IEEE Best Paper 2025 Winner (Intelligent Transportation Track)

Enabling Equitable EV Charger Deployment in Berlin with Multi-Objective Geospatial Optimization

Multi-objective geospatial optimization framework to eliminate charging deserts and ensure socioeconomic parity.

Executive Summary

Berlin's transition to electric mobility faces a critical 'Last Mile' problem. Central districts like Mitte benefit from over-supply, while residential zones in Treptow-Köpenick and Pankow face ratios exceeding 30:1.

This study utilizes a Non-dominated Sorting Genetic Algorithm (NSGA-II) combined with Fuzzy-Robust logic to solve for the optimal placement of 500 new charging points. We prove that a 13% reduction in inequality is possible with minimal impact on total network utility.

Research Methodology

1

NSGA-II Algorithm

Genetic sorting ensures we discover the 'Pareto Front' of solutions that maximize coverage while minimizing the Gini coefficient.

2

Fuzzy Logic Control

Accommodates the inherent uncertainty in EV adoption rates, ensuring the network is resilient to future demand shifts.

Mathematical Formulation

// Objective 1: Maximize Coverage (Utility)

Maximize: f₁(x) = Σ (Pᵢ * Cᵢ) / Σ Pᵢ

// Objective 2: Minimize Gini Coefficient (Equity)

Minimize: f₂(x) = 1/2n²μ * ΣΣ |rᵢ - rⱼ|

rᵢ = chargers / registered BEVs per district i

The solver iterates through generations to identify the Pareto Front — the set of all non-dominated solutions.

Artifact Metadata

IEEE ETECOM 2025

10.1109/ETECOM66111.2025.11318989

Clifford O. Ondieki, T. Lu

Spatial Inequality reduced by 13.2%

Future Research Directions

The methodology is currently being adapted for other major European capitals.

Micro-Siting Granularity

Refining the model from district level to 100m x 100m geospatial grids.

DevelopmentActive

V2G Grid Dynamics

Integrating bidirectional energy flow constraints into the optimizer.

FocusPower Systems

Socioeconomic weighting

Adding household income layers to further refine the equity metric.

Data SetPending
Exclusive Resource

The Berlin EV Geospatial Strategy

A comprehensive 5-page technical roadmap for urban planners implementing equitable charging infrastructure. Learn how to apply multi-objective optimization to your city.

NSGA-II algorithm implementation guide with pseudocode

Geospatial data preprocessing workflow for GIS integration

VDE-AR-N 4110 compliance checklist for German grid operators

Fuzzy-robust optimization methodology with real-world validation

District-level equity metrics calculation framework

Get Instant Access

No spam. Unsubscribe anytime.

Secure • GDPR Compliant

Technical Methodology FAQ

Drive the Future of Urban Mobility

Interested in applying this optimization framework to your city or collaborating on future power systems research? Let's connect.

© 2025 Clifford O. Ondieki & T. Lu — IEEE ETECOM

Berlin Senate Department for Mobility, Transport, Climate Action and the Environment.