Artificial Intelligence Generated Content (AIGC) powered by Generative Diffusion Models (GDMs) has emerged as a transformative paradigm for automated content creation. To satisfy the stringent latency requirements of AIGC services in many edge intelligence scenarios (e.g., smart cities), Mobile Edge Computing (MEC) provides critical computational support by deploying GDMs at edge servers (ES) close to end users. This paper investigates an MEC-enabled AIGC network comprising multiple ES, wireless access points (APs), and mobile users (UEs) with heterogeneous latency and accuracy demands. We formulate aJoint Communication Association and Computation Offloading (JCACO)game, where each UE strategically selects its serving AP, ES, and inference steps to minimize the overall service completion time while meeting accuracy constraints. The problem is challenging due to the network dynamics and the incomplete information. We prove that the JCACO game is apotential gameunder both complete and stochastic information settings, ensuring the existence of Nash Equilibrium (NE) in both cases. To derive the NE efficiently, we develop a distributedMulti-Agent Stochastic Learning(MASL) algorithm that provably converges to the NE with strict performance guarantees. Unlike conventional best-response schemes, MASL requires neither the knowledge of other players’ strategies nor global network information, making it fully distributed and adaptive to dynamic environments. We further provide a strict theoretical convergence analysis for MASL by usingOrdinary Differential Equations(ODEs). Simulation results demonstrate that MASL significantly reduces service completion time compared with benchmark methods while satisfying accuracy constraints, confirming its effectiveness and practicality for real-world MEC-enabled AIGC networks.

Accurate traffic forecasting under diverse weather conditions is essential for intelligent transportation systems. However, most existing models overlook the complex interactions between weather, spatial, and temporal factors, and they often suffer from high computational cost on large-scale traffic networks. To address these limitations, we propose WeaGAN++, a weather-aware traffic prediction framework that integrates spatial-temporal dependencies and real-time weather conditions via a graph attention network. WeaGAN++ further incorporates a Connected Graph Clustering Algorithm (CGCA) to improve computational efficiency by partitioning large road networks into spatially connected clusters for localized attention processing. Experimental results on two real-world traffic datasets (PeMS-BAY and METR-LA) show that WeaGAN++ achieves up to 55.97% improvement in long-term prediction accuracy and up to an 73.47% reduction in computation time compared to state-of-the-art baselines. Additionally, our numerical analysis provides interpretable insights into the impact of weather conditions, revealing that temperature, rainfall, and pressure have a greater influence on traffic prediction than humidity and cloud cover.

Generative Artificial Intelligence (GenAI) enables digital representatives to make decisions on behalf of team members in collaborative tasks, but faces challenges in accurately representing preferences. While supplying GenAI with detailed personal information improves representation fidelity, feasibility constraints make complete information access impractical. We bridge this gap by developing a game-theoretic framework that models strategic information revelation to GenAI in collective decision-making. The technical challenges lie in characterizing members’ equilibrium behaviors under interdependent strategies and quantifying the imperfect preference learning outcomes by digital representatives. Our contribution includes closed-form equilibrium characterizations that reveal how members strategically balance team decision preference against communication costs. Our analysis yields an interesting finding: Conflicting preferences between team members drive competitive information revelation, with members revealing more information than those with aligned preferences. While digital representatives produce aggregate preference losses no smaller than direct participation, individual members may paradoxically achieve decisions more closely aligned with their preferences when using digital representatives, particularly when manual participation costs are high or when GenAI systems are sufficiently advanced.

The rapid growth of AI-generated content (AIGC) services has created an urgent need for effective prompt pricing strategies, yet current approaches overlook users' strategic two-step decision-making process in selecting and utilizing generative AI models. This oversight creates two key technical challenges: quantifying the relationship between user prompt capabilities and generation outcomes, and optimizing platform payoff while accounting for heterogeneous user behaviors. We address these challenges by introducing prompt ambiguity, a theoretical framework that captures users' varying abilities in prompt engineering, and developing an Optimal Prompt Pricing (OPP) algorithm. Our analysis reveals a counterintuitive insight: users with higher prompt ambiguity (i.e., lower capability) exhibit non-monotonic prompt usage patterns, first increasing then decreasing with ambiguity levels, reflecting complex changes in marginal utility. Experimental evaluation using a character-level GPT-like model demonstrates that our OPP algorithm achieves up to 31.72 % improvement in platform payoff compared to existing pricing mechanisms, validating the importance of user-centric prompt pricing in AIGC services.

The integration of photovoltaic (PV) systems, electric vehicles (EVs), and charging stations (CSs) faces critical challenges, including PV intermittency, uncertain EV charging demand, and inefficient energy management. Existing strategies often overlook the precision of PV generation forecasts, the economic risks of electricity trading, and the diverse demands of EVs, leading to suboptimal performance. To address these limitations, we propose a two-tier management framework for PV-CS-EV systems, optimizing energy storage charging station (ESCS) operations by balancing profit maximization and risk minimization. The first tier employs accurate PV forecasting and power trading strategies between ESCS, PV farms, and the grid to mitigate economic risks from PV intermittency and market fluctuations. The second tier provides diverse charging strategies to maximize user satisfaction and profit. A key challenge lies in the complex interdependencies between the two tiers, requiring simultaneous optimization of power trading and user-specific charging scheduling under uncertainties. To tackle this, we introduce a hierarchical multi-objective reinforcement learning (MORL) algorithm, which efficiently coordinates decision tasks of both tiers through partial environment information interaction. Experimental results demonstrate the framework’s effectiveness in enhancing the economic performance of PV-CS-EV systems.

The high-definition (HD) map is a cornerstone of autonomous driving. The crowdsourcing paradigm is a cost-effective way to keep an HD map up-to-date. Current HD map crowdsourcing mechanisms aim to enhance HD map freshness within recruitment budgets. However, many overlook unique and critical traits of crowdsourcing vehicles, such as random arrival and heterogeneity, leading to either compromised map freshness or excessive recruitment costs. Furthermore, these characteristics complicate the characterization of the feasible space of the optimal recruitment policy, necessitating a method to compute it efficiently in dynamic transportation scenarios. To overcome these challenges, we propose an efficient and cost-effective vehicle recruitment (ENTER) mechanism. Specifically, the ENTER mechanism has a threshold structure and balances freshness with recruitment costs while accounting for the vehicles’ random arrival and heterogeneity. It also integrates the bound-based relative value iteration (RVI) algorithm, which utilizes the threshold-type structure and upper bounds of thresholds to reduce the feasible space and expedite convergence. Numerical results show that the proposed ENTER mechanism increases the HD map company's payoff by 23.40$\%$and 43.91$\%$compared to state-of-the-art mechanisms that do not account for vehicle heterogeneity and random arrivals, respectively. Furthermore, the bound-based RVI algorithm in the ENTER mechanism reduces computation time by an average of 18.91% compared to the leading RVI-based algorithm.

A proper mechanism design can help federated learning (FL) to achieve good social welfare by coordinating self-interested clients through the learning process. However, existing mechanisms neglect the network effects of client participation, leading to suboptimal incentives and social welfare. This paper addresses this gap by exploring network effects in FL incentive mechanism design. We establish a theoretical model to analyze FL model performance and quantify the impact of network effects on heterogeneous client participation. Our analysis reveals the non-monotonic nature of FL network effects. To leverage such effects, we propose a model trading and sharing (MTS) framework that allows clients to obtain FL models through participation or purchase. To tackle heterogeneous clients' strategic behaviors, we further design a socially efficient model trading and sharing (SEMTS) mechanism. Our mechanism achieves social welfare maximization solely through customer payments, without additional incentive costs. Experimental results on an FL hardware prototype demonstrate up to 148.86% improvement in social welfare compared to existing mechanisms.

Bike Sharing Systems (BSSs) offer a flexible and sustainable transport option that has gained popularity in urban areas globally. However, as users move bikes according to their own needs, imbalanced bike distribution becomes a significant challenge for BSS operators. To address this problem, we propose a Workload Awareness (WA) approach that considers the rebalancing workload of BSS sub-networks and congestion issues when repositioning bikes dynamically. Our algorithm, WA, identifies sub-networks in a BSS and ensures a similar rebalancing load for each sub-network. Our mixed integer nonlinear programming (MINLP) model then finds a repositioning policy for each sub-network, taking into account operator capacity, bike and dock information, and minimizing total losses due to bike shortages and dock congestion. Our experiments on the Ningbo City Bike system demonstrate that our approach outperforms state-of-the-art methods by reducing the loss of the system by up to 60% and significantly reducing computational time by up to 36%.

In recent years, traffic conditions in centralised cities have become more severe. To optimise public resources and reduce congestion, transportation departments rely on traffic prediction. However, unexpected events, for instance, rainfall can impact traffic conditions, which necessitates the introduction of weather elements to improve prediction results. Moreover, most of the existing works characterise the relationship between weather and traffic by simply combining these two issues together. Without carefully designing a structure that captures the inter-dependency between weather and traffic data, it is impossible to produce accurate predictions within a reasonable computational time. To address this issue, we propose a Weather-Aware Graph Attention Network (WeaGAN) that adapts an encoder-decoder architecture with weather attention mechanisms and a gate to model the complex spatial-temporal inter-dependency between weather and traffic adaptively. We further design a self-attention mechanism to improve prediction accuracy. Our experiments on a standard real-world dataset show that, compared to the state-of-the-art, WeaGAN: (i) can improve the prediction accuracy by up to 29%; and (ii) is efficient in terms of saving up to 61% of the computation time.

The high-definition map is a cornerstone of autonomous driving. Unlike constructing a costly fleet of mapping vehicles, the crowdsourcing paradigm is a cost-effective way to keep an HD map up to date. Achieving practical success for crowdsourcing-based HD maps is contingent on addressing two critical issues: freshness and recruitment costs. Given that crowdsource vehicles are often heterogeneous in terms of operational costs and sensing capabilities, it is practical to recruit heterogeneous crowdsource vehicles to achieve the tradeoff between freshness and recruitment costs. However, existing works neglect this aspect. To solve it, we formulate this problem as a Markov decision process. We demonstrate that the optimal policy is threshold-type age-dependent. Additionally, our findings reveal some counter-intuitive insights. In some cases, the company should initiate vehicle recruitment earlier when vehicles arrive more frequently, or have higher operational costs or sensing capabilities. Besides, we propose an efficient algorithm, called the bound-based relative value iteration (BRVI) algorithm, to overcome the technical challenge that finding an optimal policy is time-consuming. Numerical simulations show that (i) the optimal policy reduces the average cost by 19.04℅ compared to the state-of-the-art mechanism, and (ii) the proposed algorithm can reduce the convergence time by 13.66℅ on average compared to the existing algorithm.

In crowdsourcing systems, it is important for the crowdsource campaign initiator to incentivize users to share their data to produce results of the desired computational accuracy. This problem becomes especially challenging when users are concerned about the privacy of their data. To overcome this challenge, existing work often aims to provide users with differential privacy guarantees to incentivize privacy-sensitive users to share their data. However, this work neglects the network effect that a user enjoys greater privacy protection when he aligns his participation behaviour with that of other users. To explore this network effect, we formulate the interaction among users regarding their participation decisions as a population game, because a user’s welfare from the interaction depends not only on his own participation decision but also the distribution of others’ decisions. We show that the Nash equilibrium of this game consists of a threshold strategy, where all users whose privacy sensitivity is below a certain threshold will participate and the remaining users will not. We characterize the existence and uniqueness of this equilibrium, which depends on the privacy guarantee, the reward provided by the initiator and the population size. Based on this equilibria analysis, we design the PINE (Privacy Incentivization with Network Effects) mechanism and prove that it maximizes the initiator’s payoff while providing participating users with a guaranteed degree of privacy protection. Numerical simulations, on both real and synthetic data, show that (i) PINE improves the initiator’s expected payoff by up to 75%, compared to state of the art mechanisms that do not consider this effect; (ii) the performance gain by exploiting the network effect is particularly good when the majority of users are flexible over their privacy attitudes and when there are a large number of low quality task performers.

A database-assisted TV white space network can achieve the goal of green cognitive communication by effectively reducing the energy consumption in cognitive communications. The success of such a novel network relies on a proper business model that provides substantial incentives for all parties involved. In this paper, we propose an integrated spectrum and information market for a database-assisted TV white space network, where a geolocation database acts as an online platform providing services to both a spectrum market and an information market. We model the interactions among the database operator, the spectrum licensee, and the unlicensed users as a three-stage sequential decision process. Specifically, Stage I characterizes the negotiation between the database and the spectrum licensee, in terms of the commission for the licensee to use the spectrum market platform, Stage II models the pricing decisions of the database and the spectrum licensee, and Stage III characterizes the subscription behaviors of the unlicensed users. Analyzing such a three-stage model is very challenging due to the co-existence of positive and negative network externalities in the information market. We explicitly characterize the impact of network externalities on the equilibrium behaviors of all parties involved. We also analytically show that the spectrum licensee can never get a market share larger than half in the integrated market. Our numerical results further show that the proposed integrated market can outperform the pure information market in terms of network profit up to 87%.

We propose a hybrid spectrum and information market for database-assisted TV white space networks, where a geo-location white space database serves as the platform for both the spectrum market and the information market. We study the interactions among the database operator, the spectrum licensee, and unlicensed users systematically, using a three-layer hierarchical model. In Layer I, the licensee negotiates with the database regarding the commission fee of using the spectrum market platform. In Layer II, the database and the licensee compete for selling information or channels to unlicensed users. In Layer III, unlicensed users determine whether to buy the exclusive usage right of licensed channels from the licensee, or to buy the information regarding unlicensed channels from the database. Analyzing such a three-layer model is challenging, due to the coexistence of both positive and negative network externalities in the information market. We characterize the market equilibrium systematically, and analyze how the network externalities affect the equilibrium behaviours of all parties involved. Our numerical results show that the proposed hybrid market can improve the network profit more than 80%, compared with a pure information market. Meanwhile, the achieved network profit is very close to the coordinated benchmark (e.g., the gap is less than 4%).

In this paper, we investigate an oligopoly-competitive TV white space (TVWS) market, where multiple secondary network operators compete to serve a common pool of secondary end users by using TVWS purchased from a white space database. We first study the competitive interactions among secondary operators. Specifically, we formulate the interactions as a noncooperative price-inventory competition game, where operators determine the spectrum inventory (purchased from the database) and the service price (charged to end users) simultaneously. We prove the existence and uniqueness of the Nash equilibrium using the supermodular game theory. Then, we study the impact of the database manager's wholesale pricing strategy on the market equilibrium. Specifically, we analytically show how the wholesale prices affect the operators' equilibrium inventory and pricing decisions. Based on this analysis, we further propose two different spectrum wholesale pricing strategies that maximize the database manager's profit and the total network profit, respectively. Our simulations evaluate the performance difference between these two wholesale pricing strategies.

Geo-location database-assisted TV white space network reduces the need for energy-intensive processes (such as spectrum sensing), and hence can achieve green cognitive communication effectively. The success of such a network relies on a proper business model that provides incentives for all parties involved. In this paper, we propose a Model of INformation markEt for GeO-Location Database (MINE GOLD), which enables databases to sell spectrum information to unlicensed white space devices (WSDs) for profit. Specifically, we focus on an oligopoly information market with multiple databases, and study the interactions among databases and WSDs using a two-stage hierarchical model. In Stage I, databases compete to sell information to WSDs by optimizing their information prices. In Stage II, each WSD decides whether and from which database to purchase the information, to maximize his benefit of using the TV white space. We first characterize how the WSDs' purchasing behaviors dynamically evolve, and what is the equilibrium point under fixed information prices from the databases. We then analyze how the system parameters and the databases' pricing decisions affect the market equilibrium, and what is the equilibrium of the database price competition. Our numerical results show that, perhaps counter-intuitively, the databases' aggregate revenue is not monotonic with the number of databases. Moreover, numerical results show that a large degree of positive network externality would improve the databases' revenues and the system performance.

In this paper, we propose a novel information market for TV white space networks, where the spectrum database operator sells the information regarding TV white space to secondary users. Different from the traditional spectrum market, the information market processes the unique property of positive externality, as more users purchasing the information service will increase the value of the service to each buyer. We systematically characterize the market equilibrium and the database operator's optimal information pricing strategy. Specifically, we first study how the market share dynamically evolves over time and eventually converge to a market equilibrium. We show that the market equilibrium increases with the initial market share, and there exist several tipping points of the initial market share, around which a slight change will lead to a significant change on the emerging market equilibrium. Based on the market equilibrium analysis, we further study the impact of the database operator's information pricing strategy on the market equilibrium, and derive the optimal information price that maximizes the database operator's revenue. Theoretical analysis and numerical result indicate that this is a promising business model for creating incentives for the database operator in TV white space networks.

The successful deployment of a TV white space network requires the coordination and cooperation of all involved parties (including licensees, databases, secondary operators, and end-users), which form the White Space Ecosystem. In this paper, we study the white space ecosystem from the perspective of secondary network operators. Specifically, we consider a competitive white space network, where multiple secondary operators compete for the same pool of end-users. Each operator serves the attracted end-users by using either the dedicated spectrum (pre-ordered in advance) or the shared spectrum (requested in real-time). The key problem for each operator is to (i) determine the order quantity of dedicated spectrum, considering the uncertainty of end-user demand, and (ii) decide the price to the end-users, considering the competition of other operators. We formulate the interaction of operators as a non-cooperative Price-Quantity competition game (PQ-game), and study the existence and uniqueness of the Nash equilibrium (NE) systematically. We further characterize the impacts of the operator competition on the social welfare and the operators' own profits. Our results show that such impacts depend largely on the operators' cost of purchasing spectrum from the database or licensee: when the cost is low, the operator competition will decrease the social welfare and the operators' profits; when the cost is high, however, the competition will increase the social welfare and the operators' profits.

Geo-location database driven white space network is a very promising approach for improving secondary spectrum utilization. In this paper, we consider the business modeling for geo-location database driven white space network. In our proposed model, the database acts as a spectrum broker buying (reserving) bandwidth from spectrum licensees in advance, and then resells the reserved bandwidth to unlicensed white space devices (WSDs) in real-time. We study the optimal bandwidth reservation for the database with WSDs' demand uncertainty under both information symmetry and asymmetry. Under information symmetry, the database and the WSD experience the same degree of uncertainty about the market demand. We derive the optimal bandwidth reservations in a centralized/integrated manner (as a benchmark). Under information asymmetry, the WSD has more information (i.e., with less uncertainty) about demand (due to the proximity to end-users). We propose a contract-based bandwidth reservation mechanism, which ensures WSDs share their local information with the database credibly. We further characterize the optimal bandwidth reservation contract systematically. Simulations show that under information asymmetry, the optimal bandwidth reservation contract improves both the database's profit and the social welfare significantly (larger than 30% in our simulations) without sacrificing the WSDs' benefits, comparing to those mechanisms without information sharing.