InCharge

InCharge develops a SaaS platform harnessing large-scale mobility data, electricity grid information, and optimisation algorithms to plan and deploy efficient electric vehicle charging infrastructure in Arteixo.

Context

Cities and electric vehicle (EV) charging providers face major challenges in planning infrastructure that effectively aligns with real-world mobility demand. Planning decisions are frequently based on limited data, leading to underutilised assets and sluggish electric mobility adoption. Inspired by the urgent need to support the transition to clean urban mobility under the EU Green Deal, the InCharge Arteixo project addresses this bottleneck through an innovative, data-driven approach.

The project

The InCharge project in Arteixo will develop and validate a software-as-a-service (SaaS) decision-support platform designed to optimise the location, configuration, and deployment sequence of smart EV charging points. To achieve this, the platform will integrate multiple big data sources (including mobile network data, public transport network and ridership data, land use, and electricity grid capacity) to yield high-resolution insights into traffic patterns (routes, dwell times), accessibility, and grid proximity and capacity. Advanced optimisation algorithms will process these insights to pinpoint locations and configurations that maximise demand coverage. This will empower city planners to identify optimal priority sites for municipal fleets, public transport, logistics operators, and private vehicles, while adhering to grid and operational constraints.

Goals

The primary objective of the InCharge Arteixo project is to develop, demonstrate, and validate an operational SaaS decision-support prototype in the municipality of Arteixo.

The specific objectives of the project are to:

1. Ingest and harmonise heterogeneous, large-scale data sources, such as mobile network data (MND), floating car data (FCD), public transport schedules, municipal fleet operations, electricity grid data, and land use information. A dedicated data engine will synthesise this raw data into high-resolution metrics mapping traffic patterns (routes, dwell times), accessibility, and grid proximity and capacity.
2. Develop and deploy advanced mathematical optimisation algorithms capable of processing the generated descriptive indicators. These algorithms will solve spatial allocation problems to identify infrastructure locations and charger configurations (e.g., charger types and capacities) that maximise overall demand coverage while respecting operational, budgetary, and electricity grid capacity constraints.
3. Build a decision-support platform featuring interactive maps and dynamic dashboards. This will enable end-users to explore the high-resolution insights, configure planning scenarios (e.g., budget constraints), and analyse recommended sites with ease.