Dynamic Resource Allocation Problem Research Articles

Data-Driven Dynamic Optimization for Real-Time Parking Reservation Considering Parking Unpunctuality

This paper examines a real-time parking reservation service that dynamically allocates a limited number of parking slots (which can be reused) to serve parking requests in a crowded area. The study takes into account two stochastic factors: (i) random arrivals of parking requests and (ii) driver parking unpunctuality, which are seldom simultaneously considered in the existing literature. This study formulates the dynamic parking resource allocation problem as a joint chance-constrained model to maximize the expected total revenue over a finite horizon. Due to the complex nature of the model considering the two stochastic factors, the study proposes a data-driven approach using joint chance constraint decomposition and sample average approximation to approximate the model to a deterministic mixed-integer programming model. Furthermore, a stratified ranked set sampling method is introduced to construct a high-quality sample set as the input to the deterministic model, and valid inequalities are designed to accelerate the solution process. Numerical experiments based on real-world data are conducted to validate the performance of the proposed approach under multiple parking scenarios and provide findings.

Vehicle dynamic dispatching using curriculum-driven reinforcement learning

This study focuses on optimizing resource allocation problems in complex dynamic environments, specifically vehicle dispatching in closed bipartite queuing networks. We present a novel curriculum-driven reinforcement learning (RL) approach that seamlessly incorporates domain knowledge and environmental feedback, effectively addressing the challenges associated with sparse reward scenarios in RL applications. This approach involves a scalable reinforcement learning framework for dynamic vehicle fleet size. We design dense artificial rewards using domain knowledge and incorporate artificial action–reward pairs into the original experience sequence forming the basic structure of the training instances. A difficulty momentum boosting strategy is proposed to produce a series of training instances with progressively increasing difficulty, ensuring that the RL agent learns decision strategies in an organized and smooth manner. Experimental results demonstrate that the proposed method significantly surpasses existing approaches in enhancing productivity and model learning efficiency for transport tasks in open-pit mines, while confirming the superiority of a flexible and automated curriculum learning process over a rigid setting. This approach has vast potential for application in dynamic resource allocation problems across industries, such as manufacturing and logistics.

Allocation of Healthcare Resources in National Health Systems Under Climate Change

Climate change has, among others, impacts on human health and by consequence on healthcare systems. Some impacts are direct such as extreme events, air pollution and aeroallergens, and some are indirect such as reduced food production and supply, vector-borne and water-borne infectious diseases, and social and economic disruptions. The main aim of this paper is to study the pressures of climate change on national healthcare systems. An empirical dynamic resource allocation problem is proposed to estimate how healthcare systems may be affected by climate change. The problem is formulated as a nonlinear programming model which finds the optimal allocation of healthcare resources that compensate for life expectancy reductions due to climate change. We examine various scenarios of climate impacts to estimate the additional budget and healthcare resources needed. The results show that the necessary healthcare budget grows nonlinearly with respect to impacts with disproportional demands on lower income countries. Finally, the necessary healthcare investments should be made sooner as climate impacts become heavier. Our methodology could aid policy-makers in prioritizing measures to enhance the climate resilience of national healthcare systems.

DRL-Based Resource Allocation in Remote State Estimation

Remote state estimation where sensors send their measurements of distributed dynamic plants to a remote estimator over shared wireless resources is essential for mission-critical applications of Industry 4.0. Existing algorithms on dynamic radio resource allocation for remote estimation systems assumed oversimplified wireless communications models and can only work for small-scale settings. In this work, we consider remote estimation systems with practical wireless models over the orthogonal multiple-access and non-orthogonal multiple-access schemes. We derive necessary and sufficient conditions under which remote estimation systems can be stabilized. The conditions are described in terms of the transmission power budget, channel statistics, and plants’ parameters. For each multiple-access scheme, we formulate a novel dynamic resource allocation problem as a decision-making problem for achieving the minimum overall long-term average estimation mean-square error. Both the estimation quality and the channel quality states are taken into account for decision making. We systematically investigated the problems under different multiple-access schemes with large discrete, hybrid discrete-and-continuous, and continuous action spaces, respectively. We propose novel action-space compression methods and develop advanced deep reinforcement learning algorithms to solve the problems. Numerical results show that our algorithms solve the resource allocation problems effectively and provide much better scalability than the literature.

Learning Dynamic Computing Resource Allocation in Convolutional Neural Networks for Wireless Interference Identification

Wireless interference identification (WII) is a critical technology for the non-cooperative communication systems, and it is widely applied into military and civilian scenarios. With enormous success in many computer vision and language processing applications, deep learning (DL) has also achieved the remarkable performance for WII. However, existing DL based WII methods can not dynamically allocate proper computing resources conditioned on the inputs, causing serious waste of resources and low computational efficiency, which is unacceptable for edge computing devices, such as unmanned aerial vehicle (UAV)-aided systems. In this paper, the problem of dynamic computation resource allocation is modeled as adaptively learning forward propagation depth of networks on a per-input basis, and this novel method is termed as dynamic computing resource allocation in convolutional neural networks (DCRACNN). In particular, the proposed DCRACNN is composed of two subnetworks: a main network and a policy network. The main network is equipped with multiple classifiers at different depths, allowing test examples to stop early during inference so as to significantly improve computational efficiency. The policy network is optimized with reinforcement learning to address the bottleneck of non-differentiable decisions of optimal forward propagation depth for the main network while preserving recognition accuracy. To address the challenges of high error rates of early classifiers in the main network, novel methods are introduced, which can be seamlessly integrated into DRCACNN. In addition, a novel network pruning process is proposed for the main network to further reduce model sizes and computational complexity. Experiments demonstrate that DCRACNN can significantly reduce the calculation cost with boosting accuracy for WII.

Survey of Dynamic Resource-Constrained Reward Collection Problems: Unified Model and Analysis

Dynamic resource allocation problems arise under a variety of settings. In “Survey of Dynamic Resource-Constrained Reward Collection Problems: Unified Model and Analysis,” Balseiro, Besbes, and Pizarro introduce a unifying model for a large class of dynamic optimization problems dubbed dynamic resource-constrained reward collection (DRC2) problems. Surveying the literature, they show that this class encompasses a variety of disparate and classical problems typically studied separately, such as dynamic pricing with capacity constraints, dynamic bidding with budgets, network revenue management, online matching, or order fulfillment. Furthermore, they establish that the DRC2 class is amenable to analysis by characterizing the performance of a central, certainty-equivalent heuristic. Notably, they provide a novel unifying analysis that isolates the drivers of performance, recovers as corollaries some existing specialized results, generalizes other existing results by weakening the assumptions required, and yields new results in specialized settings for which no such characterization was available.

Communication-wise Comparison of the Online Resource Allocation Methods in CAV Fleets

Deploying fleets of Connected Autonomous Vehicles (CAVs), with limited peer-to-peer communication ranges, in order to provide On-demand Transport (ODT) services, requires a careful choice and evaluation of solution methods for resource allocation problems. We adopt in this paper a multiagent approach consists of: 1) defining a generic model to ODT's dynamic resource allocation problem in connected autonomous vehicle fleets, taking into account the limited connectivity and communication constraints, 2) behavior abstraction of AV Agents, and 3) abstracting the solution methods as Coordination Mechanisms (CMs) to define the characteristics of a solution method and its requirements to implement the corresponding planning sub-behavior. Using this methodology, we were able to compare the performance of a variety of solution methods with a set of evaluation criteria, namely for the solution Quality of Service (QoS) and Quality of Business (QoB). In this work, we focus on the communication-wise evaluation criteria, such as connectivity and network load.

Resource Allocation Based on Digital Twin-Enabled Federated Learning Framework in Heterogeneous Cellular Network

Federated learning (FL) allows user devices (UDs) to upload local model parameters to participate in a global model training, which protects UDs' data privacy. Nevertheless, FL still faces challenges such as core network congestion, UDs' limited resources and less efficient mapping between devices and cyber systems. Therefore, in this article, we integrate the digital twin (DT) and the mobile edge computing (MEC) technologies into a hierarchical FL framework in the heterogeneous cellular network scenario. When the UDs are not in the service range of the small base stations (SBSs), the framework allows macro base stations to assist UDs' local computation, thus reducing the transmission delay. It also protects the user privacy and allows more users to join in the training in order to improve the FL accuracy. In addition, we propose a deep reinforcement learning-based scheme to solve the joint optimization problem of dynamic UDs-stations association and resource allocation, thereby minimizing the energy consumption within a limited time delay. Simulation results show that our proposed scheme not only effectively reduces the task transmission failure rate and energy consumption compared with the baseline scheme, but also saves the communication cost through the DT network.

An Off-Policy Reinforcement Learning-Based Adaptive Optimization Method for Dynamic Resource Allocation Problem

An Off-Policy Reinforcement Learning-Based Adaptive Optimization Method for Dynamic Resource Allocation Problem

Enabling Long-term Fairness in Dynamic Resource Allocation

We study the fairness of dynamic resource allocation problem under the α-fairness criterion. We recognize two different fairness objectives that naturally arise in this problem: the well-understood slot-fairness objective that aims to ensure fairness at every timeslot, and the less explored horizon-fairness objective that aims to ensure fairness across utilities accumulated over a time horizon. We argue that horizon-fairness comes at a lower price in terms of social welfare. We study horizon-fairness with the regret as a performance metric and show that vanishing regret cannot be achieved in presence of an unrestricted adversary. We propose restrictions on the adversary's capabilities corresponding to realistic scenarios and an online policy that indeed guarantees vanishing regret under these restrictions. We demonstrate the applicability of the proposed fairness framework to a representative resource management problem considering a virtualized caching system where different caches cooperate to serve content requests.

Distributed Q-Learning Algorithm for Dynamic Resource Allocation With Unknown Objective Functions and Application to Microgrid.

Dynamic resource allocation problem (DRAP) with unknown cost functions and unknown resource transition functions is studied in this article. The goal of the agents is to minimize the sum of cost functions over given time periods in a distributed way, that is, by only exchanging information with their neighboring agents. First, we propose a distributed Q -learning algorithm for DRAP with unknown cost functions and unknown resource transition functions under discrete local feasibility constraints (DLFCs). It is theoretically proved that the joint policy of agents produced by the distributed Q -learning algorithm can always provide a feasible allocation (FA), that is, satisfying the constraints at each time period. Then, we also study the DRAP with unknown cost functions and unknown resource transition functions under continuous local feasibility constraints (CLFCs), where a novel distributed Q -learning algorithm is proposed based on function approximation and distributed optimization. It should be noted that the update rule of the local policy of each agent can also ensure that the joint policy of agents is an FA at each time period. Such property is of vital importance to execute the ε -greedy policy during the whole training process. Finally, simulations are presented to demonstrate the effectiveness of the proposed algorithms.

Dynamic Resource Allocation for Virtual Network Function Placement in Satellite Edge Clouds

Satellite edge computing has become a promising way to provide computing services for Internet of Things (IoT) users in remote areas, which are out of the coverage of terrestrial networks. Nevertheless, it is not suitable for large-scale IoT users due to the resource limitation of satellites. Cloud computing can provide sufficient available resources for IoT users, but it does not meet delay-sensitive services as high network latency. Satellite edge clouds can facilitate flexible service provisioning for numerous IoT users by incorporating the advantages of edge computing and cloud computing. In this paper, we investigate the dynamic resource allocation problem for virtual network function (VNF) placement in satellite edge clouds. The aim is to minimize the network bandwidth cost and the service end-to-end delay jointly. We formulate the VNF placement problem as an integer non-linear programming problem and then propose a distributed VNF placement (D-VNFP) algorithm to address it. The experiments are conducted to evaluate the performance of the proposed D-VNFP algorithm, where Viterbi and Game theory are considered as the baseline algorithms. The results show that the proposed D-VNFP algorithm is effective and efficient for solving the VNF placement problem in satellite edge clouds.

Order-Driven Dynamic Resource Configuration Based on a Metamodel for an Unbalanced Assembly Line

Resource-constrained product general assembly lines with complex processes face significant challenges in delivering orders on time. Accurate and efficient resources allocation of assembly lines remain a critical factor for punctual order delivery, full use of resources and associated customer satisfaction in complex production systems. In order to quickly solve the order-based dynamic resource allocation problem, in this paper a metamodel-based, multi-response optimization method is proposed for a complex product assembly line, which has the characteristics of order-based production, long working time of processes, multiple work area re-entry and restricted operator quantity. Considering the complexity of the assembly line and the uncertainty of orders, the correlation between system performance indicators and resource parameters is investigated. Multiple metamodels are constructed by the Response Surface Methodology to predict and optimize the system performance. The adequacy of the constructed metamodels is verified and validated based on the bootstrap resampling method. Under the condition of ensuring the throughput demand of the assembly line, the desirability function is applied to simultaneously optimize the multi-response, and the resource allocation solution is generated. The method in this paper can be used to rapidly adjust the resource configuration of the assembly line when considering the order changes.

Joint optimization of dynamic resource allocation and packet scheduling for virtual switches in cognitive internet of vehicles

The rapidly evolving machine learning technologies have reshaped the transportation system and played an essential role in the Cognitive Internet of Vehicles (CIoV). Most of the cognitive services are computation-intensive or storage-intensive, and thus they are usually deployed in edge or cloud data centers. In today’s data center networks, the virtual machines hosted in a server are connected to a virtual switch responsible for forwarding all packets for the cognitive services deployed on the virtual machines. Therefore, the virtual switches will become a performance bottleneck for cognitive services without an efficient resource allocation and data scheduling strategy. However, the highly dynamic characteristics of cognitive services make the resource allocation and packet scheduling problem for virtual switches surprisingly challenging. To guarantee the performance of cognitive services, we investigate the joint optimization problem of dynamic resource allocation and packet scheduling for virtual switches. We first model the joint optimization problem of dynamic resource allocation and packet scheduling for virtual switches as a mathematical optimization problem. Then, we analyze the problem with Lyapunov Optimization Framework and derive efficient optimization algorithms with performance tradeoff bounds. At last, we evaluate these algorithms on a testbed and a network-wide simulation platform. Experiment results show that our algorithms outperform other designs and meet the theoretical performance bound.

Dynamic Resource Allocation Using Improved Firefly Optimization Algorithm in Cloud Environment

ABSTRACT Today, cloud computing has provided a suitable platform to meet the computing needs of users. One of the most important challenges facing cloud computing is Dynamic Resource Allocation (DSA), which is in the NP-Hard class. One of the goals of the DSA is to utilization resources efficiently and maximize productivity. In this paper, an improved Firefly algorithm based on load balancing optimization is introduced to solve the DSA problem called IFA-DSA. In addition to balancing workloads between existing virtual machines, IFA-DSA also reduces completion time by selecting appropriate objectives in the fitness function. The best sequence of tasks for resource allocation is formulated as a multi-objective problem. The intended objectives are load balancing, completion time, average runtime, and migration rate. In order to improve the initial population creation in the firefly algorithm, a heuristic method is used instead of a random approach. In the heuristic method, the initial population is created based on the priority of tasks, where the priority of each task is determined based on the pay as you use model and a fuzzy approach. The results of the experiments show the superiority of the proposed method in the makespan criterion over the ICFA method by an average of 3%.

Multi-tier multi-tenant network slicing: A multi-domain games approach

The 5G slice networks will play a critical role in meeting the stringent quality-of-service requirements of different use cases, reducing the Capital Expenditure (CapEX) and Operational Expenditure (OpEX) of mobile network operators. Owing to the flexibility and ability of 5G slice networks to meet the needs of different verticals, it attracts new network players and entities to the mobile network ecosystem, and therefore it creates new business models and structures. Motivated by this development, this paper addresses the dynamic resource allocation in a multi-slice multi-tier multi-domain network with different network players. The dynamic resource allocation problem is formulated as a maximum utility optimisation problem from a multiplayer multi-domain perspective. Furthermore, a 3-level hierarchical business model comprising Infrastructure Providers (InPs), Mobile Virtual Network Operators (MVNOs), Service Providers (SPs), and slice users are investigated. We propose two schemes: a multi-tier multi-domain slice user matching game scheme and a distributed backtracking multiplayer multi-domain game scheme in solving the transformed maximum utility optimisation problem. We compare the multi-tier multi-tenant multi-domain game scheme with a Genetic Algorithm (GA) Intelligent Latency-Aware Resource (GI-LARE) allocation scheme, and a static slicing resource allocation scheme via Monte Carlo simulation. Our findings reveal that the proposed scheme significantly outperforms these other schemes.

Cost-and-Delay Aware Dynamic Resource Allocation in Federated Vehicular Clouds

Modern vehicular applications are resource-intensive and have different Quality of Service (QoS) requirements. In this direction, Vehicular Cloud Computing (VCC) has emerged as a new paradigm to host such applications in the cloud. In this paper, we extend the VCC paradigm to include federation, wherein the data centers from multiple cloud providers are pooled in to support applications that can not be supported in a single provider. We address the problem of dynamic resource allocation in a federated vehicular cloud. We propose a dynamic resource pricing model for sharing resources between the cloud providers, based on which we formulate resource allocation as an optimization problem. The objective is to minimize the cost of the vehicular service provider while meeting the delay bounds of different vehicular applications, for which a cost and delay-aware, polynomial-time algorithm is proposed. We evaluate the proposed algorithm under different scenarios to show that exploiting federation brings great benefits for the service providers and end-users alike. The proposed algorithm is seen to meet the delay requirements with a significant cost reduction to the provider up to 50% compared to baseline methods. We also show that the proposed algorithm can serve more than 90% of requests with lower cost and fewer VM migrations. It reduces the number of VM migrations by 72%.

A Review of Dynamic Resource Allocation Framework for Large Amount of Cloud Enterprises

Cloud computing is an on-demand service because it offers dynamic flexible resource allocation for reliable and guaranteed services in pay as-you-use manner. Because of the consistently increasing demands of the clients for services or resources, it gets hard to allocate resources accurately to the client demands to satisfy their solicitations and also to take care of the Service Level Agreements (SLA) gave by the service suppliers. Dynamic resource allocation problem is one of the most challenging problems in the resource management problems. The dynamic resource allocation in cloud computing has attracted attention of the research network in the last couple of years. Many researchers around the world have thought of new ways of facing this challenge. Ad-hoc parallel data handling has arisen to be one of the executioner applications for Infrastructure-as-a-Service (IaaS) cloud. Number of Cloud supplier companies has started to incorporate frameworks for parallel data handling in their item which making it easy for clients to access these services and to convey their programs. The handling frameworks which are at present utilized have been intended for static and homogeneous bunch arrangements. So the allocated resources may be inadequate for large parts of the submitted tasks and unnecessarily increase preparing cost and time. Again because of opaque nature of cloud, static allocation of resources is conceivable, yet the other way around in dynamic situations. The proposed new generic data handling framework is expected to expressly misuse the dynamic resource allocation in cloud for task scheduling and execution.

Survey of Dynamic Resource Constrained Reward Collection Problems: Unified Model and Analysis

Dynamic resource allocation problems arise under a variety of settings and have been studied across disciplines such as Operations Research and Computer Science. The present paper introduces a unifying model for a very large class of dynamic optimization problems, that we call dynamic resource constrained reward collection (DRC2). We show that this class encompasses a variety of disparate and classical dynamic optimization problems such as dynamic pricing with capacity constraints, dynamic bidding with budgets, network revenue management, online matching, or order fulfillment, to name a few. Furthermore, we establish that the class of DRC2 problems, while highly general, is amenable to analysis. In particular, we characterize the performance of the fluid certainty equivalent control heuristic for this class. Notably, this very general result recovers as corollaries some existing specialized results, generalizes other existing results by weakening the assumptions required, but also yields new results in specialized settings for which no such characterization was available. As such, the DRC2 class isolates some common features of a broad class of problems, and offers a new object of analysis.

D2Park

To address the increasingly serious parking pain, numerous mobile Apps have emerged to help drivers to find a convenient parking spot with various auxiliary information. However, the phenomenon of "multiple cars chasing the same spot" still exists, especially for on-street parking. Existing reservation-based resource allocation solutions could address the parking competition issue to some extent, but it is impractical to treat all spots as reservable resources. This paper first conducts a qualitative investigation based on the online survey data, which identifies diversified parking requirements involving i) reserved users, who request guaranteed spots with a reservation fee, ii) normal users, who request non-guaranteed spots with a "best-effort" service, and iii) external users, who do not use any guidance service. To this end, we design the D2Park system for diversified demand-aware parking guidance services. We formulate the problem as a novel Heterogeneous-Agent Dynamic Resource Allocation (HADRA) problem, which considers both current and future parking demands, and different constraints for diversified requirements. Two main modules are used in the system: 1) multi-step parking prediction, which makes multi-step parking inflow and occupancy rate predictions given the current parking events data and external factors; and 2) diversified parking guidance, which integrates the cooperation-based and competition-based resource allocation mechanisms based on a model predictive control framework to achieve a better performance balance among different user groups. Extensive experiments with a four-month real-world on-street parking dataset from the Chinese city Shenzhen demonstrate the effectiveness and efficiency of D2Park.