| Abstract |
The proliferation of Internet of Things (IoT) services across diverse sectors such as healthcare, industrial IoT, and smart cities has introduced unprecedented complexity in network management and orchestration (MO). Contemporary MO systems are challenged to support the coexistence of IoT services with varying Quality of Service (QoS) requirements while ensuring end-to-end (E2E) performance across heterogeneous technologies and multiadministrator domain networks. To address these requirements, emerging technologies such as intelligent intent-based network slicing (I-IBNS) systems are increasingly employed, leveraging advancements in network automation, artificial intelligence (AI), and network slicing (NS). This article focuses on three critical challenges in developing I-IBNS systems for IoT: 1) E2E resource allocation; 2) privacy preservation in multiadministrator systems; and 3) E2E QoS assurance across heterogeneous networks and time-varying traffic. We propose a privacy-preserving I-IBNS framework, named Harmony Slice Master (H-SliceMaster), which integrates a knowledge management framework for privacy-aware data aggregation, an intent propagation mechanism for translating high-level intents into network configurations, and a novel promise and price network operation (PPNO) principle for optimizing E2E resource allocation while maintaining intradomain privacy. A proof-of-concept design of the H-SliceMaster is presented, utilizing deep Q-networks (DQNs) for intra-domain resource allocation and a centralized algorithm for optimizing E2E network slice deployment. Simulation results demonstrate that the H-SliceMaster efficiently satisfies various IoT applications and delay requirements. Moreover, the proposed system achieved an 20% and 50% reduction in system costs compared to a branching dueling Q-network (BDQ) and greedy algorithm, respectively. © 2014 IEEE. |
