SDD: spectral clustering and double deep Q-network based edge server deployment strategy

Introduction With the rapid development of 5G technology, Mobile Edge Computing (MEC) has become a critical component of next-generation network infrastructures. The efficient deployment of edge servers (ESs) is essential for enhancing service quality (QoS). However, existing deployment methods often fail in large-scale, high-density scenarios due to heterogeneous user distributions and highly variable task loads. Methods To address these challenges, we propose a Spectral Clustering and Double Deep Q-Network-based edge server deployment method (SDD). First, spectral clustering is applied to extract spatial features such as base station locations, dividing them into clusters and identifying candidate deployment centers. A reinforcement learning environment guided by the clustering structure is then constructed. A Double Deep Q-Network (DDQN) framework is introduced to jointly optimize server deployment and task load distribution. Results The proposed approach improves deployment efficiency and service quality by balancing system load and reducing service delay. We conduct large-scale experiments using a real base station dataset from the Shanghai Telecom Bureau. Our method is compared with multiple baselines, including Random, Improved Top-K, K-means, and ESL. Discussion The experimental results demonstrate that our method outperforms existing approaches in both delay reduction and load balancing. These findings validate the effectiveness and practicality of the proposed SDD framework in large-scale MEC environments.