EV charging forecasting exploiting traffic, weather and user information
Aristeidis Mystakidis, Nikolaos Tsalikidis, Paraskevas Koukaras, Georgios Skaltsis, Dimosthenis Ioannidis, Christos Tjortjis, Dimitrios Tzovaras
Abstract
Abstract Driven by the urgency of transitioning to a decarbonised energy sector, the confluence of Renewable Energy Sources (RES), Smart Grids (SG), and the widespread adoption of Electric Vehicles (EVs) has made power system planning and operation a focal point of global sustainability efforts. The rapid adoption of EVs has led to challenges related to charging infrastructure, grid demand, and scheduling management while also offering opportunities as a distributed energy storage solution, aiding peak load reduction and renewable energy integration. Enhanced accuracy in EV charging predictions could alleviate energy imbalances resulting from production and consumption disparities. Additionally, it supports SG architectural functions like demand response (DR) management. Compared to the initial baseline timeseries EV charging forecasting models, which performed poorly, the proposed strategy consists of a step-by-step forecasting methodology using data from predictions of road traffic, weather/seasonality, user charging information, and EV charging load. For each target, various novel implementations and models were conducted, including zero inflated (ZI) and a novel logarithmic ZI (LogZI) regression method. Results comparison indicated an increasing accuracy of EV charging demand forecasts from 78.1 to 88.7% regarding $$R^2$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msup> <mml:mi>R</mml:mi> <mml:mn>2</mml:mn> </mml:msup> </mml:math> . It also highlighted a decreasing error from 1.75 to 1.05 kWh regarding MAE and from 2.48 to 1.77 kWh regarding RMSE (CVRMSE and NRMSE were also provided). This research contributes a novel one step ahead EV charging demand forecasting framework integrating traffic and user charging predictions with the proposed LogZI regression approach. The proposed, updated version of the ZI approach, methodology performs significantly better compared to the baseline models, aiming to enhance grid stability and optimize charging infrastructure.