More Like this

1. Data Offloading in UAV-assisted Multi-access Edge Computing Systems under Resource Uncertainty

   https://doi.org/10.1109/TMC.2021.3069911  

   Apostolopoulos, Pavlos Athanasios ; Fragkos, Georgios ; Tsiropoulou, Eirini Eleni ; Papavassiliou, Symeon ( January 2021 , IEEE Transactions on Mobile Computing)

   null (Ed.)

   In this paper, a novel data offloading decision-making framework is proposed, where users have the option to partially offload their data to a complex Multi-access Edge Computing (MEC) environment, consisting of both ground and UAV-mounted MEC servers. The problem is treated under the perspective of risk-aware user behavior as captured via prospect-theoretic utility functions, while accounting for the inherent computing environment uncertainties. The UAV-mounted MEC servers act as a common pool of resources with potentially superior but uncertain payoff for the users, while the local computation and ground server alternatives constitute safe and guaranteed options, respectively. The optimal user task offloading to the available computing choices is formulated as a maximization problem of each user's satisfaction, and confronted as a non-cooperative game. The existence and uniqueness of a Pure Nash Equilibrium (PNE) are proven, and convergence to the PNE is shown. Detailed numerical results highlight the convergence of the system to the PNE in few only iterations, while the impact of user behavior heterogeneity is evaluated. The introduced framework's consideration of the user risk-aware characteristics and computing uncertainties, results to a sophisticated exploitation of the system resources, which in turn leads to superior users' experienced performance compared to alternative approaches. 

   more » « less
2. Risk-Aware Social Cloud Computing Based on Serverless Computing Model

   https://doi.org/10.1109/GLOBECOM38437.2019.9013182  

   Apostolopoulos, Pavlos Athanasios ; Tsiropoulou, Eirini Eleni ; Papavassiliou, Symeon ( December 2019 , 2019 IEEE Global Communications Conference (GLOBECOM))

   In this paper, a flexible resource sharing paradigm is introduced, to enable the allocation of users’ computing tasks in a social cloud computing system offering both Virtual Machines (VMs) and Serverless Computing (SC) functions. VMs are treated as a safe computing resource, while SC due to the uncertainty introduced by its shared nature, is treated as a common pool resource, being susceptible to potential over-exploitation. These computing options are differentiated based on the potential satisfaction perceived by the user, as well as their corresponding pricing, while taking into account the social interactions among the users. Considering the inherent uncertainty of the considered computing environment, Prospect Theory and the theory of the Tragedy of the Commons are adopted to properly reflect the users’ behavioral characteristics, i.e., gain-seeking or loss-averse behavior, as well as to formulate appropriate prospect-theoretic utility functions, embodying the social-aware and risk-aware user’s perceived satisfaction. A distributed maximization problem of each user’s expected prospect-theoretic utility is formulated as a non-cooperative game among the users and the corresponding Pure Nash Equilibrium (PNE), i.e., optimal computing jobs offloading to the VMs and the SC, is determined, while a distributed low-complexity algorithm that converges to the PNE is introduced. The performance and key principles of the proposed framework are demonstrated through modeling and simulation. 

   more » « less
3. Risk-Aware Resource Management in Public Safety Networks

   https://doi.org/10.3390/s19183853  

   Vamvakas, Panagiotis ; Tsiropoulou, Eirini Eleni ; Papavassiliou, Symeon ( September 2019 , Sensors)

   null (Ed.)

   Modern Public Safety Networks (PSNs) are assisted by Unmanned Aerial Vehicles (UAVs) to provide a resilient communication paradigm during catastrophic events. In this context, we propose a distributed user-centric risk-aware resource management framework in UAV-assisted PSNs supported by both a static UAV and a mobile UAV. The mobile UAV is entitled to a larger portion of the available spectrum due to its capability and flexibility to re-position itself, and therefore establish better communication channel conditions to the users, compared to the static UAV. However, the potential over-exploitation of the mobile UAV-based communication by the users may lead to the mobile UAV’s failure to serve the users due to the increased levels of interference, consequently introducing risk in the user decisions. To capture this uncertainty, we follow the principles of Prospect Theory and design a user’s prospect-theoretic utility function that reflects user’s risk-aware behavior regarding its transmission power investment to the static and/or mobile UAV-based communication option. A non-cooperative game among the users is formulated, where each user determines its power investment strategy to the two available communication choices in order to maximize its expected prospect-theoretic utility. The existence and uniqueness of a Pure Nash Equilibrium (PNE) is proven and the convergence of the users’ strategies to it is shown. An iterative distributed and low-complexity algorithm is introduced to determine the PNE. The performance of the proposed user-centric risk-aware resource management framework in terms of users’ achievable data rate and spectrum utilization, is achieved via modeling and simulation. Furthermore, its superiority and benefits are demonstrated, by comparing its performance against other existing approaches with regards to UAV selection and spectrum utilization. 

   more » « less
4. Artificial Intelligence Enabled Distributed Edge Computing for Internet of Things Applications

   https://doi.org/10.1109/DCOSS49796.2020.00077  

   Fragkos, Georgios ; Tsiropoulou, Eirini Eleni ; Papavassiliou, Symeon ( May 2020 , 2020 16th International Conference on Distributed Computing in Sensor Systems (DCOSS))

   null (Ed.)

   Artificial Intelligence (AI) based techniques are typically used to model decision making in terms of strategies and mechanisms that can result in optimal payoffs for a number of interacting entities, often presenting antagonistic behaviors. In this paper, we propose an AI-enabled multi-access edge computing (MEC) framework, supported by computing-equipped Unmanned Aerial Vehicles (UAVs) to facilitate IoT applications. Initially, the problem of determining the IoT nodes optimal data offloading strategies to the UAV-mounted MEC servers, while accounting for the IoT nodes' communication and computation overhead, is formulated based on a game-theoretic model. The existence of at least one Pure Nash Equilibrium (PNE) point is shown by proving that the game is submodular. Furthermore, different operation points (i.e. offloading strategies) are obtained and studied, based either on the outcome of Best Response Dynamics (BRD) algorithm, or via alternative reinforcement learning approaches (i.e. gradient ascent, log-linear, and Q-learning algorithms), which explore and learn the environment towards determining the users' stable data offloading strategies. The corresponding outcomes and inherent features of these approaches are critically compared against each other, via modeling and simulation. 

   more » « less
5. Artificial Intelligence Empowered UAVs Data Offloading in Mobile Edge Computing

   https://doi.org/10.1109/ICC40277.2020.9149115  

   Fragkos, Georgios ; Kemp, Nicholas ; Tsiropoulou, Eirini Eleni ; Papavassiliou, Symeon ( June 2020 , 2020 IEEE International Conference on Communications (ICC))

   null (Ed.)

   The advances introduced by Unmanned Aerial Vehicles (UAVs) are manifold and have paved the path for the full integration of UAVs, as intelligent objects, into the Internet of Things (IoT). This paper brings artificial intelligence into the UAVs data offloading process in a multi-server Mobile Edge Computing (MEC) environment, by adopting principles and concepts from game theory and reinforcement learning. Initially, the autonomous MEC server selection for partial data offloading is performed by the UAVs, based on the theory of the stochastic learning automata. A non-cooperative game among the UAVs is then formulated to determine the UAVs' data to be offloaded to the selected MEC servers, while the existence of at least one Nash Equilibrium (NE) is proven by exploiting the power of submodular games. A best response dynamics framework and two alternative reinforcement learning algorithms are introduced that converge to an NE, and their tradeoffs are discussed. The overall framework performance evaluation is achieved via modeling and simulation, in terms of its efficiency and effectiveness, under different operation approaches and scenarios. 

   more » « less