This two part LNCS 15227 and 15528 volumes constitutes the proceedings of the 20th IFIP WG 10.3 International Conference on Network and Parallel Computing, NPC 2024, which was held in Haikou, China, during December 7–8, 2024. The 76 full papers presented in this volume were carefully reviewed and selected from 200 submissions. They are organized according to the following topics:  Part-I : High-performance and Parallel Computing; Novel Memory and Storage Systems; and Emerging Architectures and Systems. Part-II : Edge Computing and Intelligence; Federated Learning Algorithms and Systems; Emerging Networks; and In-network Computing and Processing.

Table of Contents:
.- Edge Computing and Intelligence. .- A Fair Cooperation Strategy in the Edge-Edge Collaboration Scenario. .- Joint Optimization of Transmission and Computation for Multi-Source MEC System Based on Deep Reinforcement Learning. .- MARL-Based Joint Optimization of Service Migration and Resource Allocation in MEC. .- NBS-Based Mobile Edge Computing: A Joint Optimization of QoS and Energy in Computation Offloading. .- Optimizing Resource Allocation in the Internet of Vehicles: An Intelligent Vehicle-Edge-Cloud Collaboration Approach. .- Proactive Intellectual Property Protection for Edge AI Models. .- SC-TSDRL: A Cloud-Edge Collaboration Framework for Diffusion Model Inference Acceleration. .- Vickrey Auction Offloading for Edge-Assisted Video Analytics with Dynamic Gain Prediction. .- Federated Learning Algorithms and Systems. .- An Efficient Federated Meta Unlearning Algorithm with Enhanced Privacy Protection. .- Balanced Federated Learning with Two-stage Client Selection for Internet of Vehicles. .- Efficient Federated Learning with Cost-Adjustable Generative AI over Heterogeneous Edge Devices. .- FedDeSnowNet: Federated De-snowing Network for LiDAR Point Clouds. .- Federal Knowledge Graph Embedding Based on Incentive Mechanism. .- FedZipper: A Layer-wise Quantization Compression Framework for Federated Learning with Statistical Heterogeneity. .- Heterogeneous Federated Learning with Controlled Gradient Variate of Client Momentum. .- No Fear of Domain Discrepancy: One-Shot Federated Learning via Class-Aware Distillation. .- Trustworthy and Incentivized Federated Learning Based on Blockchain. .- Emerging Networks. .- A Satellite-Ground Link Handover Strategy in LEO Networks using Advantage Actor-Critic Algorithm. .- A Utility-Adjustable Reverse Auction Mechanism for UAV Data Collection Task Allocation. .- Adaptive Switching of Lightweight and Complex DNNs for Air-Ground Collaborative Intelligence. .- ADMM for Energy-efficient Computation Offloading in Marine Mobile Edge Computing Networks. .- Analytical Route Discovery Time Estimation for UAV Networks. .- Cross-Layer Intrusion Detection in UWSNs Using an Optimized CNN-LSTM Model. .- Efficient Task Offloading in MEC via UAV-UGV Collaboration. .- SUCP Analysis for Region-Centric UAV-Assisted MEC Networks. .- Task Offloading Optimization in Multi-layer LEO Satellite-Terrestrial Integrated Networks with Hybrid Cloud and Edge Computing. .- In-network Computing and Processing. .- 2FA Sketch: Two-Factor Armor Sketch for Accurate and Efficient Heavy Hitter Detection in Data Streams. .- A Large-Scale Study of Abnormal Recursive DNS. .- Adaptive Gradient Data Partition and Route Selection for Distributed DNN Training. .- DeepSight: In-network packet loss management for TCP applications in datacenter networks. .- DTN Routing Algorithm Based on Social Center and Classifier. .- E2E-AutoPT: an end-to-end automated penetration testing with LSTM-PPO approach. .- EAMTI: A Novel Method Toward Early and Accurate Malicious Traffic Identification. .- Gradient-aware Incremental Network Quantization. .- Providing Fine-grained Latency Control for Time Sensitive Networking: A Reordering Method. .- rpkt: A Generic, Safe, and Efficient Userspace Packet Processing Library in Rust. .- RuleAlchemy: Bidirectional Conflict-Aware Rule Aggregation for Crossed Probing Paths in SDN. .- RVCC: Congestion Control to Reduce Victim Flows in Data Center Networks. .- TAB: Traffic-aware Buffer Management on Programmable Switches.