Optimal Resource Allocation Scheme Research Articles

A DRL-based RAQ-GERT dynamic resource allocation algorithm considering utility for multibeam satellite system

With the evolution and popularity of smart devices, the demand and requirement (e.g., communication, file transfer) of satellite users have increased rapidly. Moreover, users have different preferences for services and the quality of service (QoS), like delay and throughput, which leading to user heterogeneity. Facing numerous, time-varying, and heterogeneous users, how to dynamically allocate limited spectrum and on-board power while satisfying user requirements is the major challenge for the multibeam satellite system (MSS). Aiming to seek a solution, firstly, the resource allocation queue graphical evaluation and review technique (RAQ-GERT) network is constructed to describe the service process of the MSS, as well as to compute the channel condition parameters during the whole process. Next, appropriate QoS indicators are selected based on user requirements. Then, QoS indicators are calculated from the results of the RAQ-GERT network, which are combined to form the optimization objective of the MSS by drawing on the Cobb–Douglas utility function. After that, guided by the utility of the MSS, the proximal policy optimization (PPO) algorithm is applied to explore the optimal resource allocation scheme in this heterogeneous user scenario. Finally, the simulation comparisons show that the proposed scheme has enhancements in several performances, up to 42.19 % in service rate, 53.58 % in system capacity, 1.24 % in latency, and 3.42 % in throughput.

Multi-UAV Assisted Air–Ground Collaborative MEC System: DRL-Based Joint Task Offloading and Resource Allocation and 3D UAV Trajectory Optimization

In disaster-stricken areas that were severely damaged by earthquakes, typhoons, floods, mudslides, and the like, employing unmanned aerial vehicles (UAVs) as airborne base stations for mobile edge computing (MEC) constitutes an effective solution. Concerning this, we investigate a 3D air–ground collaborative MEC scenario facilitated by multi-UAV for multiple ground devices (GDs). Specifically, we first design a 3D multi-UAV-assisted air–ground cooperative MEC system, and construct system communication, computation, and UAV flight energy consumption models. Subsequently, a cooperative resource optimization (CRO) problem is proposed by jointly optimizing task offloading, UAV flight trajectories, and edge computing resource allocation to minimize the total energy consumption of the system. Further, the CRO problem is decoupled into two sub-problems. Among them, the MATD3 deep reinforcement learning algorithm is utilized to jointly optimize the offloading decisions of GDs and the flight trajectories of UAVs; subsequently, the optimal resource allocation scheme at the edge is demonstrated through the derivation of KKT conditions. Finally, the simulation results show that the algorithm has good convergence compared with other algorithms and can effectively reduce the system energy consumption.

Competitive resource allocation on a network considering opinion dynamics with self-confidence evolution

The formation of public opinion is typically influenced by different stakeholders, such as governments and firms. Recently, various real-world problems related to the management of public opinion have emerged, necessitating stakeholders to strategically allocate resources on networks to achieve their objectives. To address this, it is imperative to consider the dynamics of opinion formation. Notably, in existing opinion dynamics models, individuals possess self-confidence parameters reflecting their adherence to historical opinions. However, most extant studies assume the individuals’ self-confidence levels remain constant over time, which cannot accurately capture the intricacies of human behavior. In response to this gap, we first introduce a self-confidence evolution model, which encompasses two influencing factors: the self-confidence levels of one's group mates and the passage of time. Furthermore, we present the social network DeGroot model with self-confidence evolution, and conduct some theoretical analyses. Moreover, we propose a game model to identify the optimal resource allocation strategies of players on a network. Finally, we provide sensitivity analyses, comparative studies, and a case study. This paper highlights the significance of incorporating self-confidence evolution into the process of opinion dynamics, and the results can provide valuable practical insights for players seeking to improve their optimal resource allocation on a network to more effectively manage public opinions.

Navigation Resource Allocation Algorithm for LEO Constellations Based on Dynamic Programming

Navigation resource allocation for low-earth-orbit (LEO) constellations refers to the optimal allocation of navigational assets when the number and allocation of satellites in the LEO constellation have been determined. LEO constellations can not only transmit navigation enhancement signals but also enable space-based monitoring (SBM) for real-time assessment of GNSS signal quality. However, proximity in the frequencies of LEO navigation signals and SBM can lead to significant interference, necessitating isolated transmission and reception. This separation requires that SBM and navigation signal transmission be carried out by different satellites within the constellation, thus demanding a strategic allocation of satellite resources. Given the vast number of satellites and their rapid movement, the visibility among LEO, medium-earth-orbit (MEO), and geostationary orbit (GEO) satellites is highly dynamic, presenting substantial challenges in resource allocation due to the computational intensity involved. Therefore, this paper proposes an optimal allocation algorithm for LEO constellation navigation resources based on dynamic programming. In this algorithm, a network model for the allocation of navigation resources in LEO constellations is initially established. Under the constraints of visibility time windows and onboard transmission and reception isolation, the objective is set to minimize the number of LEO satellites used while achieving effective navigation signal transmission and SBM. The constraints of resource allocation and the mathematical expression of the optimization objective are derived. A dynamic programming approach is then employed to determine the optimal resource allocation scheme. Analytical results demonstrate that compared to Greedy and Divide-and-Conquer algorithms, this algorithm achieves the highest resource utilization rate and the lowest computational complexity, making it highly valuable for future resource allocation in LEO constellations.

Optimal allocation of financial resources for ensuring reliable resilience in binary-state network infrastructure

In the dynamic landscape of network infrastructures, safeguarding resilience in binary-state systems has emerged as a focal point. This study delves into optimal financial resource allocation strategies to ensure that binary-state networks exhibit consistent and dependable recovery capabilities in the face of adversities, while satisfying the required reliability. Through a comprehensive exploration, we underscore the significance of resilience that is not only robust but also reliable and capable of surviving consecutive breakdowns. By zeroing in on binary-state networks, typified by their components exhibiting either operational or non-operational states, we elucidate strategic measures to fortify their intrinsic recovery mechanisms. Our research introduces a pioneering perspective on the imperative of astute resource distribution to achieve unyielding and trustworthy recovery processes amidst network disturbances. Furthermore, we present an innovative algorithm grounded in the binary-addition-tree algorithm (BAT) and stepwise vectors to adeptly address the problem. This study contributes to the discourse on reliable resilience, a novel form of resilience that enables a system to repeatedly recover from a series of unexpected failures, all within a limited and fixed recovery budget, while maintaining a required reliability and consistency in performance.

Bayesian network-based resilience assessment of interdependent infrastructure systems under optimal resource allocation strategies

Critical infrastructure systems (CISs) play a key role in the socio-economic activity of a society, but are exposed to an array of disruptive events that can greatly impact their function and performance. Therefore, understanding the underlying behaviors of CISs and their response to perturbations is needed to better prepare for, and mitigate the impact of, future disruptions. Resilience is one characteristic of CISs that influences the extent and severity of the impact induced by extreme events. Resilience is often dissected into four dimensions: robustness, redundancy, resourcefulness, and rapidity, known as the “4Rs”. This study proposes a framework to assess the resilience of an infrastructure network in terms of these four dimensions under optimal resource allocation strategies and incorporates interdependencies between different CISs, with resilience considered as a stochastic variable. The proposed framework combines an agent-based infrastructure interdependency model, advanced optimization algorithms, Bayesian network techniques, and Monte Carlo simulation to assess the resilience of an infrastructure network. The applicability and flexibility of the proposed framework is demonstrated with a case study using a network of CISs in Austin, Texas, where the resilience of the network is assessed and a “what-if” analysis is performed.

Distributed Event-Triggered Algorithm Designs for Resource Allocation Problems via a Universal Scalar Function-Based Analysis.

In this article, we are concerned with distributed algorithm designs for resource allocation problems via event-triggered communication. The target is to search an optimal resource allocation scheme such that the summation of objective functions is minimized. Due to communication efficiency and privacy concerns, distributed algorithms with event-triggered communications are proposed in this article. The communication is only permitted or triggered if variation of gradient of the local objective function exceeds a threshold. By constructing a novel technical lemma and a universal scalar function, the convergence and linear convergence rates are established under some mild assumptions. Extensive numerical experiments on the IEEE 118-bus power system demonstrate that: Compared to the periodic algorithms, such as ADMM and Mirror-P-EXTRA, the proposed algorithms not only remarkably reduce the communication times but also have competitive convergence speed. The latter is striking that it implies there exist useless communications in the periodic algorithms that are censored by the proposed event-triggered strategy.

Enhancing urban system resilience to earthquake disasters: Impact of interdependence and resource allocation

During the post-disaster recovery process of the urban system (US), it is critical to understand the interdependencies of critical infrastructure systems (CISs) and strategically allocate resources among them. However, due to the complexity of the problem and the limitations of the perspective, the existing research usually ignores the implicit impact of interdependence and resource allocation on urban resilience. To bridge this gap, this study establishes a multilayer network-based methodological framework to characterize various types of interdependencies between different CISs and integrate the US as a complex “system of systems”. Then, the system functionality of the US under different resource allocation strategies is quantified and optimized by resilience metrics. This proposed framework was demonstrated in a virtual US including a transportation subsystem (TS), an electric power supply subsystem (EPSS), and a community subsystem (CS) under catastrophic earthquakes. The sensitivity of urban resilience to interdependencies is investigated, and the corresponding results reveal that urban resilience is most sensitive to the interdependence between TS and EPSS. In particular, when there exists strong interdependence between the TS and EPSS, the optimal resource allocation strategy to maximize urban resilience is assigning resource allocation coefficients of 0.1, 0.8, and 0.1 for the TS, EPSS, and CS, respectively. These results can be effectively applied in future planning and investment in urban resilience.

An improved resource allocation method for mapping service function chains based on A3C

AbstractNetwork function virtualization (NFV) technology deploys network functions as software functions on a generalised hardware platform and provides customised network services in the form of service function chain (SFC), which improves the flexibility and scalability of network services and reduces network service costs. However, irrational resource allocation during service function chain mapping will cause problems such as low resource utilisation, long service request processing time and low mapping rate. To address the unreasonable problem of service mapping resource allocation, an improved service function chain mapping resource allocation method (SA3C) based on the Asynchronous advantageous action evaluation algorithm (A3C) is proposed. This study proposes an SFC mapping model and a mathematical model for joint allocation, which modeled the minimization of processing time as a Markov process. The main network was trained and multiple sub‐networks were generated in parallel using the ternary and deep reinforcement learning algorithm A3C, with the goal of identifying the optimal resource allocation strategy. The experimental simulation results show that compared with the Actor‐Critic (AC) and Policy Gradient (PG) methods, SA3C algorithm can improve the resource utilisation by 9.85%, reduce the total processing time by 10.72%, and improve the mapping rate by 6.72%, by reasonably allocating node computational resources and link bandwidth communication resources.

Optimal resource allocation strategy for integrated sensing and communication cellular network with multiple user demands

AbstractFuture communication networks are widely considered to be able to provide both high‐speed communication service and reliable sensing service. Integrated sensing and communication (ISAC) is considered to be the key technology to realize this vision. Appropriate resource allocation strategy is essential for ensuring the quality of both communication and sensing services in terms of ISAC. Existing ISAC‐based resource allocation schemes mainly focus on the coexistence of sensing and communication. However, in multi‐user ISAC networks, the services required by users are diverse, including sensing‐only, communication‐only and dual‐function cases. To this end, a resource allocation strategy is proposed based on user quality of service (QoS). Specifically, the sum rate of cellular network is maximized via optimizing spectrum resource selection and transmit power, while satisfying the sensing QoS. The optimal solution to the entire problem is achieved by first demonstrating that the communication rate in this paper is a monotonically increasing function of sensing power, which allows to obtain the optimal power allocation scheme. Subsequently, a matching method is employed to obtain the optimal spectrum sharing scheme. Numerical results validate the effectiveness of the proposed algorithm and also unveil a flexible trade‐off in ISAC systems over the benchmark scheme.

Optimization of resource allocation in remanufacturing systems: A labor and automation perspective

Remanufacturing depicts a pivotal strategy within the circular economy framework to conserve and reintroduce high-quality components after their end-of-use period. Despite its acknowledged labor-intensive nature, existing literature lacks comprehensive models to aid decision-makers in allocating resources efficiently. Moreover, there is a conspicuous absence of scheduling approaches tailored to optimize labor resource allocation amidst fluctuating supply and demand dynamics. In response, this paper introduces a quantitative optimization model that enables optimal resource allocation over discrete time intervals, that facilitate industrial decision-makers to plan their remanufacturing systems accordingly. Through an illustrative example, we evaluate the feasibility of our model by applying a dynamic programming algorithm to find the optimal resource allocation strategy. Here, we find that due to the variety of complexities associated with remanufacturing the achievement of an optimal solution necessitates judicious simplifications.

Autoencoder-Embedded Iterated Local Search for Energy-Minimized Task Schedules of Human–Cyber–Physical Systems

This work considers a task scheduling problem with deadline constraints in human-cyber-physical systems. To find its energy-efficient schedules in a short time, an autoencoder-embedded iterated local search algorithm is proposed to solve it. Iterated local search is selected as a main scheduler. In order to handle real-time requirements and high computational load involved in the problem solution, a Long Short-Term Memory-based AutoEncoder model (LSTM-AE) is constructed to capture the relevant and complementary features of the considered problem. The model is used to find low-order and high-fit sub-solutions via unsupervised end-to-end learning, and generates promising solutions in an informative low-dimensional solution space. To further reduce computational burden, a two-stage optimization framework is constructed, which includes an off-line training phase and an online optimization one. The former trains LSTM-AE by using expert knowledge and historical data. The latter designs optimal resource allocation strategies to build a high-quality initial solution. Then, LSTM-AE-assisted local search operators are proposed and used to reform the initial solution and generate better ones. Various numerical experiments are performed to compare the proposed method with several classic heuristics and some recently-developed methods. The results show its superiority over them. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —In human-cyber-physical systems, a task scheduling problem is usually solved by using heuristics due to the limited computational resources. Nevertheless, fast dispatching rules tend to perform poorly. Meta-heuristics can find a relatively high-quality schedule but are time-consuming, especially for a population-based algorithm that requires to evaluate a fitness function for many candidate solutions at each iteration. To balance computational burden and solution quality, our idea is to combine machine-learning methods with meta-heuristics. Specially, we integrate a long short-term memory-based autoencoder model into iterated local search to improve the latter’s optimization ability. The combination of meta-heuristics and machine learning techniques makes it possible to obtain a high-quality schedule for the concerned problems in a short time. Theoretic analysis and experimental results show that the proposed method well outperforms its competitive peers.

The Time-Sensitive Networking Scheduling Algorithm Based on Q-learning

Abstract Time-Sensitive Networking (TSN) occupies a vital position in modern communication domains, with the 802.1Qbv standard being an important network technology designed to meet real-time requirements. This standard requires network traffic to be transmitted within strict time windows, presenting challenges in network planning, necessitating efficient resource allocation and scheduling strategies. This paper addresses the 802.1Qbv planning problem through the introduction of reinforcement learning algorithms, offering an automated and intelligent solution. We have designed a reinforcement learning agent capable of perceiving network status, learning optimal resource allocation strategies, and dynamically adjusting in real-time environments. Through simulation and experimentation, we have validated the effectiveness of our proposed method, comparing it with traditional planning approaches. The contribution of this study lies in introducing a novel solution to the 802.1Qbv planning problem for time-sensitive networks, enhancing network resource utilization and performance. This approach offers strong support for the development and enhancement of TSN-like networks, holding significant importance for meeting the growing demands of real-time applications.

Multi-objective optimization and demand variation analysis on a water energy food nexus system

The interdependence of water, energy, and food resources demands a holistic approach to sustainable resource management. This study focuses on the mathematical optimization of the water-energy-food nexus system in Sinaloa state, Mexico. Using a multi-objective optimization model, we aimed to identify optimal resource allocation strategies and assess the implications of demand variation scenarios in the domestic sector. By considering various scenarios, ranging from reduced to increased demand, the study analyzes the trade-offs between resource consumption, economic benefits, and environmental impacts. The results reveal Pareto fronts that provide insights into efficient resource allocation, highlighting the relationships between water, energy, and food demand. The study provides recommendations for policymakers and contributes to knowledge on water-energy-food nexus optimization, emphasizing the need for integrated approaches to support sustainable resource management.

Deep Learning Framework for Two-Way MISO Wireless-Powered Interference Channels

In this paper, we present a realistic and novel protocol for two-way communication in multiple-input-single-output (MISO) wireless-powered interference channels, namely, a simultaneous wireless information and power transfer (SWIPT) then wireless information transfer (WIT) protocol. In the protocol considered, transmitters first perform SWIPT in a forward link (FL) and receivers and then execute WIT using the harvested energy in a backward link (BL). Given that the operation of SWIPT in the FL affects the performance of WIT in the BL, our aim is to find a resource allocation strategy that maximizes the sum spectral efficiency (SE) of the FL and BL, which requires the joint optimization of the transmit beamforming vector, transmit power, and energy harvesting (EH) ratio in the FL and the receive beamforming vector in the BL. To deal with the non-convexity of the optimization problem, a deep learning (DL) framework is devised, in which the optimal resource allocation strategy is approximated by a well-designed deep neural network (DNN) model consisting of six independent DNN modules where the sigmoid and softmax functions are jointly utilized to properly model each control parameter. Furthermore, a two-stage training method is proposed where the DNN model is initialized using suboptimal solutions that are found using a low complexity algorithm in a supervised manner before it is fine-tuned using the main training based on unsupervised learning. Through intensive simulations performed in various environments, we confirm that the proposed method improves the training performance of the DNN model while reducing the training overhead. As a result, the proposed DL-based resource allocation achieves a near-optimal performance in terms of the sum SE with a low computation time.

An Optimal Resource Allocation Scheme with Carrier Aggregation in 5G Network under Unlicensed Band

Carrier aggregation (CA) technology in the Fifth-Generation (5G) network can be considered as a major feature for high-rate data services, which can be combined with the concept of 5G in unlicensed band (5G-U) for data offloading to further enhance the efficiency of the scarce licensed spectral resource. However, the introduction of cellular services in an unlicensed spectrum can force unlicensed band users to silent mode. Meanwhile, the coexistence among different radio access technologies operating on the same frequency band is a complex issue, especially considering the requirement diversity of quality of service (QoS) in networking. In this paper, we propose an optimal resource allocation mechanism to maximize system performance satisfaction for multiple types of services with different QoS requirements in the 5G-U network with a CA feature to address the challenge. Additionally, the performance of services in Wi-Fi system is protected by reserving the minimum spectrum resource when offloading for the 5G-U network. Analytical results on the mean ergodic achievable rate of Wi-Fi services and the mean packet delay of 5G services are provided to maximize the system performance satisfaction. Numerical results demonstrate the effectiveness of the proposed algorithm, wherein optimal spectrum and power allocation can contribute to the maximum system satisfaction in a 5G-U network with a CA feature.

Resource Allocation Strategy for Satellite Edge Computing Based on Task Dependency

Satellite edge computing has attracted the attention of many scholars, but the limited resources of satellite networks bring great difficulties to the processing of edge-computing-dependent tasks. Therefore, under the system model of the satellite-terrestrial joint network architecture, this paper proposes an efficient scheduling strategy based on task degrees and a resource allocation strategy based on the improved sparrow search algorithm, aiming at the low success rate of application processing caused by the dependency between tasks, limited resources, and unreasonable resource allocation in the satellite edge network, which leads to the decline in user experience. The scheduling strategy determines the processing order of tasks by selecting subtasks with an in-degree of 0 each time. The improved sparrow search algorithm incorporates opposition-based learning, random search mechanisms, and Cauchy mutation to enhance search capability and improve global convergence. By utilizing the improved sparrow search algorithm, an optimal resource allocation strategy is derived, resulting in reduced processing latency for subtasks. The simulation results show that the performance of the proposed algorithm is better than other baseline schemes and can improve the processing success rate of applications.

Managing Water-Energy-Carbon Nexus for Urban Areas With Ambiguous Moment Information

The rapid growth of electric load fuels urbanization but creates unsettling environmental challenges. In that regard, the energy system is a crucial part of consuming water and emitting greenhouse gases. To support reliable and economical energy system operations, with reduced water waste and carbon emissions, we design a viable co-optimization of water-energy-carbon nexus for an integrated energy system by adequately modelling essential interdependencies of power, gas, and water systems. A two-stage distributionally robust optimization method is proposed: the first-stage model minimizes the day-ahead reserve capacity scheduling for the next day, and the second-stage model enables real-time dispatch by considering the variability in renewable power generation. The carbon emissions by power generation and distribution are incorporated in both stages to ensure low-carbon operations. We use a two-stage moment-based distributionally robust approach to capture and represent the uncertainties in renewable generation. Instead of assuming a deterministic distribution, we characterize an ambiguity set with mean vectors and covariance matrices, which produces a family set of distributions. We conduct case studies using a modified IEEE 33-bus power system that includes and links a 20-node gas system and a 10-node water system. The comparative results indicate that the proposed co-optimization of water-energy-carbon nexus is superior than several benchmarks. By considering the close interdependencies of water, energy, and carbon, we create an optimal resource allocation scheme, which is capable of minimizing operation costs, lessening carbon emissions, and reducing water waste. The current research enables effective operation schemes for urban energy systems, illustrates a viable way to curb local environmental emissions, and increases water usage efficiency in the water-energy-carbon nexus.

URLLC-eMBB hierarchical network slicing for Internet of Vehicles: An AoI-sensitive approach

Network slicing has been considered as a promising candidate to meet the heterogeneous Quality of Service (QoS) requirements of various vehicular applications. In this paper, network slicing is utilized on the Road Side Unit (RSU) side for the heterogeneous data freshness requirements in Internet of Vehicles (IoV). The services in enhanced Mobile BroadBand (eMBB) slice are usually bandwidth-consuming, thus the performance can be characterized by throughput. Unlike eMBB slice, the services in Ultra-Reliable Low-Latency Communications (URLLC) slice are usually time-critical, calling for fresh content delivery within short delay, in this case, the trade-off can be made between Age of Information (AoI) and delay in URLLC slice. The resource limitation and coupling effect at both the inter-slice and the intra-slice level have brought challenges to the resource allocation of vehicular network slice. To this end, this paper models the inter- and intra-slice resource allocation problem as a Stackelberg game, in which the RSU acts as the leader and the two slices act as followers. To minimize the weighted sum of AoI and delay in URLLC slice while ensuring the throughput of eMBB slice, this paper proposes a multi-win Stackelberg game resource allocation (MWRA) algorithm. The proposed algorithm can achieve Stackelberg equilibrium (SE) and the SE point is taken as the optimal resource allocation strategy of inter- and intra-slice. Simulation shows the trade-off of inter- and intra-slice resource allocation, and further reveals the interaction of performance between different slices. Numerical results show that compared with the traditional hard slicing, the proposed algorithm can improve the AoI and delay performance of URLLC slice by about 30% under the premise of ensuring the throughput of eMBB slicing.

Network Resource Allocation Algorithm Using Reinforcement Learning Policy-Based Network in a Smart Grid Scenario

The exponential growth in user numbers has resulted in an overwhelming surge in data that the smart grid must process. To tackle this challenge, edge computing emerges as a vital solution. However, the current heuristic resource scheduling approaches often suffer from resource fragmentation and consequently get stuck in local optimum solutions. This paper introduces a novel network resource allocation method for multi-domain virtual networks with the support of edge computing. The approach entails modeling the edge network as a multi-domain virtual network model and formulating resource constraints specific to the edge computing network. Secondly, a policy network is constructed for reinforcement learning (RL) and an optimal resource allocation strategy is obtained under the premise of ensuring resource requirements. In the experimental section, our algorithm is compared with three other algorithms. The experimental results show that the algorithm has an average increase of 5.30%, 8.85%, 15.47% and 22.67% in long-term average revenue–cost ratio, virtual network request acceptance ratio, long-term average revenue and CPU resource utilization, respectively.