In 5G and beyond systems, the notion of latency gets a great momentum in wireless connectivity as a metric for serving real-time communications requirements. However, in many applications, research has pointed out that latency could be inefficient to handle applications with data freshness requirements. Recently, the notion of Age of Information (AoI) that can capture the freshness of the data has attracted a lot of attention. In this work, we consider mixed traffic with time-sensitive users; a deadline-constrained user, and an AoI-oriented user. To develop an efficient scheduling policy, we cast a novel optimization problem formulation for minimizing the average AoI while satisfying the timely throughput constraints. The formulated problem is cast as a Constrained Markov Decision Process (CMDP). We relax the constrained problem to an unconstrained Markov Decision Process (MDP) problem by utilizing Lyapunov optimization theory and it can be proved that it is solved per frame by applying backward dynamic programming algorithms with optimality guarantees. Simulation results show that the timely throughput constraints are satisfied while minimizing the average AoI. Also, simulation results show the convergence of the algorithm for different values of the weighted factor and the trade-off between the AoI and the timely throughput.
相關內容
Edge computing hosts applications close to the end users and enables low-latency real-time applications. Modern applications inturn have adopted the microservices architecture which composes applications as loosely coupled smaller components, or services. This complements edge computing infrastructure that are often resource constrained and may not handle monolithic applications. Instead, edge servers can independently deploy application service components, although at the cost of communication overheads. Consistently meeting application service level objectives while also optimizing application deployment (placement and migration of services) cost and communication overheads in mobile edge cloud environment is non-trivial. In this paper we propose and evaluate three dynamic placement strategies, two heuristic (greedy approximation based on set cover, and integer programming based optimization) and one learning-based algorithm. Their goal is to satisfy the application constraints, minimize infrastructure deployment cost, while ensuring availability of services to all clients and User Equipment (UE) in the network coverage area. The algorithms can be extended to any network topology and microservice based edge computing applications. For the experiments, we use the drone swarm navigation as a representative application for edge computing use cases. Since access to real-world physical testbed for such application is difficult, we demonstrate the efficacy of our algorithms as a simulation. We also contrast these algorithms with respect to placement quality, utilization of clusters, and level of determinism. Our evaluation not only shows that the learning-based algorithm provides solutions of better quality; it also provides interesting conclusions regarding when the (more traditional) heuristic algorithms are actually better suited.
Data-based and learning-based sound source localization (SSL) has shown promising results in challenging conditions, and is commonly set as a classification or a regression problem. Regression-based approaches have certain advantages over classification-based, such as continuous direction-of-arrival estimation of static and moving sources. However, multi-source scenarios require multiple regressors without a clear training strategy up-to-date, that does not rely on auxiliary information such as simultaneous sound classification. We investigate end-to-end training of such methods with a technique recently proposed for video object detectors, adapted to the SSL setting. A differentiable network is constructed that can be plugged to the output of the localizer to solve the optimal assignment between predictions and references, optimizing directly the popular CLEAR-MOT tracking metrics. Results indicate large improvements over directly optimizing mean squared errors, in terms of localization error, detection metrics, and tracking capabilities.
Road networks exist in the form of polylines with attributes within the GIS databases. Such a representation renders the geographic data impracticable for 3D road traffic simulation. In this work, we propose a method to transform raw GIS data into a realistic, operational model for real-time road traffic simulation. For instance, the proposed raw to simulation ready data transformation is achieved through several curvature estimation, interpolation/approximation, and clustering schemes. The obtained results show the performance of our approach and prove its adequacy to real traffic simulation scenario as can be seen in this video 1 .
Unmanned aerial vehicles (UAVs) are gaining immense attention due to their potential to revolutionize various businesses and industries. However, the adoption of UAV-assisted applications will strongly rely on the provision of reliable systems that allow managing UAV operations at high levels of safety and security. Recently, the concept of UAV traffic management (UTM) has been introduced to support safe, efficient, and fair access to low-altitude airspace for commercial UAVs. A UTM system identifies multiple cooperating parties with different roles and levels of authority to provide real-time services to airspace users. However, current UTM systems are centralized and lack a clear definition of protocols that govern a secure interaction between authorities, service providers, and end-users. The lack of such protocols renders the UTM system unscalable and prone to various cyber attacks. Another limitation of the currently proposed UTM architecture is the absence of an efficient mechanism to enforce airspace rules and regulations. To address this issue, we propose a decentralized UTM protocol that controls access to airspace while ensuring high levels of integrity, availability, and confidentiality of airspace operations. To achieve this, we exploit key features of the blockchain and smart contract technologies. In addition, we employ a mobile crowdsensing (MCS) mechanism to seamlessly enforce airspace rules and regulations that govern the UAV operations. The solution is implemented on top of the Etheruem platform and verified using four different smart contract verification tools. We also provided a security and cost analysis of our solution. For reproducibility, we made our implementation publicly available on Github.
We study constrained reinforcement learning (CRL) from a novel perspective by setting constraints directly on state density functions, rather than the value functions considered by previous works. State density has a clear physical and mathematical interpretation, and is able to express a wide variety of constraints such as resource limits and safety requirements. Density constraints can also avoid the time-consuming process of designing and tuning cost functions required by value function-based constraints to encode system specifications. We leverage the duality between density functions and Q functions to develop an effective algorithm to solve the density constrained RL problem optimally and the constrains are guaranteed to be satisfied. We prove that the proposed algorithm converges to a near-optimal solution with a bounded error even when the policy update is imperfect. We use a set of comprehensive experiments to demonstrate the advantages of our approach over state-of-the-art CRL methods, with a wide range of density constrained tasks as well as standard CRL benchmarks such as Safety-Gym.
Contextual multi-armed bandit (MAB) achieves cutting-edge performance on a variety of problems. When it comes to real-world scenarios such as recommendation system and online advertising, however, it is essential to consider the resource consumption of exploration. In practice, there is typically non-zero cost associated with executing a recommendation (arm) in the environment, and hence, the policy should be learned with a fixed exploration cost constraint. It is challenging to learn a global optimal policy directly, since it is a NP-hard problem and significantly complicates the exploration and exploitation trade-off of bandit algorithms. Existing approaches focus on solving the problems by adopting the greedy policy which estimates the expected rewards and costs and uses a greedy selection based on each arm's expected reward/cost ratio using historical observation until the exploration resource is exhausted. However, existing methods are hard to extend to infinite time horizon, since the learning process will be terminated when there is no more resource. In this paper, we propose a hierarchical adaptive contextual bandit method (HATCH) to conduct the policy learning of contextual bandits with a budget constraint. HATCH adopts an adaptive method to allocate the exploration resource based on the remaining resource/time and the estimation of reward distribution among different user contexts. In addition, we utilize full of contextual feature information to find the best personalized recommendation. Finally, in order to prove the theoretical guarantee, we present a regret bound analysis and prove that HATCH achieves a regret bound as low as $O(\sqrt{T})$. The experimental results demonstrate the effectiveness and efficiency of the proposed method on both synthetic data sets and the real-world applications.
Although recent neural conversation models have shown great potential, they often generate bland and generic responses. While various approaches have been explored to diversify the output of the conversation model, the improvement often comes at the cost of decreased relevance. In this paper, we propose a method to jointly optimize diversity and relevance that essentially fuses the latent space of a sequence-to-sequence model and that of an autoencoder model by leveraging novel regularization terms. As a result, our approach induces a latent space in which the distance and direction from the predicted response vector roughly match the relevance and diversity, respectively. This property also lends itself well to an intuitive visualization of the latent space. Both automatic and human evaluation results demonstrate that the proposed approach brings significant improvement compared to strong baselines in both diversity and relevance.
In this work, we consider the distributed optimization of non-smooth convex functions using a network of computing units. We investigate this problem under two regularity assumptions: (1) the Lipschitz continuity of the global objective function, and (2) the Lipschitz continuity of local individual functions. Under the local regularity assumption, we provide the first optimal first-order decentralized algorithm called multi-step primal-dual (MSPD) and its corresponding optimal convergence rate. A notable aspect of this result is that, for non-smooth functions, while the dominant term of the error is in $O(1/\sqrt{t})$, the structure of the communication network only impacts a second-order term in $O(1/t)$, where $t$ is time. In other words, the error due to limits in communication resources decreases at a fast rate even in the case of non-strongly-convex objective functions. Under the global regularity assumption, we provide a simple yet efficient algorithm called distributed randomized smoothing (DRS) based on a local smoothing of the objective function, and show that DRS is within a $d^{1/4}$ multiplicative factor of the optimal convergence rate, where $d$ is the underlying dimension.
Network Virtualization is one of the most promising technologies for future networking and considered as a critical IT resource that connects distributed, virtualized Cloud Computing services and different components such as storage, servers and application. Network Virtualization allows multiple virtual networks to coexist on same shared physical infrastructure simultaneously. One of the crucial keys in Network Virtualization is Virtual Network Embedding, which provides a method to allocate physical substrate resources to virtual network requests. In this paper, we investigate Virtual Network Embedding strategies and related issues for resource allocation of an Internet Provider(InP) to efficiently embed virtual networks that are requested by Virtual Network Operators(VNOs) who share the same infrastructure provided by the InP. In order to achieve that goal, we design a heuristic Virtual Network Embedding algorithm that simultaneously embeds virtual nodes and virtual links of each virtual network request onto physic infrastructure. Through extensive simulations, we demonstrate that our proposed scheme improves significantly the performance of Virtual Network Embedding by enhancing the long-term average revenue as well as acceptance ratio and resource utilization of virtual network requests compared to prior algorithms.
In this paper, we study the optimal convergence rate for distributed convex optimization problems in networks. We model the communication restrictions imposed by the network as a set of affine constraints and provide optimal complexity bounds for four different setups, namely: the function $F(\xb) \triangleq \sum_{i=1}^{m}f_i(\xb)$ is strongly convex and smooth, either strongly convex or smooth or just convex. Our results show that Nesterov's accelerated gradient descent on the dual problem can be executed in a distributed manner and obtains the same optimal rates as in the centralized version of the problem (up to constant or logarithmic factors) with an additional cost related to the spectral gap of the interaction matrix. Finally, we discuss some extensions to the proposed setup such as proximal friendly functions, time-varying graphs, improvement of the condition numbers.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191