The non-linearities and un-modeled dynamics inevitably degrade the quality and reliability of power conversion, and as a result, pose big challenges on higher-performance voltage stabilization of dc/dc buck converters. The stability of such power electronic equipment is further threatened when feeding the non-ideal constant power loads (CPLs) because of the induced negative impedance specifications. In response to these challenges, the advanced regulatory and technological mechanisms associated with the converters require to be developed to efficiently implement these interface systems in the Microgrid configuration. This paper addresses an intelligent proportional-integral (iPI) based on sliding mode observer (SMO) to mitigate the destructive impedance instabilities of non-ideal CPLs with time-varying nature in the ultra-local model (ULM) sense. In particular, in the current work, an auxiliary deep deterministic policy gradient (DDPG) controller is adaptively developed to decrease the SMO estimation error and further ameliorate the dynamic characteristics of dc/dc buck converters. The design of the DDPG is realized in two parts: i) an actor-network which generates the policy commands, while ii) a critic-network evaluates the quality of the policy command generated by the actor.

The high-penetration of distributed generation technologies in the form of MicroGrids (MGs), in recent years, has increased the risk of frequency instability since their energy is supplied by renewable energy resources (RESs) with uncertain nature. Under such circumstances, providing an MG model with an efficient load frequency control (LFC) has a fundamental role in restoring the stability of the unstructured power system. In this study, a hybrid power system with the application of the Tidal Power Unit (TPU) and Vehicle-to-Grid (V2G) is effectively planed as an isolated MG. A new fractional gradient descent (FGD) based on a single-input interval type-2 fuzzy logic controller (SIT2-FLC) is suggested as the main LFC controller, where the footprint of uncertainty (FOU) coefficient of the SIT2-FLC is specifically adjusted to enhance the LFC performance. Additionally, a deep deterministic policy gradient (DDPG) with the actor-critic framework is considered to generate the supplementary control action, which is useful for the frequency stabilization by adapting to the randomness of load disturbances and RESs. Lastly, a model-in-the-loop (MiL) simulation is conducted to appraise the feasibility and applicability of the suggested design method from a systemic perspective.

The recent advances in power plants and energy resources have extended the applications of buck-boost converters in the context of DC micro-grids (MGs). However, the implementation of such interface systems in the MG applications is seriously threatened with instability issues imposed by the constant power loads (CPLs). The objective is that without the accurate modeling information of a DC MG system, develop a new adaptive control methodology for voltage stabilization of the DC-DC converters feeding CPLs with low ripples. To achieve this goal, in this letter, the deep reinforcement learning (DRL) technique with the Actor-Critic architecture is incorporated into an ultra-local model (ULM) control scheme to address the de-stabilization effect of the CPLs under the reference voltage variations. In the suggested control approach, the feedback controller gains of the ULM controller are considered as the adjustable controller coefficients which will be adaptively designed by the DRL technique through online learning of its neural networks (NNs). It is proved that the suggested scheme will ensure the rigorous stability of the power electronic system, for simultaneous effects of CPL and reference voltage changes, by adaptively adjusting the ULM controller gains. To appraise the merits and usefulness of the suggested adaptive methodology, some dSPACE MicroLabBox outcomes on a real-time testbed of the DC-DC converter feeding a CPL are presented.

In this paper, a non-integer PID type controller based on the deep deterministic policy gradient (DDPG) algorithm is developed for the tracking problem of a mobile robot. This robot system is a typical case of non-holonomic plants and is exposed to the measurement noises and external disturbances. To accomplish the control methodology, two control mechanisms are established independently: a kinematic controller (which is designed based on the kinematic model of the vehicle) and a dynamic controller (which is realized according to the physical specifications of the vehicle dynamics). In particular, an optimal non-integer PID controller is initially designed as the primary dynamic controller for the tracking problem of a non-holonomic wheeled mobile robot (WMR). Then, a DDPG algorithm with the actor-critic framework is established for the supplementary dynamic controller, which is beneficial to the tracking stabilization by adapting to the uncertainties and disturbances. This strategy implements the supplementary based control to compensate for what the original controller is unable to handle and it fully utilizes the prior knowledge of the primary controller. A prototype of the WMR was also adopted to investigate the applicability of the suggested controller from a real-time platform perspective.

Environmental pollutants as a global concern has led to a general increase in the utilization of renewable energy resources instead of fossil fuels. Accordingly, the penetration of these resources in allelectric ships, as well as power grids, has increased in recent years. In this paper, in order to have a zeroemission and cost-effective energy management in an allelectric ferry boat, a new reliable and optimal power scheduling is presented that uses fuel cell and battery energy storage systems. Furthermore, the real information including load profile and paths is considered for the case study to assess the feasibility and superiority of the proposed approach. In addition to the cost of energy management, to have a reliable combination of the proposed resources, loss of load expectation (LOLE) as a reliability index is considered in energy management context and the problem is solved by the deep reinforcement learning in a multi-objective manner. The results of the consideration of two common standards including DNVGL-ST-0033 and DNVGL-ST-0373 demonstrate that the proposed energy management method is applicable in industrial applications. Finally, the real-time simulation-based hardware-in-the-loop (HIL) is conducted to validate the performance and efficacy of the suggested power scheduling for the emission-free ships.

Wireless power transfer (WPT), in a general scene, is the transmission of electrical energy for various technologies by means of magnetic couple resonance. Its potential applications change from low power electric equipment (like smartphones) to high power devices over short distances of centimeters to tens of centimeters. In this letter, a pulse-width-modulation (PWM)-based adaptive data-driven strategy is newly developed for the output voltage regulation of the series-series (SS) compensated WPT. In an attempt to achieve a fast and adaptive voltage regulation, a deep deterministic policy gradient (DDPG) based on an ultra-local model (ULM) control scheme is applied to the dc-dc buck-boost converter feeding CPLs installed in the receiver side of the WPT. In the suggested scheme, an intelligent feedback controller based on the ULM is used to stabilize the voltage response of the buck-boost converter while the unknown dynamics of the converter are estimated by a sliding mode observer (SMO). An auxiliary deep DDPG algorithm with Actor-Critic architecture is implemented to employ its adaptive capability to eliminate the SMO estimation error and improve the voltage regulation of the WPT plant. Some experimental outcomes on a laboratory testbed of the WPT plant are presented to assess the merits and real-time implementation of the adaptive data-driven scheme from a systematic perspective.