Sustainable agricultural microgrids have emerged as a promising solution to address reliable power supply issues in remote regions by integrating renewable energy sources and energy storage systems. However, the inherent intermittency of renewable resources and the lack of reliable communication infrastructure hinder efficient energy coordination and system stability. This paper proposes a composite model predictive control based decentralized coordination strategy for sustainable agricultural microgrids using hydrogen-battery hybrid energy storage systems. This strategy achieves decentralized dynamic power sharing with optimized transient performance and guaranteed large-signal stability, without relying on real-time communication. The proposed control method incorporates an MPC controller to enhance the dynamic performance of the system and a high-order sliding mode observer to estimate disturbances caused by renewable generation and agricultural load uncertainties. This approach enables smooth power sharing, suppresses current ripple, and ensures system robustness. Additionally, the design is tailored to the characteristics of remote agricultural microgrids by supporting long-term energy storage and mitigating short-term renewable power fluctuations. The effectiveness of the proposed method is verified by simulations and experiments.

Green hydrogen is becoming a key technology in the energy transition. Its production comes from electrolyzers consuming electric power from renewable energy sources. These devices have a high flexibility thanks to hydrogen storage, decoupling hydrogen consumption from electricity demand. This makes electrolyzer a flexible load able to provide grid services such as frequency regulation, increasing grid stability in power systems with high share of renewable energies. The provision of frequency regulation needs to meet the technical and information exchange requirements of the Transmission System Operator (TSO). However, the current TSO requirements do not include the flexibility constrains due to hydrogen storage in electrolyzer systems. Furthermore, the hydrogen storage is also not included in the data models of international standards. This paper analyses the current alignment of international standards with the TSO information exchange requirements for electrolyzer systems, and proposes new requirements to consider the capabilities and limitations caused by the use of hydrogen storage. A study case is employed for this analysis, considering a Proton Exchange Membrane Electrolyzers (PEMEL) providing Frequency Containment Reserve for Disturbances (FCR-D) in the Nordic power system.

Driven by sustainability goals and the increasing integration of renewable energy sources, effective energy management systems (EMS) are crucial for enabling smart buildings to operate efficiently. This paper proposes a safe real-time scheduling method based on deep reinforcement learning (DRL), employing the deep deterministic policy gradient (DDPG) algorithm to handle uncertainties in solar PV generation and energy demand without explicit forecasting. Compared to conventional DDPG, the proposed safe DDPG framework introduces a projection layer after the actor and target actor networks to ensure that all actions remain within operational constraints. A case study conducted on an educational building in Stockholm demonstrates the effectiveness of the proposed method in maintaining user comfort, satisfying EV charging requirements, ensuring dishwasher operation, and effectively utilizing the flexibility of both EVs and the dishwasher.

The integration of energy storage systems (ESS) into railway traction power supply systems (TPSS) presents a promising approach to enhancing energy efficiency in modern electrified railways. This paper proposes an energy management strategy for electric railway system with the integration of ESSs, which achieves effective peak shaving, enhances energy utilization, and reduces electricity cost. A combined model incorporating train trajectory optimization, traction system power flow calculation, and ESS behavior is established to jointly optimize ESS location, sizing, and operational strategy. At last, the proposed method is validated on a Swedish railway case study to demonstrate improved energy management performance under realistic conditions.

The rapid advancement of intelligent devices and smart meters has positioned smart buildings as key components in modern living. To ensure users’ comfort, regulate the indoor temperature, and minimize the overall cost of a building, an effective energy management system (EMS) is necessary. This paper proposes a deep deterministic policy gradient (DDPG)-based energy management system (EMS) for smart buildings, incorporating photovoltaic (PV) panels, energy storage systems (ESS), heat pump (HP), and EV chargers. Unlike traditional methods that linearize temperature variations, our approach leverages DDPG to handle nonlinear models. The proposed EMS automatically addresses uncertainties in temperature and solar irradiation and provides a real-time scheduling commands without the demand for predicted data. Simulation results demonstrate the effectiveness of the DDPG-based EMS in minimizing costs while ensuring user comfort, outperforming traditional methods in both cost savings and temperature control precision.

Wide deployment of electric vehicles (EVs) requires the investment of new charging infrastructures and brings the security issues on the grid. In this paper, a two-stage collaborative planning strategy is proposed for location selection of fast charging stations (FCSs) to achieve optimal planning and scheduling with guaranteed constraints of power network (PN) and transportation network (TN). In the scheduling model, a mixed-integer linear programming (MILP) model is formulated based on the integration of a PN and a TN, in which an extended road model is established with consideration of various vehicle types, such as EVs and gasoline vehicles (GVs), to achieve optimal operation of the coupled power and transportation systems. In the planning model, FCSs and solar PV systems are established considering both investment and scheduling costs. Finally, the SOS2 method is used to linearize the TN model and the particle swarm-genetic algorithm (PSO-GA) is used to solve the nonlinearity caused by the coupling between the planning model and the scheduling model. The effectiveness and applicability of the proposed planning strategy are validated using the IEEE 33 bus power system and 12 node transportation system.

This article introduces a novel self-supervised method that leverages incoherence detection for video representation learning. It stems from the observation that the visual system of human beings can easily identify video incoherence based on their comprehensive understanding of videos. Specifically, we construct the incoherent clip by multiple subclips hierarchically sampled from the same raw video with various lengths of incoherence. The network is trained to learn the high-level representation by predicting the location and length of incoherence given the incoherent clip as input. Additionally, we introduce intravideo contrastive learning to maximize the mutual information between incoherent clips from the same raw video. We evaluate our proposed method through extensive experiments on action recognition and video retrieval using various backbone networks. Experiments show that our proposed method achieves remarkable performance across different backbone networks and different datasets compared to previous coherence-based methods.

DC microgrids have emerged as a promising solution for efficient and reliable electricity distribution. In DC microgrids, when power electronic loads and motor drives are tightly regulated, they behave as constant power loads (CPLs) and may lead to the instability issue. In this paper, a novel output-constrained controller for the DC/DC buck converter feeding CPLs is proposed. By introducing the output-constrained technique into the backstepping method, the proposed control scheme can keep the DC bus working within the pre-specific boundary even when large-signal disturbances happen. Relevant theoretical analyses are conducted by employing Laypunov stability theorem. Simulations in Matlab/Simulink are presented to verify the proposed controller.

Dual-active-bridge (DAB) converter is a promising technology for the high-frequency and high-power application of electric vehicle (EV) chargers. To reduce losses of power exchange between EV battery and power source or load, several control methods, such as tripe phase-shift (TPS) control with minimum-current-stress optimization, are used in DAB converter. However, in most existing works, the dead-time effects are not considered, which will result in a non-zero-voltage-switching (non-ZVS) operation and thus inaccurate optimization results. This paper analyzes the influence of junction capacitance and dead time on the ZVS characteristics, and proposes a TPS control-based optimization scheme aiming at the minimum inductor current stress under the premise of ZVS operation. The proposed approach can further improve the operating efficiency of DAB converters. Simulation results validate the effectiveness of proposed optimization scheme, where the losses can be reduced significantly under light load.

WiFi technology has been applied to various places due to the increasing requirement of high-speed Internet access. Recently, besides network services, WiFi sensing is appealing in smart homes since it is device free, cost effective and privacy preserving. Though numerous WiFi sensing methods have been developed, most of them only consider single smart home scenario. Without the connection of powerful cloud server and massive users, large-scale WiFi sensing is still difficult. In this article, we first analyze and summarize these obstacles, and propose an efficient large-scale WiFi sensing framework, namely, EfficientFi. The EfficientFi works with edge computing at WiFi access points and cloud computing at center servers. It consists of a novel deep neural network that can compress fine-grained WiFi channel state information (CSI) at edge, restore CSI at cloud, and perform sensing tasks simultaneously. A quantized autoencoder and a joint classifier are designed to achieve these goals in an end-to-end fashion. To the best of our knowledge, the EfficientFi is the first Internet of Things-cloud-enabled WiFi sensing framework that significantly reduces communication overhead while realizing sensing tasks accurately. We utilized human activity recognition (HAR) and identification via WiFi sensing as two case studies, and conduct extensive experiments to evaluate the EfficientFi. The results show that it compresses CSI data from 1.368 Mb/s to 0.768 kb/s with extremely low error of data reconstruction and achieves over 98% accuracy for HAR.

In this article, we consider the resilience problem in the presence of communication faults encountered in distributed secondary voltage and frequency control of an islanded alternating current microgrid. Such faults include the partial failure of communication links and some classes of data manipulation attacks. This practical and important yet challenging issue has been taken into limited consideration by existing approaches, which commonly assume that the measurement or communication between the distributed generations (DGs) is ideal or satisfies some restrictive assumptions. To achieve communication resilience, a novel adaptive observer is first proposed for each individual DG to estimate the desired reference voltage and frequency under unknown communication faults. Then, to guarantee the stability of the closed-loop system, voltage and frequency restoration, and accurate power sharing regardless of unknown communication faults, sufficient conditions are derived. Some simulation results are presented to verify the effectiveness of the proposed secondary control approach.

For the fuel cell-ultracapacitor auxiliary power unit (FC-UC APU), the basic energy management objectives could be summarized as achieving dynamic load power sharing (i.e. the FC supplies the average load power while the UC buffers all the fluctuating load power), extending the service life, improving energy efficiency, and ensuring the system stability. Conventionally, the dynamic load power sharing objective is achieved by using centralized energy management system (EMS) which suffers from poor flexibility, scalability and reliability. What's more, the system stability can hardly be guaranteed because serious interactions between source converters and power-electronic interfaced loads, which behave as constant power loads (CPLs), always exist. In this paper, a completely decentralized EMS based on modified droop control and passivity-based control (PBC) is proposed to achieve the required objectives simultaneously in a decentralized way. First, the architecture and model of the FC-UC APU are described in detail. Then, analysis on the operational principle of the proposed EMS is deeply studied. Finally, simulation results verified the correctness of the theoretical analysis and effectiveness of the proposed decentralized EMS.

The high penetration of power electronic converter loads in dc microgrid causes system stability issue, or also known as constant power load issue, due to their negative impedance characteristics. The stability concern will be more complicated for a self-disciplined microgrid that allows plug and play of various distributed generations (DGs). This article proposes a robust droop-based controller for decentralized power sharing in a dc microgrid considering large-signal stability. For each DG interface converter subsystem, the interactions with other DG interface converters and loads are estimated by a nonlinear disturbance observer (NDO) utilizing the subsystem's own information to achieve decentralized power sharing and fast voltage regulation. With the uncertainties of circuit parameters modeled as a lumped disturbance term and compensated by an NDO, the proposed controller can significantly enhance the robustness against the uncertainties of circuit parameters. The large-signal stability of the whole interconnected system is proved by the backstepping algorithm and Lyapunov theorem. The efficacy and large-signal stability of the proposed approach are verified by both simulations and experiments.

This paper presents a decentralized secondary control scheme to solve the voltage restoration and current sharing problem in islanded DC microgrid (MG) systems. The existing solutions to this problem are either centralized control or distributed control based approaches. For these methods, communication and information exchange is inevitable. In order to improve the system robustness and reduce the system implementation cost, a decentralized communication-free leaky integral control is proposed in this paper, which is able to realize the same control goals without any communication. The stability of overall system together with proposed decentralized controller is analysed. A test DC MG system is built in Matlab Simulink to validate the effectiveness of proposed control method.

The wide utilization of power electronic converters causes the constant power load stability issue in DC microgrids. This paper proposes an offset-free model predictive controller for a DC/DC boost converter feeding constant power loads. First, a baseline nonlinear model predictive controller is designed by solving a receding horizon optimization problem explicitly. Then a higher-order sliding mode observer is utilized to estimate the unknown load variation and system uncertainties. Finally an offset-free controller is integrated by the baseline controller and observer. The proposed controller achieves optimized transient dynamics and accurate tracking with large signal stability. Simulation results are presented to verify the proposed approach.

Economic operation is a major concern for microgrids. Conventionally, economic dispatch of distributed generations (DGs) are solved by centralized control with optimization algorithms or distributed control with consensus algorithm. To improve the reliability, scalability and economy of microgrids, a fully decentralized economic power sharing strategy is proposed in this paper. The proposed method is based on frequency/incremental cost droop (f/IC) characteristics and incremental cost (IC) functions of DGs. ICs of DGs reach equality with the convergence of system frequency. Power dispatch of each DG is automatically achieved based on its relevant incremental cost function. Therefore, by using this method, the incremental cost of each DG will reach equality autonomously and the total operating cost can be optimized without any communication or central controllers. Simulation platform of an autonomous AC MG with three DGs is built in Matlab/Simulink to verify the effectiveness of the proposed method.