Enhanced data management techniques for real time logistics planning - PowerPoint PPT Presentation

Enhanced data management techniques for real time logistics planning and scheduling Andrew Palmer 5 th International SRF Workshop, Cambridge 30 th November 2018

About LOGISTAR • A consortium of 15 partners from across Europe, coordinated by the University of Deusto (Spain) • Overall budget: 4.997.548,75 € • Duration: 36 months (Started June 2018) • Project funded by H2020:  Work programme: Smart, green and integrated transport  Call: MG-5.2-2017: Innovative ICT solutions for future logistics operations 2

LOGISTAR overall concept • The LOGISTAR system will include horizontal and vertical collaboration combined with real time data to make planning and optimising of transport operations more effective • A real-time decision making and visualization tool of freight transport will be developed to deliver information and services to the various agents involved in the supply chain 3

Other key innovation aspects • Artificial Intelligence focused on prediction  Inference based on event detection and probabilistic programming frameworks • Optimisation planning  Realistic optimisation models based on robust and multi-objective optimisation.  Hybrid metaheuristics based on paradigms of parallel computing • Automated negotiation and planning re-optimization  Constraint satisfaction problem solving techniques • Event Identification Rules  A new application domain for the processing of complex events and their aggregation • Service layer – Decision making tool  Increased data gathering, cleansing and structuring • Data gathering techniques  ETL tools for linked data. Scraping and transforming 4

Partners and roles Project Coordinator Implementation and integration of Global optimization planning services techniques Artificial Intelligence techniques Geo-special oriented software solutions focused on prediction Automated negotiation algorithms Testing and validation – Real time co- loading in chemical industries use case Cloud IoT data Testing and validation – Synchromodality use case Dissemination activities Data gathering and harmonization Testing and validation – Backhauling and co-loading use case Functional requirements and end- Testing and validation – Backhauling users engagement and co-loading use case New and emerging business models Testing and validation – assessment Synchromodality use case Predictive analysis and processing of real-time data 5

Work packages structure 6

Living labs LOGISTAR services will be tested in an operational environment in three use cases Real time co-loading in the Real time backhauling in the Synchromodality chemicals sector FMCG sector Real time re-planning due to Real time planning of resources Process of various information disrupting events: corrective and looking for transport synergy and coming from the different preventive bundling opportunities. companies ( schedules, resources, Planning of synchromodal constraints, truck, positions, empty routes based on real time Real-time alerts and return legs…) to improve backhaul events. recommendations to take action, management Dynamic assigning of freight facilitating the decision-making Overview of the status of the transport networks. process. operations through the real-time Real time status on goods dashboards and the real-time movements: position of vehicles, information on road transport arrival time of cargo fleets . system . 7

List of companies interviewed 21 companies interviewed www.logistar-project.eu 8

The TMS process Transport planning Shipper or LSP Order Delivery POD/CMR operations for: processing Load building Vehicle scheduling execution Owned vehicles Yes Yes Yes Yes Yes Contracted carriers - Yes Yes Yes Yes Yes dedicated Contracted carriers - Yes No No No Yes non dedicated Ad hoc carriers Yes No No No Yes www.logistar-project.eu 9

Logistar overview Dashboard information Cloud based system

Contact details Project Project coordination coordination : www.logistar-project.eu enrique.onieva@deusto.es LOGISTAR project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 769142.