Multiagent Deep Reinforcement Learning for Optimal Resource Allocation in AoI-Aware Energy-Efficient Platoon-Based C-V2X Networks

This paper investigates the problem of age of information (AoI) aware radio resource management for a platooning system. Multiple autonomous platoons exploit the cellular wireless vehicle-to-everything (C-V2X) communication technology to disseminate the cooperative awareness messages (CAMs) to their followers while ensuring timely delivery of safety-critical messages to the Road-Side Unit (RSU). To lower the computational load at the RSU and cope with the challenges of dynamic channel conditions, we exploit a distributed resource allocation framework based on multi-agent reinforcement learning (MARL), where each platoon leader (PL) acts as an agent and interacts with the environment to learn its optimal policy. Motivated by the existing literature in RL, we propose two novel MARL frameworks based on the multi-agent deep deterministic policy gradient (MADDPG), named Modified MADDPG, and Modified MADDPG with task decomposition. Both algorithms train two critics with the following goals: A global critic which estimates the global expected reward and motivates the agents toward a cooperating behavior and an exclusive local critic for each agent that estimates the local individual reward. Furthermore, based on the tasks each agent has to accomplish, in the second algorithm, the holistic individual reward of each agent is decomposed into multiple sub-reward functions where task-wise value functions are learned separately. Numerical results indicate our proposed algorithms' effectiveness compared with other contemporary RL frameworks, e.g., federated reinforcement learning (FRL) in terms of AoI performance and CAM message transmission probability.

A novel multi-objective optimization based multi-agent deep reinforcement learning approach for microgrid resources planning

PASCAL: PopulAtion-Specific Curriculum-based MADRL for collision-free flocking with large-scale fixed-wing UAV swarms

In the future, mixed traffic flow will include two types of vehicles: connected autonomous vehicles (CAVs) and human-driven vehicles (HDVs). CAVs emerge as new solutions to disrupt the traditional transportation system. This new solution shares real-time data with each other and the roadside units (RSU) for network management. Reinforcement learning (RL) is a promising approach for traffic signal management in complex urban areas by leveraging information gathered from CAVs. In particular, coordinating signal management at many intersections is a critical challenge in multi-agent reinforcement learning (MARL). According to this vision, we propose an approach that combines an actor–critic network–based multi-agent deep deterministic policy gradient (MADDPG) model and a rerouting technique (RT) to increase traffic performance in vehicular networks. This algorithm overcomes the inherent non-stationary of Q-learning and the high variance of policy gradient (PG) algorithms. Based on centralized learning with decentralized execution, the MADDPG model employs one actor and one critic for each agent. The actor network uses local information to execute actions, while the critic network is trained with extra information, including the states and actions of other agents. Through a centralized learning process, agents can coordinate with each other, diminishing the influence of an unstable environment. Unlike previous studies, we not only manage traffic light systems but also consider the effect of platooning vehicles on increasing throughput. Experimental results show that our model outperforms other models in terms of traffic performance in different scenarios.

Aerial base stations (AeBSs), as crucial components of air-ground integrated networks, are widely employed in cloud computing, disaster relief, and various applications. How to quickly and efficiently deploy multi-AeBSs for higher capacity gain has become a key research issue. In this paper, we address the 3D deployment optimization problem of multi-AeBSs with the objective of maximizing system capacity. To overcome communication overhead and privacy challenges in multi-agent deep reinforcement learning (MADRL), we propose a federated deep deterministic policy gradient (Fed-DDPG) algorithm for the multi-AeBS deployment decision. Specifically, a high-altitude platform (HAP)-assisted multi-AeBS deployment architecture is designed, in which low-altitude AeBS act as the local nodes to train its own deployment decision model, while the HAP acts as the global node to aggregate the weights of local models. In this architecture, AeBSs do not exchange raw data, addressing data privacy concerns and reducing communication overhead. Simulation results show that the proposed algorithm outperforms fully distributed MADRL algorithms and closely approximates the performance of multi-agent deep deterministic policy gradient (MADDPG), which requires global information during training, but with less training time.

The large-scale integration of distributed renewable generation (DRG) reduces carbon emissions in power systems, but its intermittency and volatility introduce new challenges for voltage and frequency control. This paper proposes a multi-time-scale reactive power optimization approach that incorporates demand-side response. Firstly, based on the interaction characteristics between sources and loads in the distribution network, a demand-side response mechanism using dynamic time-of-use pricing is designed to explore the source-load matching and tracking capabilities. Secondly, a multi-scale day-ahead reactive power optimization control model is constructed, which comprehensively considers the dynamic response mechanism on the demand side. The objective function of this model aims to minimize network losses and voltage deviations while accounting for the day-ahead price response characteristics of loads. The multi-scale reactive power optimization model is then transformed into a Markov decision process and solved via a locally-observed multi-agent deep deterministic policy gradient algorithm to obtain real-time intraday reactive power and voltage control strategies. Finally, the effectiveness of the proposed method is verified through experiments on the IEEE 33-bus system and an actual power grid. Experimental results show that this method can effectively coordinate various reactive power compensation devices and flexible resources, and improve the efficiency and real-time performance of reactive power and voltage control.

A multi-agent deep reinforcement learning (MADRL) is a promising approach to challenging problems in wireless environments involving multiple decision-makers (or actors) with high-dimensional continuous action space. In this paper, we present a MADRL-based approach that can jointly optimize precoders to achieve the outer-boundary, called pareto-boundary, of the achievable rate region for a multiple-input single-output (MISO) interference channel (IFC). In order to address two main challenges, namely, multiple actors (or agents) with partial observability and multi-dimensional continuous action space in MISO IFC setup, we adopt a multi-agent deep deterministic policy gradient (MA-DDPG) framework in which decentralized actors with partial observability can learn a multi-dimensional continuous policy in a centralized manner with the aid of shared critic with global information. Meanwhile, we will also address a phase ambiguity issue with the conventional complex baseband representation of signals widely used in radio communications. In order to mitigate the impact of phase ambiguity on training performance, we propose a training method, called phase ambiguity elimination (PAE), that leads to faster learning and better performance of MA-DDPG in wireless communication systems. The simulation results exhibit that MA-DDPG is capable of learning a near-optimal precoding strategy in a MISO IFC environment.

In mixed-mode operation, arrivals and departures are allowed to land and depart on the same runway. An appropriate strategy from air traffic controllers for arrivals and departures sequencing would boost the runway through-put significantly. On the other hand, safety is still the most crucial feature in the operation. Therefore, to assist air traffic controllers to make decisions on departures and arrivals with efficient utilization of runway capacity and safe operations, this paper proposed a Multi-agent Deep Reinforcement Learning approach using Multi-agent Deep Deterministic Policy Gradient to train two agents simultaneously: departure agent, and arrival agent. The departure agent makes departure slotting decisions for departures while the arrival agent determines the time delay or spacing decision on the arrival stream. A data-driven simulation environment is developed using Singapore Changi Airport data to support the learning process. Besides, a random sampling technique is also introduced to reduce redundant samples and increase off-policy sample efficiency. Moreover, the impact of different reward functions on runway throughput is also investigated and two specific models, e.g., ‘arrival priority’ and ‘departure priority’, are selected for further analysis in this study. As the result, by comparing the trained models with the ad-hoc model, the proposed approach increases the runway throughput significantly, with the highest 12.8% additional departure releases and overall 5.3% additional departure releases in identical environments while safety separations are maintained.

One of the toughest challenges in the multi-agent deep reinforcement learning (MADRL) is that when the opponents' policies change rapidly, the collaborative agents can't learn well to respond to the opponents' policies effectively. This may lead to a local optimum w.r.t. the learned policy of the collaborative agents may be only locally optimal to the opponents' current policies. To address this problem, we propose a novel algorithm termed Friend-or-Foe Deep Deterministic Policy Gradient (FD2PG), in which the cooperative agents can be trained more robust and have stronger cooperation ability in continuous action space. These collaborative agents can generalize easily and respond correctly, even if their opponents' policies alter. Inspired by the classic Friend-or-Foe Q-learning algorithm (FFQ), we introduce the idea of minimizing the foes and maximizing the friends into the centralized training distributed execution framework, multi-agent deep deterministic policy gradient algorithm (MADDPG), to enhance collaborative agents' robustness and cooperativity. Besides, we introduce a Minimax Multi-Agent Learning (MMAL) method to explore two special equilibriums (the adversarial equilibrium and the coordination equilibrium), which can guarantee the convergence of FD2PG and improve optimization. Extensive fine-grained experiments, including four representative scenario experiments and two scale-performance correlation experiments, were conducted to demonstrate the superior performance of FD2PG comparing with existing baselines.

An optimal solutions-guided deep reinforcement learning approach for online energy storage control

To address the challenges of real-time decision-making and resource optimization in multi-agent cooperative interception tasks within dynamic environments, this paper proposes a hierarchical framework for reinforcement learning-based interception algorithm (HFRL-IA). By constructing a hierarchical Markov decision process (MDP) model based on dynamic game equilibrium theory, the complex interception task is decomposed into two hierarchically optimized stages: dynamic task allocation and distributed path planning. At the high level, a sequence-to-sequence reinforcement learning approach is employed to achieve dynamic bipartite graph matching, leveraging a graph neural network encoder–decoder architecture to handle dynamically expanding threat targets. At the low level, an improved prioritized experience replay multi-agent deep deterministic policy gradient algorithm (PER-MADDPG) is designed, integrating curriculum learning and prioritized experience replay mechanisms to effectively enhance the interception success rate against complex maneuvering targets. Extensive simulations in diverse scenarios and comparisons with conventional task assignment strategies demonstrate the superiority of the proposed algorithm. Taking a typical scenario of 10 agents intercepting as an example, the HFRL-IA algorithm achieves a 22.51% increase in training rewards compared to the traditional end-to-end MADDPG algorithm, and the interception success rate is improved by 26.37%. This study provides a new methodological framework for distributed cooperative decision-making in dynamic adversarial environments, with significant application potential in areas such as maritime multi-agent security defense and marine environment monitoring.

Multi-agent deep reinforcement learning (MADRL) has been used for disaster rescue and other robotic applications. In most MADRL cases, agents are trained only to deal with specific tasks, so once there are unpredictable changes in target tasks, the earlier trained-models might no longer work, and agents have to get trained again from scratch in limited time, which means traditional MADRL is unsuited to unpredictable post-disaster environments. In order to promote the scalability and flexibility of the multi-agent system, meta-learning, which has achieved few shot learning successfully in supervised deep learning field, could reuse the earlier models as the prior knowledge to guide and speed up the new task learning process. In this work, we propose a framework to apply meta learning methods to multi-agent deep deterministic policy gradient (MADDPG), and achieve efficient adaption to new tasks with less time and fewer samples. Some common experiences in the previous tasks learning will be refined as the meta knowledge. Once the tasks get changed with new scenarios, agents will get retrained with good initial network parameters based on this meta knowledge. Although the new scenarios might be different from the previous scenarios, agents could quickly adjust their policy and get better performance within only few episodes. In two experiments, our method performs better learning efficiency than others, getting higher rewards in the first several episodes of new tasks learning.

Multi-agent deep reinforcement learning based demand response for discrete manufacturing systems energy management

VANETs relies on the repetitive exchange of Cooperative Awareness Messages (CAMs) among vehicle's On­Board Units (OBUs) and vehicles to roadside units (RSUs), thus making CAMs the backbone of the network. This exchange may lead to degradation of network performance caused by the ample amount of data exchange between the vehicles. Therefore, a trade­off between CAM broadcast within the network and optimum utilization of network resources is required. Most of the existing work focuses on retransmission of beacon messages supporting unicast 802.11 models which are not directly suited for the VANET scenario. To deal with this problem, the paper presents a model for non-repetitive single-hop broadcast of CAM within the network, thus supporting IEEE802.11p. For non-repetitive broadcast of CAM, the concept of preemption of messages is introduced in the model. Simulation is carried out using MATLAB 15's Simiilink. The model performance is evaluated by extracting its statistical properties in terms of Channel Utilization, CAM's Average Waiting Time within the queue and Average Queue Length. To validate our model, the simulation is implemented on real world data acquired from wheel speed for all wheels for the duration of a test drive.

The Dual Active Bridge converter (DABC), known for its bidirectional power transfer capability and high efficiency, plays a crucial role in various applications, particularly in electric vehicles (EVs), where it facilitates energy storage, battery charging, and grid integration. The Dual Active Bridge Converter (DABC), when paired with a high-performance CLLC filter, is well-regarded for its ability to transfer power bidirectionally with high efficiency, making it valuable across a range of energy applications. While these features make the DABC highly efficient, they also complicate controller design due to nonlinear behavior, fast switching, and sensitivity to component variations. We have used a Fractional-order PID (FOPID) controller to benefit from the simple structure of classical PID controllers with lower complexity and improved flexibility because of additional filtering gains adopted in this method. However, for a FOPID controller to operate effectively under real-time conditions, its parameters must adapt continuously to changes in the system. To achieve this adaptability, a Multi-Agent Reinforcement Learning (MARL) approach is adopted, where each gain of the controller is tuned individually using the Deep Deterministic Policy Gradient (DDPG) algorithm. This structure enhances the controller’s ability to respond to external disturbances with greater robustness and adaptability. Meanwhile, finding the best initial gains in the RL structure can decrease the overall efficiency and tracking performance of the controller. To overcome this issue, Grey Wolf Optimization (GWO) algorithm is proposed to identify the most suitable initial gains for each agent, providing faster adaptation and consistent performance during the training process. The complete approach is tested using a Hardware-in-the-Loop (HIL) platform, where results confirm accurate voltage control and resilient dynamic behavior under practical conditions. In addition, the controller’s performance was validated under a battery management scenario where the DAB converter interacts with a nonlinear lithium-ion battery. The controller successfully regulated the State of Charge (SOC) through automated charging and discharging transitions, demonstrating its real-time adaptability for BMS-integrated EV systems. Consequently, the proposed MARL-FOPID controller reported better disturbance-rejection performance in different working cases compared to other conventional methods.