22 July 2021
Predictive analytics based on real-time data is crucial to reaching government targets to phase out the sale of new fossil-fuel powered vehicles by 2030, argues Geoff McGrath.
The rollout of Electric Vehicle (EV) infrastructure has long been a challenge in the debate around how the industry can support efforts to reach net zero emissions by 2050 or sooner. As the Department for Transport (DfT) have made clear in their Decarbonising Transport plan, reaching the target will depend a great deal on several variables – including the provision of alternative fuel and transport sources, and the capacity of Distribution Network Operators (DNOs) to accommodate shifting patterns of electricity consumption. First and foremost, however, we need a targeted approach to improving accessibility for consumers, which means understanding end-user demand and advancing our capabilities to roll out new charge point infrastructure smartly and at pace.
In broad policy terms, this means breaking down barriers between stakeholders, enhancing charge point accessibility for both fleet and consumer vehicles and investing in deprived neighbourhoods to avoid charging blackspots. This means adopting meaningful, data-driven models that are responsive, agile, and capable of delivering on ever-shifting consumer priorities. With the adoption of EVs so dependent on external factors, predictive analytics models combined with mobility and network data can help us to achieve these aims by better helping us map out risks and opportunities that are crucial to determining the success of the mass rollout of associated EV infrastructure.
Keeping charge points accessible for all
Mobility data combined with predictive analytics allows for the planning and understanding of future travel scenarios based on insight into aggregated patterns of behaviour. Part of its ongoing success in transport planning is that it can indicate key commuter routes in towns and cities and help pinpoint which areas are likely to experience a quicker EV uptake before the network is embedded.
This data can be leveraged in real-time to help local authorities to rollout charging infrastructure with a near-complete view of satisfying end-user demand. Predictive analytics can also drive cost savings and greater efficiency for councils and other local authorities deploying charge points that can drive a positive return on investment (ROI). We’ve seen proven success with this data in identifying which demographics are likeliest to invest in EVs (18–24-year-old ‘white collar’ workers) and it will be essential if we are to improve accessibility and public confidence in charge point provision.
Utilising real-time data enabled by predictive analytics and machine learning can enable developers, local and planning authorities and estate managers to better understand and leverage usage information. This means they can generate smarter, more flexible planning cyclers that can account for evolving trends we are witnessing such as reduced demand during off-peak hours and shifting rates of adoption of fleet EV vehicles. This information can also be integrated with additional systems data so that those responsible for demand planning can adopt a more holistic approach to catering for EV demand.
Meeting consumer demand
As well as forecasting demand for EV charge points, predictive analytics and real-time data monitoring can help shape the preparedness of DNOs and improve the resilience of their Low Voltage (LV) electricity networks). The ability to integrate several operational data sets through innovative machine learning capabilities means that operators can utilise new models that help estimate maximum load profiles for LV substations on DNO networks without relying on consumer smart meter data. Through embracing the art of the prediction through quality data and machine learning, we can ensure that DNOs are ready to meet consumer demand for new charge point infrastructure.
Widespread application of predictive analytics
From planning through to grid optimisation, predictive analytics will be a key tool in our mission to phase out the sale of fossil fuel-powered vehicles. To meet the UK’s 2035 deadline for phasing out the sale of diesel and fossil-fuel powered vehicles, we need a coordinated approach from different stakeholders to develop and deliver the right interventions during the development and operation of key assets. Making use of meaningful data and predictive modeling can ensure that we reach our target in an equitable, fair and sustainable manner.
To read CKDelta’s latest report, ‘Predictive Analytics. Powering an Electric Vehicle Revolution’, click here.
About the author Geoff McGrath is an entrepreneur, strategist, innovator and technologist. For over eight years, Geoff was the chief innovation officer for McLaren Applied, where he took insights from the world of Formula 1 to drive change in the wider transport sector and beyond, Geoff is now the Managing Director of data science business, CKDelta.
From time-to-time we host guest blogs or articles on our website. The views, opinions and positions expressed within these guest posts are those of the author alone and do not represent those of Electric Vehicle Association England.