed to optimise in a myriad of contexts and for cargo that has differential levels of prioritisation, as well as leveraging historical data (and extrapolating from these historical data) to derive accurate simulations.

UVP3: PI Networks

ICONET models the concept of a PI Network that is analogous to principles of the internet, in turn fulfilling the routing of cargo from source to destination based on the principles of self-optimising networks. ICONET also models the concept of PI Subnets, essentially allowing large actors to model, implement and optimise within the context of their own SC network and SC collaborators, ultimately delivering private network configurations.

UVP4: IoT for PI

ICONET leverages IoT semantics to facilitate the automated tagging and tracking of cargo through the PI network, in turn allowing for point in time reporting, insights and tracking and, in turn, providing important historical context that will allow a cognitive system that exploits machine learning principles to support a PI optimisation engine.

UVP5: Blockchain for PI

ICONET recognises that a PI-based solution requires inherent accountability and auditability at all stages where cargo moves through nodes and hubs across the supply chain, and investigates a blockchain-based transactional ledger to facilitate this auditability and transparency, and well as a vehicle to facilitate real time updates and situational awareness for the purposes of reporting and tracking for all interested parties.

UVP6: PI inspired Cognitive Engine

ICONET leverages machine learning principles and historical transactional data to improve accuracy and precision for ICONET’s PI optimisation engine. ICONET takes the view that tomorrow’s context can be further optimised by trends and patterns evidenced in retrospective contexts, such as repeated patterns of delays in trucks due to traffic in certain locations, such as acknowledging classes of delay around holiday periods, etc.

UVP7: Controller Management and PI Plans

ICONET offers the user the ability to create multiple models via a controller management façade that optimise for various circumstances and KPIs, with the end goal of modelling the PI system and network. Differential implementations of the model will be recommended based on optimising for stated KPIs, ultimately delivering a PI plan for a network of hubs, warehouses, network flows (transport chains) and SC actors relative to the outset parameters specified.

UVP8: ICONET API and External Interfaces

ICONET anticipates its ICT platform having broader relevance in a PI-implemented world, and provides APIs and External interfaces that can be exploited by existing planning tools. These interfaces will allow, for example, querying internal systems that can provide transactional data from a blockchain ledger (for auditability, governance, track and trace), interrogating the ICONET platform for planning and facilitation purposes, gleaning predictive analytics to help configure planning decisions, etc.

Sign up to ICONET Newsletter

© 2018 ICONET

EU-flag-(high-resolution)

This project is funded from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 769119

The views expressed by the ICONET Consortium do not necessarily represent the views of the EU Commission/INEA.
The Consortium and the EU Commission/INEA are not responsible for any use that may be made of the information it contains
EU-flag-(high-resolution)

This project is funded from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 769119

The views expressed by the ICONET Consortium do not necessarily represent the views of the EU Commission/INEA.
The Consortium and the EU Commission/INEA are not responsible for any use that may be made of the information it contains