Purpose – The purpose of this paper is to propose a model for sharing network capacity on demand among different underloaded and overloaded P2P ROME-enabled networks. The paper aims to target networks of nodes with highly dynamic workload fluctuations that may experience a burst of traffic and/or massive nodes’ failure rates. Design/methodology/approach – The paper shows that when locally available network capacity is not adequate for the workload requirements, the excessive capacity needs to be sought into other networks with more availability. A random flat P2P overlay of the ROME servers is used for the discovery and movement of nodes between two networks. Centralised or decentralised DHT-based directories of available nodes cannot cope with high workload fluctuations and frequent join/leave actions of nodes. The paper also introduces semantics to refine the answers to the ones with the most appropriate nodes for the requesting network and to find the requested capacity faster and more efficiently. The behaviour of the model is simulated to evaluate with several experiments the model based on some metrics. Findings – The paper finds that all the user queries of an overloaded underlying network are dropped if G-ROME is not used but as G-ROME overlay satisfies the requested capacity of a ROME server, its Chord ring size increases. In case of uniformly distributed and/or plentiful capacity over the overlay, shallow searches may give very good results. On the contrary, deeper searches are required for scarce capacity but the number of messages increases almost exponentially. Originality/value – This paper provides a model for moving the required resources to the requesting job environment rather than the job and its context to the resource.