Zhou Gu

This paper studies the reinforcement learning-based distributed secondary frequency control and active power allocation of islanded microgrids under event-triggered mechanism. First, a novel bandwidth-conscious memory-event-triggered mechanism is proposed to reduce communication and computation burdens, which introduces the mean of memory signals to smooth the measured outputs perturbed by disturbances and noises. Meanwhile, a dynamic triggering threshold depending on real-time bandwidth status is constructed to adaptively adjust the data transmission rate according to the changes in bandwidth status and system responses. Second, a new reinforcement learning-based distributed secondary controller using Q-learning algorithm is presented to dynamically regulate the frequency controller gains in response to complex system environments, which helps in achieving better frequency restoration performance. Third, the system stability is analyzed by some linear matrix inequality conditions. Then, simulation outcomes based on load variation and plug-and-play test illustrate that our strategy achieves satisfactory performance in frequency restoration and active power sharing. In addition, some comparison results show the merits of the constructed event-triggered scheme and Q-learning-based distributed secondary frequency controller. Note to Practitioners—This article is concerned with the reinforcement learning-based distributed secondary frequency control and active power allocation of islanded microgrids, addressing challenges induced by limited communication resources, dynamic bandwidth status and complex operation environment. The innovative bandwidth-conscious memory-event-triggered scheme increases the usage efficiency of communication network, and the reinforcement learning-based distributed secondary frequency controller optimizes the frequency restoration performance for islanded microgrids under load changes and random plug and unplug behaviors. The developed strategy is able to handle these realistic problems in practical systems. This strategy can provide technical support for electrical engineers to enhance the stability performance of islanded microgrids.

This study is devoted to event-triggered secure formation control of multi-UAV systems with multiple leaders. The leadership structure comprises one reference leader supplying a macroscopical flight trajectory to the other UAVs, and some formation leaders spanning the convex hull tracked by follower UAVs. Unlike the UAV system relying on a single leader's information, each UAV in this system tracks the convex combination of multiple leaders' states, enhancing the system's resilience to the potential information loss from certain leaders. To mitigate the network overload, a probability-selection-based event-triggered mechanism (PETM) is designed to schedule the network transmissions of sampling signals from a multi-UAV system. The transmission assignment is determined by two steps. To begin with, triggering packets employing the conventional ETMs are relabeled, and then a probability selection scheme is applied to ascertain which one is the actual transmitted packet (ATP). This approach significantly reduces redundant transmission data, particularly when the UAV system is approaching stability, thereby optimizing network resource allocation. Considering deception attacks, the PETM-based tracking control strategy is formulated for the multi-UAV system with multiple leaders by employing the Lyapunov stability theory. Simulation results are presented to manifest the efficacy of the proposed method.

This paper proposes an innovative event-triggered interval type-2 (IT-2) fuzzy consensus control method for agent-based full-vehicle suspension systems (FSSs) using a leader-following approach. By developing a novel IT-2 Takagi-Sugeno (T-S) fuzzy model, the amalgamation of heterogeneous agent-based FSSs into a cohesive homogeneous multi-agent framework becomes feasible, thereby reducing control complexity and effectively dealing with system uncertainty. Within the proposed agent-based architecture, a virtual leader is designed at the core of the agent-based FSS, and the four interconnected quarter-vehicle suspension systems are construed as the following agents. To optimize network bandwidth between the agents, a new event-triggered mechanism (ETM) is established, which is sensitive to significant state changes, particularly when deviations from consensus among the following agents arise abruptly. Sufficient conditions are derived to ensure both the optimal attitude performance and ride comfort of FSSs. Finally, a simulation example of agent-based FSSs is presented to validate the advantages of the proposed approach in optimizing ride comfort and system robustness.

As machine learning technologies progress and are increasingly applied to critical and sensitive fields, the reliability issues of earlier technologies are becoming more evident. For the new generation of machine learning solutions, trustworthiness frequently takes precedence over performance when evaluating their applicability for specific applications. This manuscript introduces the IT2-ENFIS neuro-fuzzy model, a robust and trustworthy single-network solution specifically designed for data regression tasks affected by substantial label noise and outliers. The primary architecture applies interval type-2 fuzzy logic and the Sugeno inference engine. A meta-heuristic gradient-based optimizer (GBO), the Huber loss function, and the Cauchy M-estimator are employed for robust learning. IT2-ENFIS demonstrates superior performance on noise-contaminated datasets and excels in real-world scenarios, with excellent generalization capability and interpretability.