Distributed Resource Allocation Research Articles

Distributed event‐triggered algorithm for resource allocation over directed balanced networks with communication edge attacks

AbstractThis paper focuses on the problem of multi‐agent resource allocation in the context of directed balanced network attacks and event‐triggered communications. Considering the potential communication link failures due to external attacks, this paper proposes a continuous‐time distributed resource allocation algorithm to effectively address these challenges. Additionally, an event‐triggered communication mechanism is implemented, which intelligently determines the timing of information exchanges to enhance system responsiveness while significantly reducing communication resource consumption. Through extensive theoretical analysis, the algorithm is proven to effectively avoid Zeno behaviors and to converge exponentially to the optimal solution. Finally, some simulation experiments further validate the accuracy of the theoretical analysis and the practical effectiveness of the algorithm.

Novel Distributed Downlink Resource Allocation Methods for Heterogeneous Networks

ABSTRACTThis paper proposes novel distributed subchannel and power allocation algorithms for heterogeneous networks. First, we introduce a subchannel allocation algorithm that minimizes the maximum effective interference experienced by users in the network. We analytically prove that the proposed subchannel allocation algorithm minimizes the effective interference in the network. Subsequently, two power control algorithms are presented for the power allocation problem, and their convergence analysis is given. Afterward, the improvement in throughput by utilizing the proposed power control algorithm is shown by simulations. Finally, the proposed subchannel and power allocation algorithms are combined to form a joint resource allocation method, which is shown to outperform existing distributed resource allocation methods in the literature.

A Master–Slave Game-Based Strategy for Trading and Allocation of Virtual Power Plants in the Electricity Spot Market

With the transformation of the energy structure, the integration of numerous small-scale, widely distributed renewable energy sources into the power grid has introduced operational safety challenges. To enhance the operational competitiveness, the virtual power plant (VPP) has emerged to aggregate and manage these distributed energy resources (DERs). However, current research on the VPP’s frequency modulation performance and bidding strategy remains insufficient in the joint market of electrical energy and frequency modulation (FM) ancillary services, with inadequate coordination of internally distributed resources. To fully leverage the flexibility of VPPs and incentivize their participation in electricity market operations, this paper investigates game-based bidding strategies and internal distributed resources allocation methods for VPPs in the joint market for electrical energy and frequency ancillary services. Firstly, the regulatory performance indicators of VPPs participating in the joint market and develops the corresponding market-clearing model. Secondly, to address the competition among distributed resources within VPPs, a master-slave game approach is innovatively employed to optimize the VPP’s trading strategies. This method ensures the rational allocation of electricity consumption among distributed energy resources within the VPP and derives the optimized bidding prices and quantities for both the VPP and its internal members. Finally, the case study shows that the proposed trading strategy provides effective bidding strategies for distributed energy resources participating in the joint market for energy and frequency regulation ancillary services. It enhances the regulatory performance of VPPs in the energy-frequency regulation market, ensures the profitability of distributed energy resources, and contributes to the economically stable operation of the market.

Reinforcement Learning-Based Resource Allocation Scheme of NR-V2X Sidelink for Joint Communication and Sensing.

Joint communication and sensing (JCS) is becoming an important trend in 6G, owing to its efficient utilization of spectrums and hardware resources. Utilizing echoes of the same signal can achieve the object location sensing function, in addition to the V2X communication function. There is application potential for JCS systems in the fields of ADAS and unmanned autos. Currently, the NR-V2X sidelink has been standardized by 3GPP to support low-latency high-reliability direct communication. In order to combine the benefits of both direct communication and JCS, it is promising to extend existing NR-V2X sidelink communication toward sidelink JCS. However, conflicting performance requirements arise between radar sensing accuracy and communication reliability with the limited sidelink spectrum. In order to overcome the challenges in the distributed resource allocation of sidelink JCS with a full-duplex, this paper has proposed a novel consecutive-collision mitigation semi-persistent scheduling (CCM-SPS) scheme, including the collision detection and Q-learning training stages to suppress collision probabilities. Theoretical performance analyses on Cramér-Rao Lower Bounds (CRLBs) have been made for the sensing of sidelink JCS. Key performance metrics such as CRLB, PRR and UD have been evaluated. Simulation results show the superior performance of CCM-SPS compared to similar solutions, with promising application prospects.

Exponentially Convergent Algorithms Design for Distributed Resource Allocation under Non-strongly Convex Condition: From Continuous-time to Event-triggered Communication

Exponentially Convergent Algorithms Design for Distributed Resource Allocation under Non-strongly Convex Condition: From Continuous-time to Event-triggered Communication

Safe Pricing Mechanisms for Distributed Resource Allocation With Bandit Feedback

Safe Pricing Mechanisms for Distributed Resource Allocation With Bandit Feedback

An online dual consensus algorithm for distributed resource allocation over networks

We address the problem of online resource allocation in a distributed environment where requests arrive dynamically over time at different agents in the network. As each request arrives, the receiving agent must make an immediate decision that incurs a cost and consumes a certain amount of resources. The requests are drawn independently from unknown distributions that are different for each agent. First, we present an Online Consensus Alternating Direction Method of Multipliers (OC-ADMM) algorithm for the dual counterpart of the online distributed resource allocation problem, focusing on the dual variables. Then, we propose an Online Dual Consensus ADMM (ODC-ADMM) algorithm for the primal problem to derive the primal variables from the dual update process in the OC-ADMM algorithm. The ODC-ADMM algorithm exhibits sublinear growth in both regret and expected constraint violation with respect to the time horizon. Furthermore, extensive numerical results on both synthetic and real-world data confirm its effectiveness.

Distributed Resource Allocation Over Multiple Interacting Coalitions: A Game-Theoretic Approach

Distributed Resource Allocation Over Multiple Interacting Coalitions: A Game-Theoretic Approach

The Shared Experience Actor–Critic (SEAC) Approach for Allocating Radio Resources and Mitigating Resource Collisions in 5G-NR-V2X Mode 2 Under Aperiodic Traffic Conditions

5G New Radio (NR)-V2X, standardized by 3GPP Release 16, includes a distributed resource allocation Mode, known as Mode 2, that allows vehicles to autonomously select transmission resources using either sensing-based semi-persistent scheduling (SB-SPS) or dynamic scheduling (DS). In unmanaged 5G-NR-V2X scenarios, SB-SPS loses effectiveness with aperiodic and variable data. DS, while better for aperiodic traffic, faces challenges due to random selection, particularly in high traffic density scenarios, leading to increased collisions. To address these limitations, this study models the Cellular V2X network as a decentralized multi-agent networked Markov decision process (MDP), where each vehicle agent uses the Shared Experience Actor–Critic (SEAC) technique to optimize performance. The superiority of SEAC over SB-SPS and DS is demonstrated through simulations, showing that the SEAC with an N-step approach achieves an average improvement of approximately 18–20% in enhancing reliability, reducing collisions, and improving resource utilization under high vehicular density scenarios with aperiodic traffic patterns.

Optimization of distributed energy resources planning and battery energy storage management via large-scale multi-objective evolutionary algorithm

Optimization of distributed energy resources planning and battery energy storage management via large-scale multi-objective evolutionary algorithm

Adaptive Neurodynamic Approach to Multiple Constrained Distributed Resource Allocation.

In this article, an adaptive neurodynamic approach over multiagent systems is designed to solve nonsmooth distributed resource allocation problems (DRAPs) with affine-coupled equality constraints, coupled inequality constraints, and private set constraints. It is to say, agents focus on tracking the optimal allocation to minimize the team cost under more general constraints. Among the considered constraints, multiple coupled constraints are dealt with by introducing auxiliary variables to make Lagrange multipliers reach consensus. Furthermore, aiming to address private set constraints, an adaptive controller is proposed with the aid of the penalty method, thus avoiding the disclosure of global information. Through using the Lyapunov stability theory, the convergence of this neurodynamic approach is analyzed. In addition, to reduce the communication burden of systems, the proposed neurodynamic approach is improved by introducing an event-triggered mechanism. In this case, the convergence property is also explored, and the Zeno phenomenon is excluded. Finally, a numerical example and a simplified problem on a virtual 5G system are implemented to demonstrate the effectiveness of the proposed neurodynamic approaches.

Joint spectrum and power allocation scheme based on value decomposition networks in D2D communication networks

Device-to-device (D2D) communications allow short-range communication devices to multiplex cellular-licensed spectrum to directly establish local connections for ultra-high number of terminal connections and greater system throughput. However, spectrum sharing also brings serious interference to the network. Therefore, a reliable and efficient resource allocation strategy is important to mitigate the interference and improve the system spectral efficiency. In this paper, we investigated spectrum access and power allocation in D2D communications underlay cellular networks based on deep reinforcement learning with the aim of finding a feasible resource allocation strategy to maximize data rate and system fairness. We proposed a value decomposition network-based resource allocation scheme for D2D communication networks. Our proposed scheme avoids frequent information exchanges among D2D users by centralized training, while allowing D2D users to make distributed joint resource allocation decisions. Simulation results show that the proposed scheme has stable convergence and good scalability, and can effectively improve the system capacity.

Distributed Resources Allocation Method for Space-Ground Integrated Mobile Communication System.

This paper presents an innovative approach towards space-ground integrated communication systems by combining terrestrial cellular networks, UAV networks, and satellite networks, leveraging advanced slicing technology. The proposed architecture addresses the challenges posed by future user surges and aims to reduce network overhead effectively. Central to our approach is the introduction of a marginal mobile station (MS)-assisted network resource allocation decision architecture. Building upon this foundation, we introduce the DP-DQN model, an enhanced decision-making algorithm tailored for MSs in dynamic network environments. Furthermore, this study introduces a feedback mechanism to ensure the accuracy and adaptability of the marginalization model over time. Through extensive simulations and experimental validations, our DP-DQN-based edge decision method demonstrates substantial potential in alleviating core network overhead while improving success access ratios compared to conventional methods.

Meta Federated Reinforcement Learning for Distributed Resource Allocation

Meta Federated Reinforcement Learning for Distributed Resource Allocation

A Systematic Literature Review in Distributed Resource Allocation for C-V2X

A Systematic Literature Review in Distributed Resource Allocation for C-V2X

Resilient algorithm for distributed resource allocation under false data injection attacks

AbstractFor a first‐order nonlinear multi‐agent system who is subject to false data injection (FDI) attacks on agents' actuators and sensors, agents execute a distributed resource allocation algorithm according to the compromised control inputs and interactive information such that the multi‐agent system is unstable and agents' decisions deviate from the optimal resource allocation. At first, we analyze the robustness of the distributed resource allocation algorithm under the FDI attacks. Then, a resilient distributed algorithm is proposed to solve the distributed resource allocation problem by resisting the adverse effect of the attacks. In detail, the unknown nonlinear term and the false data injected in agents are considered as extended states that can be estimated by extended state observers. The estimation is used in the feedback control to suppress the effect of the FDI attacks. As a result, the designed resilient algorithm ensures that agents' decisions converge to the optimal allocation without requiring any information about the nature of the attacks. An example is given to illustrate the results.

Framework for Federated Learning and Edge Deployment of Real-Time Reinforcement Learning Decision Engine on Software Defined Radio

Machine learning promises to empower dynamic resource allocation requirements of Next Generation (NextG) wireless networks including 6G and tactical networks. Recently, we have seen the impact machine learning can make on various aspects of wireless networks. Yet, in most cases, the progress has been limited to simulations and/or relies on large processing units to run the decision engines as opposed to deploying it on the radio at the edge. While relying on simulations for rapid and efficient training of deep reinforcement learning (DRL) may be necessary, it is key to mitigate the sim-real gap while trying to improve the generalization capability. To mitigate these challenges, we developed the Marconi-Rosenblatt Framework for Intelligent Networks (MR-iNet Gym), an open-source architecture designed for accelerating the deployment of novel DRL for NextG wireless networks. To demonstrate its impact, we tackled the problem of distributed frequency and power allocation while emphasizing the generalization capability of DRL decision engine. The end-to-end solution was implemented on the GPU-embedded software-defined radio and validated using over-the-air evaluation. To the best of our knowledge, these were the first instances that established the feasibility of deploying DRL for optimized distributed resource allocation for next-generation of GPU-embedded radios.

A collective neurodynamic approach to distributed resource allocation with event-triggered communication

To solve a distributed optimal resource allocation problem, a collective neurodynamic approach based on recurrent neural networks (RNNs) is proposed in this paper. Multiple RNNs cooperatively solve a global constrained optimization problem in which the objective function is a total of local non-smooth convex functions and is subject to local convex sets and a global equality constraint. Different from the projection dynamics to deal with local convex sets in the existing work, an internal dynamics with projection output is designed in the algorithm to relax the Slater’s condition satisfied by the optimal solution. To overcome continuous-time communication in a group of RNNs, an aperiodic communication scheme, called the event-triggered scheme, is presented to alleviate communication burden. It is analyzed that the convergence of the designed collective neurodynamic approach based on the event-triggered communication does not rely on global information. Furthermore, it is proved the freeness of the Zeno behavior in the event-triggered scheme. Two examples are presented to illustrate the obtained results

Federated learning-based trajectory prediction for dynamic resource allocation in moving small cell networks

Federated learning-based trajectory prediction for dynamic resource allocation in moving small cell networks

Distributed optimization game algorithm to improve energy efficiency for multi-radio multi-channel wireless sensor network

To send and receive data simultaneously, reduce network interference, and effectively improve energy efficiency, this paper analyzes the network characteristics of Multi-Radio Multi-Channel Wireless Sensor Network and optimizes the power and channel of each radio frequency interface. Based on the novel energy efficiency model and energy consumption efficiency model, this paper establishes a distributed optimization game model using Game Theory to maximize network energy efficiency, minimize energy consumption, and ensure network connectivity. Based on the game model, an efficient distributed resource allocation game algorithm is designed, in which a joint power control and channel allocation can quickly converge to Nash Equilibrium with low complexity. At the same time, the simulation results show that the distributed resource allocation game algorithm can effectively improve the energy efficiency, reduce network interference and bit error rate to ensure the successful data transmission.