What question did this study set out to answer?

To develop an intelligent, collaborative framework for suppressing multi-source interference and optimizing resource allocation in dense heterogeneous communication networks.

August 16, 2026Advanced Electromagnetics0 citationsOpen Access

Research on Mobile Communication Interference Suppression Technology and Network Optimization for Heterogeneous Networks

YLY. LiKunming University of Science and Technology

Key Points

To develop an intelligent, collaborative framework for suppressing multi-source interference and optimizing resource allocation in dense heterogeneous communication networks.
Designed a deep reinforcement learning algorithm to adaptively adjust transmission power and spectrum allocation according to real-time channel conditions and traffic loads.
Formulated a privacy-preserving federated learning scheme to coordinate cross-domain resource scheduling and load balancing without sharing raw user data.
Evaluated performance using simulation experiments modeled on urban hotspots, high-speed railway environments, and industrial deployment settings.
Simulations demonstrated substantial qualitative improvements in interference mitigation capacity and overall network robustness across all test environments.
Cross-domain collaborative scheduling enhanced spectrum resource utilization efficiency and balanced network loads without exposing user-level data.

Abstract

The dense deployment of heterogeneous communication networks significantly improves spectrum utilization and network capacity but simultaneously introduces complex co-channel and cross-tier interference. To address the challenges of multi-source interference, dynamic network environments, and large-scale coordination, this study develops a collaborative framework integrating intelligent interference suppression and dynamic network optimization. A deep reinforcement learning-based interference coordination algorithm is first designed to adaptively adjust transmission power and spectrum resource allocation according to channel conditions and traffic load, thereby improving spectrum efficiency and reducing inter-layer interference. Subsequently, a federated learning-based crossdomain optimization strategy is proposed to achieve collaborative resource scheduling and load balancing without sharing raw user data. To validate the effectiveness of the proposed framework, simulation experiments are conducted under urban hotspot, high-speed railway, and industrial deployment scenarios. Results demonstrate significant improvements in interference mitigation capability, network robustness, and resource utilization efficiency. The proposed method provides technical support for future wireless communication systems and contributes to the development of electromagnetic wave propagation management, intelligent spectrum allocation, and next-generation heterogeneous networks.

AI से पूछें

Bookmark

View Full Paper