The dynamic mobility of IoT devices poses challenges to the sustainability of energy crowdsourcing ecosystems. This mobility often leads to imbalanced energy supply and demand across different locations. We propose a preference-aware crowdsourcing approach that aligns energy provisioning with providers’ mobility patterns. This approach balances under-supplied microcells by allocating providers based on their spatial and temporal proximity to energy demand. Considering providers’ preferences reduces behavioural resistance and lowers incentive costs. We develop a mobile energy service model that captures providers’ spatio-temporal provisioning preferences. Our approach utilises this model to maximise energy fulfilment and minimise rewards. We evaluated our approach using real datasets that are combined to simulate realistic crowdsourcing scenarios. The experiments demonstrate that our approach is faster and more cost-efficient than state-of-the-art heuristics.