Real-time Resource Allocation Research Articles

PMRNA: Parameter matching of realtime and non‐realtime applications for resource provisioning in fog‐integrated cloud

SummaryFog computing, an emerging technology, extends Cloud computing services to the network's edge in the proximity of the application request. This extension yields improvement in Bandwidth (BW) utilization, faster responses to Real‐Time (RT) and Internet of Things (IoT) requests, and the provision of the heterogeneous resource services. While extensive work has been conducted on resource allocation for RT and Non‐Real‐Time (NRT) requests separately in Fog as well as Cloud computing, there is limited focus on resource provisioning for mixed RT and NRT requests in the Fog‐integrated Cloud (FiC) environment. Moreover, the majority of the existing provisioning methods primarily consider parameters from the system's perspective, overlooking crucial user aspects such as deadline and request size. To address the gap, this work introduces a resource provisioning method named “Parameter Matching of Realtime and Non‐Realtime Applications (PMRNA),” which considers user parameters and resource information, gathered by the broker. The performance evaluation of the proposed model is done in CloudSim, using various combinations of RT and NRT requests along with diverse Fog and Cloud resource configurations. Evaluation metric includes average Execution Time (ET), average Waiting Time (WT), average Turn Around Time (TAT), and resource utilization. The experimental results demonstrate a significant reduction in both average WT and average TAT for the diverse pool of RT and NRT requests in the FiC compared to the Cloud‐only environment.

Mobile Edge Computing and Machine Learning in the Internet of Unmanned Aerial Vehicles: A Survey

Unmanned Aerial Vehicles (UAVs) play an important role in the Internet of Things and form the paradigm of the Internet of UAVs, due to their characteristics of flexibility, mobility, and low costs. However, resource constraints such as dynamic wireless channels, limited battery capacities, and computation resources of UAVs make traditional methods inefficient in the Internet of UAVs. The thriving of Mobile Edge Computing (MEC) and Machine Learning (ML) is of great significance and is promising for real-time resource allocation, trajectory design, and intelligent decision making. This survey provides a comprehensive review of key technologies, applications, solutions, and challenges based on the integration of MEC and ML in the Internet of UAVs. First, key technologies of MEC and ML are presented. Then, their integration and major issues in the Internet of UAVs are presented. Furthermore, the applications of MEC and ML in the Internet of UAVs under urban, industrial, and emergency scenarios are discussed. After that, this survey summarizes the current solutions for MEC and ML in the Internet of UAVs based on the considered issues. Finally, some open problems and challenges are discussed.

SNAF: DRL-Based Interdependent E2E Resource Slicing Scheme for a Virtualized Network

The fifth generation (5G) mobile cellular network relies on network slicing (NS) to satisfy the diverse quality of service (QoS) requirements of various service providers operating on a standard shared infrastructure. However, the synchronization of radio access network (RAN) and core network (CN) slicing has not been well-studied as an interdependent resource allocation problem. This work proposes a novel slice-to-node access factor (SNAF)-based end-to-end (E2E) slice resource provisioning scheme and deep reinforcement learning (DRL)-based real-time resource allocation algorithm for E2E interdependent resource slicing and allocation, respectively, specifically for RAN and CN. To ensure effective resource slicing and allocation, we consider the versatile user equipment (UEs) QoS requirements on transmission delay and data rate. Notably, the SNAF-based scheme provides proper resource provisioning and traffic synchronization, while the DRL-based algorithm allocates radio resources based on affordable traffic and backhaul resources. Based on the 5G air interface, we conduct system-level simulations to evaluate the performance of our proposed methods from various perspectives. Simulation results confirm that our proposed SNAF and DRL-based interdependent E2E resource slicing and allocation techniques achieve better E2E traffic-resource synchronization, and improve the QoS satisfaction with minimal resource utilization compared to other existing benchmark schemes.

Lightweight Digital Twin and Federated Learning With Distributed Incentive in Air-Ground 6G Networks

The sixth-generation (6G) wireless network is conceptualized to provide ubiquitous and reliable network access through effective inter-networking among space, air, and terrestrial networks, while posing considerable pressure on dynamic network orchestration. Digital twin (DT) provides an alternative approach to proactively make real-time resource allocation by mapping and learning the complex network topology. However, the dual challenges of limited energy capacity and insufficient computing power of unmanned aerial vehicles make it difficult to establish digital twin on aerial networks. In light of this, in this paper, we propose a lightweight DT empowered air-ground network architecture, where the DT modelling task is distributed to diverse ground devices based on federated learning. To improve the efficiency of DT modelling, we design a distributed incentive mechanism that incentivizes high-performance ground devices to take part in federated learning. Considering the computing burden and possible private disclosure caused by the incentive, we further solve the incentive scheme with a new distributed algorithm. The optimal solution, such as the local training rounds and required accuracy of terminal devices, could be calculated in parallel on ground devices.Simulation results show the effectiveness of the proposed lightweight DT scheme in terms of energy consumption and model accuracy.

Real-time resource allocation in the emergency department: A case study

Overcrowding is a phenomenon that affects Emergency Departments (EDs) worldwide determining a harmful impact on the healthcare provided. Because of the wide variety of different patient paths, in the literature the ED processes are usually modeled making significant assumptions, and neglecting fundamental aspects. Such assumptions could make sense for strategic or tactical decisions but nowadays the objective most frequently required by practitioners is the optimization of already available resources. To deal with this problem, we need to act at the operational level, with a particular attention to resource allocation in real time since arrivals and activities to be performed are known only over time. In this paper we present the case study of an Italian ED to investigate if an online allocation algorithm based on prioritization combined with a prediction tool can improve the ED performance, alleviating the overcrowding. Then, we propose several policies for the online allocation of the ED resources, which take into account the real-time state of the ED and the prediction of the next activities provided by an ad hoc process mining model. The proposed approach is validated and analyzed on the case study through a fine-grained simulation model. Results suggest that if the decisions of allocating resources for the execution of activities take into consideration the probably subsequent activities, then there is a room for improvement for the average door-to-doctor time, ED Length-of-Stay, and resource utilization.

Digital-twin based real-time resource allocation for hull parts picking and processing

Digital-twin based real-time resource allocation for hull parts picking and processing

DRL-Based Resource Allocation for Computation Offloading in IoV Networks

Due to the dynamic nature of a vehicular fog computing environment, efficient real-time resource allocation in an Internet of Vehicles (IoV) network without affecting the quality of service of any of the onboard vehicles can be challenging. This article proposes a priority-sensitive task offloading and resource allocation scheme in an IoV network, where vehicles periodically exchange beacon messages to inquire about available services and other important information necessary for making the offloading decisions. In the proposed methodology, the vehicles are stimulated to share their idle computation resources with the task vehicles, whereby a deep reinforcement learning algorithm based on soft actor–critic is designed to classify the tasks based on priority and computation size of each task for optimally allocating the power. Furthermore, we also design deep deterministic policy gradient (DDPG) and twin delayed DDPG (TD3) algorithms for the considered framework. In particular, the algorithms work toward achieving the optimal policy for task offloading by maximizing the mean utility of the considered network. Extensive numerical results under different network conditions, along with comparison among the three algorithms, are presented to validate the feasibility of distributed reinforcement learning for task offloading in future IoV networks.

Real-Time Resource Allocation in Passive Optical Network for Energy-Efficient Inference at GPU-Based Network Edge

In recent years, the advances in deep learning (DL) technology have greatly improved artificial intelligence (AI)-related research and services. Among them, real-time object recognition using network cameras has become an important technology for various applications. A large number of network cameras are being deployed for real-time object detection using DL models at GPU-based edge servers. A significant issue for widely deploying this type of systems is low-cost network deployment and low-latency data transmission. A promising option for efficiently accommodating numerous network cameras is time- and wavelength-division multiplexed passive optical network (TWDM-PON), which has prevailed in optical access network systems. The key challenge in a GPU-based inference system via TWDM-PON is to optimally allocate upstream wavelengths and bandwidths to enable real-time inference. To address this problem, this article proposes the concept of an inference system in which many cameras upload image data to a GPU-based edge server via TWDM-PON. A real-time resource allocation scheme for TWDM-PON is also proposed to guarantee low latency and time-synchronized data arrival at the edge. We formulated the wavelength and bandwidth allocation problem as a Boolean satisfiability problem (SAT) for fast computation. The performance of the proposed method is verified by computer simulation. The proposed scheme contributes to the increase in the batch size of arriving data at the edge server while ensuring low-latency data transmission. As a consequence, the computational efficiency of the GPU-based inference server is greatly improved by the increase in the batch size of data.

Intelligent Joint Network Slicing and Routing via GCN-Powered Multi-Task Deep Reinforcement Learning

In 6G mobile systems, network slicing is an emerging technology to support services with distinct requirements by dividing a common infrastructure into multiple logical networks. However, as a network management method, it is difficult for network slicing to achieve a real-time resource allocation to satisfy the stringent requirement of services in 6G networks. This paper introduces a joint network slicing and routing mechanism, which combines the network management and control framework to provide a fine-grained, real-time and dynamic resource allocation. Graph Convolutional Networks (GCN)-powered Multi-Task Deep Reinforcement Learning (DRL) is proposed to solve this complicated resource allocation problem. We first extend the DRL model into multi-task manner, where multiple output branches are matched to joint scheduling resources in every network slice. GCN with differentiable pooling mechanism is integrated into DRL model to capture the topological information from graph-structured network status. We implement our model in the SDN controller and evaluate it with representative topologies. The packet-level experiments show that 1) compared to rule-based and other learning-based methods, GCN-powered multi-task DRL can improve the performance of joint network slicing and routing; 2) our method is robust to diverse network environments; 3) in contrast with other learning-based algorithms, our method achieves a better performance.

Learning Power Allocation for Multi-Cell-Multi-User Systems With Heterogeneous Graph Neural Networks

A well-trained deep neural network (DNN) enables real-time resource allocation by learning the relationship between a policy and its impacting parameters. When wireless systems operate in dynamic environments, the DNN has to be re-trained frequently and hence training complexity should be low. A promising approach to deal with this issue is to construct DNNs with prior knowledge. In this paper, we show that the power allocation policy in multi-cell-multi-user systems exhibits a combination of permutation equivariance properties, which can be harnessed by graph neural networks (GNNs). In particular, we construct a heterogeneous graph and resort to heterogeneous GNN for learning the policy, whose outputs are only equivariant to some permutations of vertexes rather than arbitrary permutations as homogeneous GNNs. We prove that the properties of the functions learned by existing heterogeneous GNN for the formulated graph are inconsistent with the properties of the policy. To avoid the performance degradation by embedding wrong priors, we design a parameter sharing scheme for heterogeneous GNN such that the learned relationship satisfies the desired properties. Simulation results show that the sample and computational complexities for training the constructed GNN are much lower than existing DNNs to achieve the same sum rate.

Utilizing microblogs for optimized real-time resource allocation in post-disaster scenarios.

In the aftermath of a disaster event, it is of utmost important to ensure efficient allocation of emergency resources (e.g. food, water, shelter, medicines) to locations where the resources are needed (need-locations). There are several challenges in this goal, including the identification of resource-needs and resource-availabilities in real time, and deciding a policy for allocating the available resources from where they are available (availability-locations) to the need-locations. In recent years, social media, and especially microblogging sites such as Twitter, have emerged as important sources of real-time information on disasters. There have been some attempts to identify resource-needs and resource-availabilities from microblogging sites. However, there has not been much work on having a policy for optimized and real-time resource allocation based on the information obtained from microblogs. Specifically, the allocation of critical resources must be done in an optimal way by understanding the utility of emergency resources at various need-locations at a given point of time. This paper attempts to develop such a utility-driven model for optimized resource allocation in a post-disaster scenario, based on information extracted from microblogs in real time. Experiments show that the proposed model achieves much better allocation of resources than baseline models—the allocation by the proposed model is not only more efficient in terms of quickly bringing down resource-deficits at various need-locations, but also more fair in distributing the available resources among the various need-locations.

Distributed Artificial Intelligence Empowered Sustainable Cognitive Radio Sensor Networks: A Smart City on-demand Perspective

Smart cities are claimed to be smart if the new technologies are capable of providing desired sustainable outcome. The sustainable properties of smart city applications require less energy consumption and efficient resource allocation. The Internet-of-Things (IoT), 5G, and fog networks have emerged as the most crucial researched areas due to their numerous applications for smart cities to provide the desired sustainable outcome. The sustainable properties of Wireless Sensor Networks (WSNs) play a vital role in the deployment of these technologies into the physical world and efficient utilization of the available spectrum is a major problem faced here. As a potential solution of this, Cognitive Radio (CR) merged with WSN as Cognitive Radio Sensor Networks (CRSNs) make the smart perspective with high resource management through cooperative communication. The proposed work establishes a dynamic correlation between Secondary Users/nodes (SUs) in a single cluster according to their statistical behavior at the time of performing smart cooperative communication in CRSNs to improve sustainability of smart world IoT applications. Distributed Artificial Intelligence (DAI) is used to calculate the real-time resource allocation to these clusters using their respective Coordinator Agent (CoA) based on the dynamic behaviors. To improve sustainability in the smart city applications, the time delay in the prediction of vacant channels is reduced which results in making these applications become more energy efficient. The effectiveness of the proposed work is illustrated with mathematical analysis and simulation results confirm its better sustainable performance compared to the existing techniques.

Intelligent Dynamic Real-Time Spectrum Resource Management for Industrial IoT in Edge Computing.

Intelligent dynamic spectrum resource management, which is based on vast amounts of sensing data from industrial IoT in the space–time and frequency domains, uses optimization algorithm-based decisions to minimize levels of interference, such as energy consumption, power control, idle channel allocation, time slot allocation, and spectrum handoff. However, these techniques make it difficult to allocate resources quickly and waste valuable solution information that is optimized according to the evolution of spectrum states in the space–time and frequency domains. Therefore, in this paper, we propose the implementation of intelligent dynamic real-time spectrum resource management through the application of data mining and case-based reasoning, which reduces the complexity of existing intelligent dynamic spectrum resource management and enables efficient real-time resource allocation. In this case, data mining and case-based reasoning analyze the activity patterns of incumbent users using vast amounts of sensing data from industrial IoT and enable rapid resource allocation, making use of case DB classified by case. In this study, we confirmed a number of optimization engine operations and spectrum resource management capabilities (spectrum handoff, handoff latency, energy consumption, and link maintenance) to prove the effectiveness of the proposed intelligent dynamic real-time spectrum resource management. These indicators prove that it is possible to minimize the complexity of existing intelligent dynamic spectrum resource management and maintain efficient real-time resource allocation and reliable communication; also, the above findings confirm that our method can achieve a superior performance to that of existing spectrum resource management techniques.

Data-driven cloud simulation architecture for automated flexible production lines: application in real smart factories

In recent years, more manufacturing enterprises are building automated flexible production lines (AFPLs) to satisfy the dynamic and diversified demand. Currently, static planning methods can hardly meet the requirements of the dynamic resource allocation for AFPLs. The technologies of the digital twin can help solve dynamic problems. Therefore, we propose a data-driven cloud simulation architecture for AFPLs in smart factories. First, we design a cloud simulation platform as the architecture foundation. Second, we use the data-driven modelling and simulation method to achieve automated modelling. Third, we implement the system on the cloud using Java, MySQL, and the Anylogic platform, and verify the efficiency of the proposed method by experiments in the real workshop of a 3C (Computer, Communication, Consumer electronics) company. The experimental results show the proposed architecture can support the real-time resource allocation decisions to maximise the throughput in AFPLs. This paper makes contributions by proposing an architecture realising automatic modelling and data-driven simulation first in the cloud simulation environment, and filling the gap of dynamic resource allocation in the research of AFPLs.

Fatter or stronger: Resource allocation strategy and the underlying metabolic mechanisms in amphibian tadpoles

The allocation of resources between storage and somatic growth is an essential physiological phenomenon in animals. Allocation mechanisms have broad theoretical and applied implications. The real-time resource allocation patterns in animals remain to be elucidated, and there is limited understanding of the metabolic mechanisms. We investigated the resource allocation strategy of Rana omeimontis tadpoles. Their ontogenetic fat accumulation began when body weight increased to 30–50 mg, at which time storage had a high priority in resource allocation. Beyond this weight range, somatic growth accelerated but storage investment was maintained, resulting in a positive correlation between body fat index and body weight at the population level. This pattern could be explained by assuming a positive relationship between storage abundance and growth investment, and this was supported by the prioritized increment of body fat to body weight when tadpoles were provided with increased food. At the metabolic level, hepatic fat accumulation was accompanied by upregulated utilization of fat storage, and the tadpoles presented lipid-based energy metabolism. Activating the mobilization of hepatic fat storage promoted somatic growth. In short, the liver is like a reservoir with valves that regulate energy flow for downstream developmental processes. These results provide novel mechanistic insights into resource allocation.

TDD Massive MISO Piloting Strategy With User Information: A Reinforcement Learning Approach

In TDD massive MISO systems, user equipments (UEs) send channel measurement pilots to the BS for beamforming. Frequently sending these pilots, although improving beamforming, could consume significant communication resources. In this letter, we investigate how frequent these pilots should be sent for each UE so as to increase overall throughput performance for TDD massive MISO downlink. This real-time resource allocation problem is challenging due to non-trivial performance metric and boundary conditions. Assuming that instantaneous speed and location information of UEs can be obtained by the BS, we propose a reinforcement learning framework in which the BS acts as a learning agent to decide pilot intervals. Simulation results show that, for this multi-terminal setting where UEs compete for resources, using this centralized reinforcement learning framework, performance can be improved by choosing pilot intervals and transmission rates based on the UE information.

Strategic Timing and Dynamic Pricing for Online Resource Allocation

This paper optimizes dynamic pricing and real-time resource allocation policies for a platform facing nontransferable capacity, stochastic demand-capacity imbalances, and strategic customers with heterogenous price and time sensitivities. We characterize the optimal mechanism, which specifies a dynamic menu of prices and allocations. Service timing and pricing are used strategically to: (i) dynamically manage demand-capacity imbalances, and (ii) provide discriminated service levels. The balance between these two objectives depends on customer heterogeneity and customers’ time sensitivities. The optimal policy may feature strategic idlenexss (deliberately rejecting incoming requests for discrimination), late service prioritization (clearing the queue of delayed customers), and deliberate late-service rejection (focusing on incoming demand by rationing capacity for delayed customers). Surprisingly, the price charged to time-sensitive customers is not increasing with demand—high demand may trigger lower prices. By dynamically adjusting a menu of prices and service levels, the optimal mechanism increases profits significantly, as compared with dynamic pricing and static screening benchmarks. We also suggest a less information-intensive mechanism that is history-independent but fine-tunes the menu with incoming demand; this easier-to-implement mechanism yields close-to-optimal outcomes. This paper was accepted by Gabriel Weintraub, revenue management and market analytics.

AI-Driven Collaborative Resource Allocation for Task Execution in 6G-Enabled Massive IoT

In the foreseeable future, the rapid growth of devices in the Internet of Things (IoT) will make it difficult for 5G networks to ensure sufficient network resources. 6G technology has attracted increasing attention, bringing new design concepts to the dynamic real-time resource allocation. The resource requirements of devices are usually variable, so a dynamic resource allocation method is needed to ensure the smooth execution of tasks. Therefore, this article first designs a 6G-enabled massive IoT architecture that supports dynamic resource allocation. Then, a dynamic nested neural network is constructed, which adjusts the nested learning model structure online to meet training requirements of dynamic resource allocation. An AI-driven collaborative dynamic resource allocation (ACDRA) algorithm is proposed based on the nested neural network combined with Markov decision process training for 6G-enabled massive IoT. Extensive simulations have been carried out to evaluate ACDRA in terms of several performance criteria, including resource hit rate and decision delay time. The results validated that ACDRA improves the average resource hit rate by about 8% and reduces the average decision delay time by about 7% compared with three reference existing algorithms.

Optimal Multi-stage Configuration Allocation with Applications to Video Advertising

In modern applications of real-time resource allocation, for example allocating ad opportunities created by users to relevant advertisers during video streaming, a prevalent scenario is when an arriving user can be served under different configurations''. For example, in video advertising, a configuration can be an arrangement of video-ads of various lengths and formats for a subset of advertisers, showing up at different time-stamps of the video. Each selected configuration assigns a certain number of impressions to each advertiser. Depending on their long-term contracts, each advertiser is willing to pay for a certain number of impressions during the decision making horizon at a per-impression price depending on the assigned configuration. While this application is real-time, there is an inherent allowance for latency in showing ads to users, as several of these ads show up in the middle (or at the end) of the video. This provides an opportunity for ad allocator to batch the users and to make more profitable allocation decisions. While designing algorithms for the fully online variant of this setting has been studied in the literature [Devanur et al., 2016], the multi-stage variant where the allocation decisions are made batch-by-batch is not studied. Motivated by the above application, we study designing optimal competitive multi-stage configuration allocation algorithms (with preemption) in an adversarial setting, where users arrive in batches in a stage-wise fashion. The allocator then decides on an irrevocable configuration for each of the users in an arriving batch at each stage so as to maximize the total revenue. We propose a novel convex-programming based multi-stage configuration allocation algorithm that is 1-(1-1/K)^K competitive, where K is the number of stages. We further show an intimate connection between the convex programs used in each stage and a recursive functional equation (with a sequence of polynomials of decreasing degrees as its solution). Using this connection, we develop a recursive primal-dual analysis for our algorithm and extend the previous analysis framework of multi-stage fractional matching [Feng and Niazadeh, 2021] to this more general setting. Interestingly, we show there is an intimate connection between convex Lagrangian dual of each stage of our algorithm and how the primal-dual analysis needs to be set up, which might be of independent interest.

Deep Learning–Based Energy Beamforming With Transmit Power Control in Wireless Powered Communication Networks

In this paper, we propose deep learning–based energy beamforming in a multi-antennae wireless powered communication network (WPCN). We consider a WPCN where a hybrid access point (HAP) equipped with multiple antennae broadcasts an energy-bearing signal to wireless devices using energy beamforming. We investigate the joint optimization of the time allocation for wireless energy transfer (WET) and wireless information transfer (WIT) with the design for energy beams while minimizing the transmit power at the HAP for efficient use of its available resources. However, this is a non-convex problem, and it is numerically intractable to solve it. In the literature, the traditional approach to solving this problem is based on an iterative algorithm that incurs high computational and time complexity, which is not feasible for real-time applications. We study and analyze a deep neural network (DNN)-based scheme and propose a faster and more efficient approach for the fair approximation of a near-optimal solution to this problem. To train the proposed DNN, we acquire training data samples from a sequential parametric convex approximation (SPCA)-based iterative algorithm. Instead of acquiring data samples and training the DNN, which is highly complex, we use offline training for the DNN to provide a faster solution to the real-time resource allocation optimization problem. Through the simulation results, we show the proposed DNN scheme provides a fair approximation of the traditional SPCA method with low computational and time complexity.