User scheduling is a classical problem and key technology in wireless communication, which will still plays an important role in the prospective 6G. There are many sophisticated schedulers that are widely deployed in the base stations, such as Proportional Fairness (PF) and Round-Robin Fashion (RRF). It is known that the Opportunistic (OP) scheduling is the optimal scheduler for maximizing the average user data rate (AUDR) considering the full buffer traffic. But the optimal strategy achieving the highest fairness still remains largely unknown both in the full buffer traffic and the bursty traffic. In this work, we investigate the problem of fairness-oriented user scheduling, especially for the RBG allocation. We build a user scheduler using Multi-Agent Reinforcement Learning (MARL), which conducts distributional optimization to maximize the fairness of the communication system. The agents take the cross-layer information (e.g. RSRP, Buffer size) as state and the RBG allocation result as action, then explore the optimal solution following a well-defined reward function designed for maximizing fairness. Furthermore, we take the 5%-tile user data rate (5TUDR) as the key performance indicator (KPI) of fairness, and compare the performance of MARL scheduling with PF scheduling and RRF scheduling by conducting extensive simulations. And the simulation results show that the proposed MARL scheduling outperforms the traditional schedulers.
相關內容
Recently, Intelligent Transportation Systems are leveraging the power of increased sensory coverage and computing power to deliver data-intensive solutions achieving higher levels of performance than traditional systems. Within Traffic Signal Control (TSC), this has allowed the emergence of Machine Learning (ML) based systems. Among this group, Reinforcement Learning (RL) approaches have performed particularly well. Given the lack of industry standards in ML for TSC, literature exploring RL often lacks comparison against commercially available systems and straightforward formulations of how the agents operate. Here we attempt to bridge that gap. We propose three different architectures for TSC RL agents and compare them against the currently used commercial systems MOVA, SurTrac and Cyclic controllers and provide pseudo-code for them. The agents use variations of Deep Q-Learning and Actor Critic, using states and rewards based on queue lengths. Their performance is compared in across different map scenarios with variable demand, assessing them in terms of the global delay and average queue length. We find that the RL-based systems can significantly and consistently achieve lower delays when compared with existing commercial systems.
In this work, we develop practical user scheduling algorithms for downlink bursty traffic with emphasis on user fairness. In contrast to the conventional scheduling algorithms that either equally divides the transmission time slots among users or maximizing some ratios without physcial meanings, we propose to use the 5%-tile user data rate (5TUDR) as the metric to evaluate user fairness. Since it is difficult to directly optimize 5TUDR, we first cast the problem into the stochastic game framework and subsequently propose a Multi-Agent Reinforcement Learning (MARL)-based algorithm to perform distributed optimization on the resource block group (RBG) allocation. Furthermore, each MARL agent is designed to take information measured by network counters from multiple network layers (e.g. Channel Quality Indicator, Buffer size) as the input states while the RBG allocation as action with a proposed reward function designed to maximize 5TUDR. Extensive simulation is performed to show that the proposed MARL-based scheduler can achieve fair scheduling while maintaining good average network throughput as compared to conventional schedulers.
Volunteer computing is an Internet-based distributed computing system in which volunteers share their extra available resources to manage large-scale tasks. However, computing devices in a Volunteer Computing System (VCS) are highly dynamic and heterogeneous in terms of their processing power, monetary cost, and data transferring latency. To ensure both the high Quality of Service (QoS) and low cost for different requests, all of the available computing resources must be used efficiently. Task scheduling is an NP-hard problem that is considered one of the main critical challenges in a heterogeneous VCS. Due to this, in this paper, we design two task scheduling algorithms for VCSs, named Min-CCV and Min-V. The main goal of the proposed algorithms is jointly minimizing the computation, communication and delay violation cost for the Internet of Things (IoT) requests. Our extensive simulation results show that proposed algorithms are able to allocate tasks to volunteer fog/cloud resources more efficiently than the state-of-the-art. Specifically, our algorithms improve the deadline satisfaction task rates by around 99.5% and decrease the total cost between 15 to 53% in comparison with the genetic-based algorithm.
Deep Reinforcement Learning (DRL) widely applies to job scheduling and resource allocation applications and remarkably improves performances. Existing resource management approaches essentially optimize makespan minimization on the fixed number of jobs. Although previous researches purport to express breakthrough performances, we alternatively corroborate the job scheduling problem in a more practical scenario where the scheduler (1) aims to minimize average latency in a steady-state condition and (2) assigns varying numbers of tasks to heterogeneous resources. Broadly, these conditions are essential in the System-on-Chip (SoC) application, which developed with high-frequency job generation and operated distributed resources in a parallel. We assume the indefinite jobs are continuously injected into the simulation in a stream fashion and empirically discover that existing research hard adapts in the suggested scenario. Moreover, the agent must tackle concurrent observations caused by the task dependency. This paper introduces the Eclectic Interaction Matching technique to tackle such difficulties and the System-on-Chip Resource AdapTivE Scheduling (SoCRATES) that specialized in scheduling hierarchical jobs to heterogeneous resources the SoC application. The proposed method outperforms other existing RL-based schedulers and state-of-the-art heuristic schedulers.
We introduce DBS, a new technique for user selection in downlink multi-user communications with extra-large (XL) antenna arrays. DBS categorizes users according to their equivalent distance to the antenna array. Such categorization effectively accounts for inter-user interference while largely reducing the computational burden. Results show that (i) DBS achieves the same performance as the reference zero-forcing beamforming scheme with a lower complexity; (ii) a simplified version of DBS achieves a similar performance when realistic spherical-wavefront (SW) propagation features are considered; (iii) SW propagation brings additional degrees of freedom, which allows for increasing the number of served users.
Deep Reinforcement Learning has proved to be able to solve many control tasks in different fields, but the behavior of these systems is not always as expected when deployed in real-world scenarios. This is mainly due to the lack of domain adaptation between simulated and real-world data together with the absence of distinction between train and test datasets. In this work, we investigate these problems in the autonomous driving field, especially for a maneuver planning module for roundabout insertions. In particular, we present a system based on multiple environments in which agents are trained simultaneously, evaluating the behavior of the model in different scenarios. Finally, we analyze techniques aimed at reducing the gap between simulated and real-world data showing that this increased the generalization capabilities of the system both on unseen and real-world scenarios.
This paper presents an upgraded, real world application oriented version of gym-gazebo, the Robot Operating System (ROS) and Gazebo based Reinforcement Learning (RL) toolkit, which complies with OpenAI Gym. The content discusses the new ROS 2 based software architecture and summarizes the results obtained using Proximal Policy Optimization (PPO). Ultimately, the output of this work presents a benchmarking system for robotics that allows different techniques and algorithms to be compared using the same virtual conditions. We have evaluated environments with different levels of complexity of the Modular Articulated Robotic Arm (MARA), reaching accuracies in the millimeter scale. The converged results show the feasibility and usefulness of the gym-gazebo 2 toolkit, its potential and applicability in industrial use cases, using modular robots.
Accelerated Randomized Coordinate Descent Algorithms for Stochastic Optimization and Online Learning
We propose accelerated randomized coordinate descent algorithms for stochastic optimization and online learning. Our algorithms have significantly less per-iteration complexity than the known accelerated gradient algorithms. The proposed algorithms for online learning have better regret performance than the known randomized online coordinate descent algorithms. Furthermore, the proposed algorithms for stochastic optimization exhibit as good convergence rates as the best known randomized coordinate descent algorithms. We also show simulation results to demonstrate performance of the proposed algorithms.
We consider the multi-agent reinforcement learning setting with imperfect information in which each agent is trying to maximize its own utility. The reward function depends on the hidden state (or goal) of both agents, so the agents must infer the other players' hidden goals from their observed behavior in order to solve the tasks. We propose a new approach for learning in these domains: Self Other-Modeling (SOM), in which an agent uses its own policy to predict the other agent's actions and update its belief of their hidden state in an online manner. We evaluate this approach on three different tasks and show that the agents are able to learn better policies using their estimate of the other players' hidden states, in both cooperative and adversarial settings.
A recommender system aims to recommend items that a user is interested in among many items. The need for the recommender system has been expanded by the information explosion. Various approaches have been suggested for providing meaningful recommendations to users. One of the proposed approaches is to consider a recommender system as a Markov decision process (MDP) problem and try to solve it using reinforcement learning (RL). However, existing RL-based methods have an obvious drawback. To solve an MDP in a recommender system, they encountered a problem with the large number of discrete actions that bring RL to a larger class of problems. In this paper, we propose a novel RL-based recommender system. We formulate a recommender system as a gridworld game by using a biclustering technique that can reduce the state and action space significantly. Using biclustering not only reduces space but also improves the recommendation quality effectively handling the cold-start problem. In addition, our approach can provide users with some explanation why the system recommends certain items. Lastly, we examine the proposed algorithm on a real-world dataset and achieve a better performance than the widely used recommendation algorithm.
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