Periodic Reporting for period 2 - TT (Transforming Transport)
Reporting period: 2018-07-01 to 2019-07-31
TransformingTransport intends to demonstrate, in a realistic, measurable and replicable way the transformative effects that Big Data will have to the mobility and logistics market. To this end, TransformingTransport will pursue the following main objectives:
• Objective O1 “Piloting”: Execute effective large-scale piloting and targeted demonstrations of the transformative nature that existing and very-near-to market big data technologies can bring about in the mobility and logistics sector by covering all relevant modes of transport, as well as multi-modal and transversal processes with strong impact and relevance of Big Data solutions.
• Objective O2 “Value”: Show concrete, measurable and verifiable evidence of data value that can be achieved in mobility and logistics in terms of significant increase in (i) operational efficiency of processes and services by at least 15%, (ii) improved customer experience, and (iii) new business models for the mobility and logistics sector.
• Objective O3 “Reusability”: Demonstrate the generic nature of Big Data solutions developed by TransformingTransport by showing how they may be reused (including with adaptation) and replicated across use cases and application domains.
• Objective O4 “Scalability”: Ensure that the Big Data solutions developed in TransformingTransport will work at the scale of the anticipated mobility and logistics processes, as well as data volume and velocity at the end of the TransformingTransport project, which means more than 55.000 GB, more than 25 GB/day and more than 20 different data sources on average per pilot by the year 2020.
• Objective O5 “Engagement”: Engage at least 120 key European industry actors – both large and SME, as well as both Big Data providers and Big Data users – and relevant public bodies in sectorial trials and demonstrations of TransformingTransport.
• Objective O6 “Transfer”: Implement effective knowledge transfer, dissemination and uptake of lessons learned and best practice examples, as well as standardization and policy recommendations to facilitate doubling the use of Big Data solutions in the mobility and logistics sector from the currently 19% to at least 38%.
• Objective O7 “Market Impact”: Strengthen both the position of EU Big Data providers as well as sectorial companies to engage in bids and business opportunities within the mobility and logistics market by combining sectorial, domain expertise with ICT knowledge, ultimately fostering an increase of market share of up to 600% (72% on average) and/or absolute market share of up to 12%.
• Objective O8 “Sustainability”: Set up a strong plan for sustainability actions to ensure availability and lasting impact of the TransformingTransport outcomes during the funding period of the Big Data Value PPP and beyond.
• Objective O9 “Mobilisation”: Mobilise verifiable commitment to additional sector investments in data assets and big data technologies, which reach a leverage factor of at least 6 times the EC contribution.
- Measurement of results and KPIs assessment framework to measure and evaluate results obtained in the piloting activities.
- Maintenance of the Open data portal that gathers information on the datasets used in the project.
- 208 data assets have been analysed and used in the different pilots.
- 13 pilots have successfully launched 47 large-scale experiments (use cases).
- 28 exploitable assets have been identified.
- Participation in 7 Project events, 12 domain events and 29 pilot specific events
In addition, with respect to CO2 and other emissions such as NOX and PM, savings reach up to 37%.
WP4 has shown outstanding potential in making highways “smarter” by using Big Data to optimise traffic and alert road authorities about unfolding road conditions and incidents.
During the project we have demonstrated that big data can also contribute to decrease waste through savings in operational activities and improved management of assets extending their lifetime and reducing downtime. Final results show a percentage of improvement higher than 32%.
Predictive Terminal Process Analytics has achieved a good balance between high accuracy rate (e.g. avoiding false negative predictions) but also generating predictions as early as possible in order to increase proactiveness, leading to a cost savings of 27 % on average.
Regarding customer experience, TT has shown that overall the optimisation of maintenance activities directly affects rail traffic management. Reducing the number of maintenance interventions will increase the number of trains that can ride daily over the railway tracks.
On the other hand, findings of the Dynamic Supply Networks pilot present various insights about the role of Big Data and business analytics in e-commerce logistics providing innovative services to enhance customer experience
New business models have been tested in cases like the airport domain, thanks to the collaboration established with duty-free operators in the Athens Airport pilot. Finally, TT has also demonstrated the potential of Big Data for improving traffic in the city by exploiting the data generated from the ever-increasing number of sensors.