Browsing by Author "Jamalipour, Abbas"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
- Deep Graph-based Reinforcement Learning for Joint Cruise Control and Task Offloading for Aerial Edge Internet-of-Things (EdgeIoT)Publication . Li, Kai; Ni, Wei; Yuan, Xin; Noor, Alam; Jamalipour, AbbasThis paper puts forth an aerial edge Internet-of-Things (EdgeIoT) system, where an unmanned aerial vehicle (UAV) is employed as a mobile edge server to process mission-critical computation tasks of ground Internet-of-Things (IoT) devices. When the UAV schedules an IoT device to offload its computation task, the tasks buffered at the other unselected devices could be outdated and have to be cancelled. We investigate a new joint optimization of UAV cruise control and task offloading allocation, which maximizes tasks offloaded to the UAV, subject to the IoT device’s computation capacity and battery budget, and the UAV’s speed limit. Since the optimization contains a large solution space while the instantaneous network states are unknown to the UAV, we propose a new deep graph-based reinforcement learning framework. An advantage actor-critic (A2C) structure is developed to train the real-time continuous actions of the UAV in terms of the flight speed, heading, and the offloading schedule of the IoT device. By exploring hidden representations resulting from the network feature correlation, our framework takes advantage of graph neural networks (GNN) to supervise the training of UAV’s actions in A2C. The proposed GNN-A2C framework is implemented with Google Tensorflow. The performance analysis shows that GNN-A2C achieves fast convergence and reduces considerably the task missing rate in aerial EdgeIoT.
- Deep Q-Learning based Resource Management in UAV-assisted Wireless Powered IoT NetworksPublication . Li, Kai; Ni, Wei; Tovar, Eduardo; Jamalipour, AbbasIn Unmanned Aerial Vehicle (UAV)-assisted Wireless Powered Internet of Things (IoT), the UAV is employed to charge the IoT nodes remotely via Wireless Power Transfer (WPT) and collect their data. A key challenge of resource management for WPT and data collection is preventing battery drainage and butter overflow of the ground IoT nodes in the presence of highly dynamic airborne channels. In this paper, we consider the resource management problem in practical scenarios, where the UAV has no a-prior information on battery levels and data queue lengths of the nodes. We formulate the resource management of UAV-assisted WPT and data collection as Markov Decision Process (MDP), where the states consist of battery levels and data queue lengths of the IoT nodes, channel qualities, and positions of the UAV. A deep Q-learning based resource management is proposed to minimize the overall data packet loss of the IoT nodes, by optimally deciding the IoT node for data collection and power transfer, and the associated modulation scheme of the IoT node.
- Leverage variational graph representation for model poisoning on federated learningPublication . Li, Kai; Yuan, Xin; Zheng, Jingjing; Ni, Wei; Dressler, Falko; Jamalipour, AbbasThis article puts forth a new training data-untethered model poisoning (MP) attack on federated learning (FL). The new MP attack extends an adversarial variational graph autoencoder (VGAE) to create malicious local models based solely on the benign local models overheard without any access to the training data of FL. Such an advancement leads to the VGAE-MP attack that is not only efficacious but also remains elusive to detection. VGAE-MP attack extracts graph structural correlations among the benign local models and the training data features, adversarially regenerates the graph structure, and generates malicious local models using the adversarial graph structure and benign models’ features. Moreover, a new attacking algorithm is presented to train the malicious local models using VGAE and sub-gradient descent, while enabling an optimal selection of the benign local models for training the VGAE. Experiments demonstrate a gradual drop in FL accuracy under the proposed VGAE-MP attack and the ineffectiveness of existing defense mechanisms in detecting the attack, posing a severe threat to FL.
- On-Board Deep Q-Network for UAV-Assisted Online Power Transfer and Data CollectionPublication . Li, Kai; Ni, Wei; Tovar, Eduardo; Jamalipour, AbbasUnmanned Aerial Vehicles (UAVs) with Microwave Power Transfer (MPT) capability provide a practical means to deploy a large number of wireless powered sensing devices into areas with no access to persistent power supplies. The UAV can charge the sensing devices remotely and harvest their data. A key challenge is online MPT and data collection in the presence of on-board control of a UAV (e.g., patrolling velocity) for preventing battery drainage and data queue overflow of the devices, while up-to-date knowledge on battery level and data queue of the devices is not available at the UAV. In this paper, an on-board deep Q-network is developed to minimize the overall data packet loss of the sensing devices, by optimally deciding the device to be charged and interrogated for data collection, and the instantaneous patrolling velocity of the UAV. Specifically, we formulate a Markov Decision Process (MDP) with the states of battery level and data queue length of devices, channel conditions, and waypoints given the trajectory of the UAV; and solve it optimally with Q-learning. Furthermore, we propose the on-board deep Q-network that enlarges the state space of the MDP, and a deep reinforcement learning based scheduling algorithm that asymptotically derives the optimal solution online, even when the UAV has only outdated knowledge on the MDP states. Numerical results demonstrate that our deep reinforcement learning algorithm reduces the packet loss by at least 69.2%, as compared to existing non-learning greedy algorithms.
- Online Velocity Control and Data Capture of Drones for the Internet of Things: An Onboard Deep Reinforcement Learning ApproachPublication . Li, Kai; Ni, Wei; Tovar, Eduardo; Jamalipour, AbbasApplications of unmanned aerial vehicles (UAVs) for data collection are a promising means to extend Internet of Things (IoT) networks to remote and hostile areas and to locations where there is no access to power supplies. The adequate design of UAV velocity control and communication decision making is critical to minimize the data packet losses at ground IoT nodes that result from overflowing buffers and transmission failures. However, online velocity control and communication decision making are challenging in UAV-enabled IoT networks, due to a UAV?s lack of up-to-date knowledge about the state of the nodes, e.g., the battery energy, buffer length, and channel conditions.