Across the UK and Europe, major retailers and delivery operators are turning their attentions to ‘greening’ their fleets by investing in electric vehicles. Geoff McGrath, managing director of data specialist company CKDelta, discusses the role of predictive analytics in supporting fleet operators’ transition to EVs.

Geoff McGrath, managing director of CKDelta

The ban on the sale of new fossil fuel-powered vehicles is to be introduced in under a decade. Fleet operators and managers cannot delay planning for this battery-powered future. Significant investments in charging infrastructure and vehicles will be required. In a rapidly changing world, how can data help to de-risk decisions?

Analytical insights

Predictive analytics – the identification of trends found in large data sets to help understand future risk and opportunity – can help inform the decision, and investment-making, processes of businesses. This analytical insight can be used from inception through to completion to qualify the use of proposed installation locations at strategic hubs and depots – reviewing vicinity, availability of charging, and local network constraints.

Operators, when making the decision to switch to a battery-powered fleet and planning for this switchover, need to consider the capacity of the local energy grid. Installing numerous charge points might seem attractive, but what if the energy grid lacks the capacity to power them? By working with the Distribution Network Operators (DNOs), operators can ensure that they have the right connections by upgrading site infrastructure and to deliver the grid capacity required to charge their fleet.

Prior to engaging with DNOs, exploring analytical data can help operators understand at which sites charge points will best be utilised and offer the greatest Return on Investment (ROI). This will prove critical in the early years of EV adoption as their use is expected to grow at 47% Compound Annual Growth Rate (CAGR) through to 2026. EVs in business ownership will form a significant share of the early EV fleet as companies purchase vehicles ahead of the ICE ban in 2030 and can take advantage of EV incentives such as the 0% Benefit in Kind and 100% first year capital deductions.

By understanding these constraints companies are provided with supporting information that can underpin risks associated with investments, helping to ensure that each new installation can deliver an ROI for charge point operators and landowners.

Predictive analytics also provides us with concrete information on energy profiling at sites from a network of smart meters which could be installed to support ongoing monitoring and optimisation of charge point installations. These meters can harness data which, when used alongside other renewable and energy programmes, can support businesses in the pursuit of cost-efficient and sustainable energy choices.

Decentralised fleets

One of the greatest challenges facing major fleet operators is decentralisation. Many individuals working for major organisations take their vehicles home at the end of the day. In some parts of the country fewer than 30% of people have a driveway allowing them to charge off-street. Major fleet operators will need to consider how they can efficiently provide these individuals with a central charging hub in their local area. This could see companies cross-collaborating on the creation of ‘charge point hubs’ whereby businesses share transport hubs and associated costs.

Considered as part of a wider sustainability strategy this could provide fleet operators with a means of reducing infrastructure investment costs and their environmental footprint, while simultaneously boosting their competitive advantage. Mobility data can be harnessed and then combined with a variety of alternative data sets, either those in the public domain, or through private partnerships, to assist with this predictive infrastructure modelling. This would allow for the planning and understanding of future scenarios to understand aggregated patterns of fleet behaviour and means that forecasters can provide estimates and predictions of where (geographically) and when (time of day) there are likely to be peaks and troughs in demand for electricity at a given ‘charge point hub’.

Towards a data-driven future

The world is at a turning point in its pursuit of net zero emissions by 2030 or sooner. In the UK, we have an opportunity to set the EV standard and write the rules on delivering a successful rollout of EV infrastructure. To achieve this, industry must make use of data-driven modelling and simulation to plan for, and execute, a smooth transition to an economically and environmentally sustainable transportation sector.

To read CKDelta’s latest report, ‘Predictive Analytics. Powering an Electric Vehicle Revolution’, click here.