Generative Diffusion Models (GDMs) have emerged as a transformative force in the realm of Generative Artificial Intelligence (GenAI), demonstrating their versatility and efficacy across various applications. The ability to model complex data distributions and generate high-quality samples has made GDMs particularly effective in tasks such as image generation and reinforcement learning. Furthermore, their iterative nature, which involves a series of noise addition and denoising steps, is a powerful and unique approach to learning and generating data. This paper serves as a comprehensive tutorial on applying GDMs in network optimization tasks. We delve into the strengths of GDMs, emphasizing their wide applicability across various domains, such as vision, text, and audio generation. We detail how GDMs can be effectively harnessed to solve complex optimization problems inherent in networks. The paper first provides a basic background of GDMs and their applications in network optimization. This is followed by a series of case studies, showcasing the integration of GDMs with Deep Reinforcement Learning (DRL), incentive mechanism design, Semantic Communications (SemCom), Internet of Vehicles (IoV) networks, etc. These case studies underscore the practicality and efficacy of GDMs in real-world scenarios, offering insights into network design. We conclude with a discussion on potential future directions for GDM research and applications, providing major insights into how they can continue to shape the future of network optimization.

Technological evolutions in the automobile industry, especially the development of connected and autonomous vehicles, have granted vehicles more computing, storage, and sensing resources. The necessity of efficient utilization of these resources leads to the vision of vehicular cloud computing (VCC), which can offload the computing tasks from the edge or remote cloud to enhance the overall efficiency. In this paper, we study the problem of computation offloading through the vehicular cloud (VC), where computing missions from edge cloud (EC) can be offloaded and executed cooperatively by vehicles in VC. Specifically, computing missions are further divided into computing tasks with interdependency and executed in different vehicles in the VC to minimize the overall response time. To characterize the instability of computing resources resulting from the high vehicular mobility, a mobility model focusing on vehicular dwell time is utilized. Considering the heterogeneity of vehicular computing capabilities and the inter-dependency of computing tasks, we formulate an optimization problem for task scheduling, which is NP-hard. For low complexity, a modified genetic algorithm (MGA) based scheduling scheme is designed where integer coding is used rather than binary coding, and relatives are defined and employed to avoid infeasible solutions. In addition, a task load based stability analysis of the VCC system is presented for the cases where some vehicles within the VC are offline. Numerical results demonstrate that the proposed scheme can significantly improve the utilization of computing resources while guaranteeing low latency and system stability.

The vehicular edge computing is considered an enabling technology for intelligent and connected vehicles since the optimization of communication and computing on edge has a significant impact on driving safety and efficiency. In this paper, with the road traffic assignment to "proactively" reshape the spatiotemporal distribution of resource demands, we investigate the joint service migration and mobility optimization problem for vehicular edge computing. The goal is to meet the service delay requirements of vehicular edge computing with minimum migration cost and travel time. As service migration and mobility optimization are coupled, the joint scheduling problem suffers from the curse of dimensionality, which cannot be solved in real time by centralized algorithms. To this end, a multi-agent deep reinforcement learning (MADRL) algorithm is proposed to maximize the composite utility of communication, computing, and route planning in a distributed way. In the MADRL algorithm, a two-branch convolution based deep Q-network is constructed to coordinate migration action and routing action. Extensive experimental results show that the proposed algorithm is scalable and substantially reduces service delay, migration cost and travel time as compared with the existing baselines.

With the advance of unmanned aerial vehicles (UAVs) and low earth orbit (LEO) satellites, the integration of space, air and ground networks has become a potential solution to the beyond fifth generation (B5G) Internet of remote things (IoRT) networks. However, due to the network heterogeneity and the high mobility of UAVs and LEOs, how to design an efficient UAV-LEO integrated data collection scheme without infrastructure support is very challenging. In this paper, we investigate the resource allocation problem for a two-hop uplink UAV-LEO integrated data collection for the B5G IoRT networks, where numerous UAVs gather data from IoT devices and transmit the IoT data to LEO satellites. In order to maximize the data gathering efficiency in the IoT-UAV data gathering process, we study the bandwidth allocation of IoT devices and the 3-dimensional (3D) trajectory design of UAVs. In the UAV-LEO data transmission process, we jointly optimize the transmit powers of UAVs and the selections of LEO satellites for the total uploaded data amount and the energy consumption of UAVs. Considering the relay role and the cache capacity limitations of UAVs, we merge the optimizations of IoT-UAV data gathering and UAV-LEO data transmission into an integrated optimization problem, which is solved with the aid of the successive convex approximation (SCA) and the block coordinate descent (BCD) techniques. Simulation results demonstrate that the proposed scheme achieves better performance than the benchmark algorithms in terms of both energy consumption and total upload data amount.