Using analytics to secure an equitable rollout of EV charge points
Transitioning away from models based on historical data to predictive analytics powered by real-time data to map consumer behaviour can unlock the electric vehicle (EV) infrastructure revolution, writes Geoff McGrath, Managing Director of CKDelta.
The rollout of electric vehicles (EVs) to the mass market has been a perennial challenge as we pursue a cleaner, greener economy. With most globalised economies committed to phasing out the sale of fossil-fuel powered vehicles by 2030, the opportunity for the industry to take the lead in reaching net zero emissions is clearer than ever.
And yet, patterns of market growth continue to be inconsistent. The delayed rollout of new charge point infrastructure has led to growing criticisms towards the risk of charging blackspots in rural and less affluent areas. Without the right policy and market framework to drive the EV rollout, the market boom risks becoming inequitable, inaccessible, and unsustainable for communities around the globe.
Central to the industry’s strategy for growth should be adopting meaningful, data-driven models that are responsive, agile, and capable of delivering against shifting consumer priorities. Historical data once served us well. It enabled us to train models to make predictions of future outcomes, based on limited variables. With shifting patterns of consumer behaviour borne of the pandemic, and new challenges in grid capacity and planning however, the old approach has proven inadequate for the scale and rate of change of the challenge we face.
The power of predictive analytics
Predictive analytics combined with real-time data is key to unlocking sustained growth of EV charge point infrastructure. The main functional application of the technology is to identify patterns found in large datasets to map future risks and opportunities. Predictive analytics can help develop data systems that embed intelligence through cost-efficient sensors and ubiquitous communications – enabling information to be shared openly and at-pace in unique digital interfaces. It can be integrated by developers, public sector bodies and service providers at all stages of the planning cycle and across different value chains – including in the utilities and manufacturing sectors.
By integrating charge point data early in planning cycles for new infrastructure, local authorities can predict end-user demand both in the planning and operational phases of development. Real-time data modelling enabled by predictive analytics also means we are able to better address the environmental challenges posed by urban planning. This can be achieved by integrating more flexible planning cycles that can account for evolving trends that become clearer with systems innovation. If we are serious about meeting our shared sustainability goals, we must move fast to adopt smart data models and implementation approaches.
Unique systems software modelled around the technology can also provide Distribution Network Operators (DNOs) visibility over patterns of consumption and capacity across the entire network. Predictive analytics is therefore a requirement to ensure that EVs and hybrid vehicles can enter the mass market equitably and at pace. With the right innovations, we can deliver the necessary revolution in EV infrastructure development.
Equitable delivery
Ultimately, the success of facilitating this revolution will hinge on fulfilling end-user demand. Using predictive analytics and adaptive intelligence to accommodate fluctuating patterns of usage can enable the industry to install new charge points en masse and mitigate the risks of unequal product demand and inaccessibility for the less economically mobile, and more rural communities. Measures to cut vehicle costs for consumers through loan and tariff mechanisms are to be welcomed. However, they risk being ineffectual if the industry is not using targeted data to create the conditions required for EVs to be adopted in the first place.
Just as EVs alone will not be the sole driver in our mission to reach net zero, so too predictive analytics is not the panacea to secure the successful rollout of charge point infrastructure. What it presents, however, is an integrated, whole-system solution that can be embedded at all stages of the planning system and across the value chain.
All data systems will inevitably be tested by shifting variables. Innovations in hydrogen technology look set to further disrupt the rollout of EV technology, and the current volatility of energy markets brings considerable risk in embedding new Low Voltage (LV) infrastructure into the grid. What predictive analytics can achieve is ensuring the industry remains resilient and provides consumers with the confidence needed to enable an equitable transition to net zero.
About the author
Geoff McGrath is an entrepreneur, strategist, innovator and technologist. For over eight years, Geoff was the former 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.
Image courtesy of CKDelta.
