Preliminary Study on Adaptive Task and Resource Allocation for Digital Twin-Enabled Urban Services

In digital twin-enabled smart cities, the delivery of various urban services based on urban digital twins is expected. These services comprise various microservice-like artificial-intelligence-empowered atomic tasks that use dynamic spatial information through the digital twin. To maintain urban service quality amid fluctuating demand, effective resource utilization is essential. In this paper, we propose a system model for provisioning urban services composed of atomic tasks, along with an adaptive task and resource allocation method based on the monitor, analyze, plan, execute, and knowledge (MAPE-K) loop framework. Performance evaluation demonstrates that combining task quality and resource allocation adjustments enables effective adaptation to demand fluctuations.