Heart disease is a leading global cause of death, while federated learning (FL) is an effective way to predict it. Due to patient privacy concerns and the centralized nature of current FL approaches, collaborative research in heart disease prediction (HDP) faces significant hurdles in computational health systems. This article introduces a distributed online aggregation method within fully decentralized federated learning (DFL), named DeFedHDP, to address these privacy challenges and improve the model of HDP. Moreover, the differential privacy (DP) mechanism is applied to the aggregation strategy of DeFedHDP to protect the privacy of the patients. The data holder communicates directly with neighbors in a series of time-varying directed graphs without the involvement of a central server. Furthermore, each participant is both a trainer of the local model and a collaborator of the other participants’ models. The data does not leave the local device, only the model parameters are exchanged and integrated, and this decentralized approach can further improve the level of privacy protection. In addition, to cope with model gradient disappearance and gradient explosion, the one-point bandit feedback (OPBF) strategy is utilized to estimate the true gradient values. Experiments on a public medical dataset show that the effectiveness of DeFedHDP is close to the centralized FedAVG algorithm for client-server architectures in terms of accuracy and speed.

For islanded microgrids, traditional droop-based control leads to frequency deviation and low economic efficiency. To solve this problem, a novel event-triggered optimal active power control strategy, which achieves frequency regulation and economic operation in a fully distributed way, is proposed in this paper. Frequency deviations are monitored and used to trigger the load estimation algorithm, which can track the changes of power demand. Based on the estimated demand values, a distributed economic dispatch algorithm, which only requires that the communication topology satisfies the jointly connected condition, is proposed to calculate the optimal generation references for the generators. The economic dispatch algorithm has the finite-time convergence property, which is rigorously proved by Lyapunov theory, LaSalle’s invariance principle and homogeneous property. Based on the optimal generation references, the parameters of droop controller are reset in real time, which makes microgrid achieve frequency restoration and economic operation simultaneously. Finally, several case studies are performed to illustrate the effectiveness of the proposed control strategy.

By combining the Newton-Raphson method, the graph discovery algorithm, and the finite-time consensus algorithm, a novel iterative algorithm is proposed in this paper to solve the economic dispatch problem of modern cyber-physical power systems. Fully distributed implementation and finite-time convergence properties distinguish our algorithm from the existing iterative algorithms. Several numerical examples are applied to illustrate our design procedure and validate our proposed algorithm.

The paper investigates the distributed convex optimisation problem of multi-agent systems over strongly connected and balanced digraph with time delay. To reduce the traffic among agents and the control inputs' update frequency, a sample-based distributed event-triggered zero-gradient-sum optimisation algorithm has been proposed. A sufficient stability condition with respect to the related parameters and time delay is derived via the Lyapunov function approach. Moreover, it is proved that the states of agents asymptotically converge to the global optimal point. Since the sampling control is adopted, Zeno behaviour can be naturally excluded. The results of the numerical simulation illustrate the effectiveness of the proposed algorithm.

This paper investigates a class of privacy-enhancing decentralized federated learning (DFL) algorithms. The majority of current DFL algorithms rely on the premise that obtaining gradient information for the cost function is efficient and that the weight matrix of the communication network adheres to either doubly stochastic or column stochastic. However, in many cases, obtaining gradient information may be challenging, and the requirement for the weight matrix is also stringent. To overcome these challenges, a decentralized online bandit federated learning algorithm with differential privacy (DP) is proposed. By employing the one-point bandit feedback (OPBF), the algorithm can estimate the gradient without the requirement of complex computation of gradient information. Moreover, the proposed algorithm models the communication network as an unbalanced directed network with a row stochastic weight matrix, eliminating the stringent requirements on the network. Our algorithm accomplishes both sublinear convergence and $\varepsilon$ -DP through rigorous theoretical derivations. Finally, the effectiveness of our algorithm is validated through simulation experiments on multiple mainstream datasets with various data scenarios.

This paper proposes an event-triggered adaptive control algorithm with prescribed performance for quadrotor unmanned aerial vehicles (UAVs). The dynamic uncertainty and unknown external interference of the system are compensated by the property of approximation in a radial basis function (RBF) neural network. Based on this, introduce a performance constraint function to ensure that the trajectory tracking error of quadrotor UAV converges to a preset area, thereby guaranteeing transient and steady-state performance. In addition, design an event-triggered adaptive controller with the combination of the event-triggered mechanism, reducing the controller’s update frequency. Simulation results demonstrate that this algorithm exhibits strong anti-interference properties and effectively resolves the flight control problem of quadrotor UAV.