From Artificial to Quantum Intelligence: The Next Frontier of Low-Carbon Energy Systems

Muhammad Ali Sahibzada; Hadi, Muhammad; Usama, Fnu; Khan, Muhammad Sarfraz; Iqbal, Mansoor; Ahmad, Shehzad

doi:10.1109/ICIICE69672.2026.11565487

From Artificial to Quantum Intelligence: The Next Frontier of Low-Carbon Energy Systems

Date Issued

April 18, 2026

Author(s)

Muhammad Ali Sahibzada

COMSATS University Islamabad

Hadi, Muhammad

Usama, Fnu

Khan, Muhammad Sarfraz

Iqbal, Mansoor

Ahmad, Shehzad

DOI

10.1109/ICIICE69672.2026.11565487

Abstract

The accelerating transition toward low-carbon energy systems introduces major computational and operational challenges driven by large-scale coupling, renewable uncertainty, and nonconvex energy management. While classical AI supports forecasting and control, its effectiveness degrades as dimensionality and stochasticity increase, limiting scalability and reliability. This paper proposes a hybrid Quantum–AI framework that combines probabilistic learning with quantum-ready optimization to address these limitations. The architecture integrates uncertainty-aware forecasting, constraint-aware preprocessing, and QUBO-based reformulation within a single decision pipeline. We evaluate the framework on an IEEE 118-bus system augmented with renewables, storage, and aggregated EV charging using approximately 150,000 real-world operational samples. Results show improved scalability, faster convergence, and stronger robustness under extreme uncertainty while preserving grid feasibility, alongside better cost–carbon performance, lower tail risk, improved EV coordination, and enhanced storage lifetime relative to classical baselines.