Modeling accuracy of DC-DC converters may deviate largely in the presence of different variation levels of constant power loads (CPLs), hence is well acknowledged as a main hurdle for the design of advanced model-driven control strategies in the literature. Aiming to enhance the bus voltage regulation performance of DC-DC buck converters, a model-free deep reinforcement learning (DRL) control strategy is proposed in this brief. Firstly, a Markov Decision Process (MDP) model and a deep Q network (DQN) algorithm are utilized for the stabilization issue of the converter. Secondly, through a subgoal reward/penalty mechanism, the control objective and prescribed performance of the system are therefore guaranteed. Moreover, a specified action space is designed to match the switch speed of the switching element. As a distinguishable feature, the settling time under the proposed control scheme is significantly reduced in the occurrence of disturbance, resulting from the fast adaption ability of DRL. The simulation comparison results in reference to PI and fuzzy PI controllers demonstrate the efficacy and superiorities under large signal perturbation conditions.

The reinforcement learning (RL) control approach with application to power electronics systems has become an emerging topic, while the sim-to-real issue remains a challenging problem as very few results can be referred to in the literature. Indeed, due to the inevitable mismatch between simulation models and real-life systems, offline-trained RL control strategies may sustain unexpected hurdles in practical implementation during the transfer procedure. In this article, a transfer methodology via a delicately designed duty ratio mapping is proposed for a dc–dc buck converter. Then, a detailed sim-to-real process is presented to enable the implementation of a model-free deep reinforcement learning controller. As the main contribution of this article, the proposed methodology is able to endow the control system to achieve: 1) voltage regulation and 2) adaptability and optimization abilities in the presence of uncertain circuit parameters and various working conditions. The feasibility and efficacy of the proposed methodology are demonstrated by comparative experimental studies.

In high-power electronic industrial systems, constant power loads (CPLs) can affect the system performance or even cause instability due to its inherent negative impedance characteristics. Regarding this control issue, model predictive control (MPC) methods are generally applied into DC/DC converters feeding CPLs, aiming to achieve satisfactory control performance. However, they are mostly based on a fixed horizon design, whose optimal performance may be far from the desired one due to the change of operating conditions, e.g., different variation levels of CPLs. In this context, a novel generalized dynamic predictive control (GDPC) strategy employing a simple self-tuning horizon mechanism is proposed for the first time, allowing the controller to adaptively optimize the system transient-time performance even under largely-varied operating conditions. Firstly, a disturbance observer is utilized to reconstruct the lumped disturbances within the system, which are subsequently brought into the control design through feedforward compensation loops. Secondly, an adaptive horizon is introduced into the generalized predictive control (GPC) design and rigorous stability analysis based on Lyapunov theorem is given. The effectiveness and performance improvement of the proposed regulation methodology is verified by both simulation and experimental studies in reference to the double-loop PI control and a benchmark GPC algorithm.

In the primary control layer of DC microgrids, engineers usually select the control gains with a robust design strategy (i.e., the worst case study), aiming to ensure stable operation of the system with the presence of large-signal disturbances. However it will inevitably result in degraded nominal control performance. To this end, a compromise between dynamic performance and system stability appears and how to reconcile it is a challenging task. In this context, we propose a novel adaptive control strategy aiming to pursue a balance between the above two properties. Firstly, a higher-order sliding mode observation technique is employed to estimate the disturbance variations within a finite time. Secondly, an adaptive gain regulation mechanism is designed in an easy-implementable fashion. Finally, by combing the feedforward decoupling procedure and the adaptive feedback scheme, the control performance of the DC microgrids can be adjusted adaptively in different working conditions. Through the above design produces, the proposed controller will bring the following new features: 1) The robustness redundancy of existing robust control strategies can be essentially avoided. 2) The balance between dynamic performance and system stability is achieved. 3) The self-tuning regulation facilitates the process of gain selection and the concise adaptive structure can be easily utilized in practical implementation. The efficacy of the proposed controller is verified by both simulation and experiment results.

For the DC/DC boost converter feeding constant power loads (CPLs), improving its dynamic characteristics and guaranteeing the output voltage stability have aroused much attention from the power electronics society in recent years. This paper proposes an optimal output regulation strategy by fusing a robust stabilization strategy with deep reinforcement learning (DRL). Firstly, by employing the high-order sliding mode observer (HOSMO) to estimate the uncertainties of the system, then we are able to realize a fast performance recovery ability via feedforward compensation loops. Secondly, the deep deterministic policy gradient (DDPG) is trained to adaptively adjust the control coefficients. Thirdly, the stability analysis is given to guarantee the large-signal stability of the control system. In order to evaluate the strength and effectiveness of the proposed adaptive method, experiments are conducted in this paper on a DC microgrid platform.

The negative impedance characteristic of constant power loads (CPLs) can cause DC bus voltage fluctuations or even DC microgrid instability. In this paper, a nonlinear synergetic control method is used to guarantee the DC bus voltage stability of DC microgrids with CPLs. First, to regulate the capacitor voltage to its desired value, a macro-variable is defined using the synergetic control theory. Then, due to the sensitivity of the system to the parameters of the input voltage, the CPL, and the resistive load, and also to enhance the overall system performance, an improved macro-variable is introduced by adding an integral action. Finally, the finite-time synergetic controller is proposed to provide the finite-time convergence for the DC microgrid voltage and also to avoid the chattering phenomenon. The simulation and experimental results demonstrate the acceptable performance of the proposed controller.