Search

This review paper thoroughly explores the impact of artificial intelligence on the planning and operation of distributed energy systems in smart grids. With the rapid advancement of artificial intelligence techniques such as machine learning, optimization, and cognitive computing, new opportunities are emerging to enhance the efficiency and reliability of electrical grids. From demand and generation prediction to energy flow optimization and load management, artificial intelligence is playing a pivotal role in the transformation of energy infrastructure. This paper delves deeply into the latest advancements in specific artificial intelligence applications within the context of distributed energy systems, including the coordination of distributed energy resources, the integration of intermittent renewable energies, and the enhancement of demand response. Furthermore, it discusses the technical, economic, and regulatory challenges associated with the implementation of artificial intelligence-based solutions, as well as the ethical considerations related to automation and autonomous decision-making in the energy sector. This comprehensive analysis provides a detailed insight into how artificial intelligence is reshaping the planning and operation of smart grids and highlights future research and development areas that are crucial for achieving a more efficient, sustainable, and resilient electrical system. [ABSTRACT FROM AUTHOR]

The internet of things is undergoing rapid expansion, transforming diverse industries by facilitating device connectivity and supporting advanced applications. In the domain of energy production, internet of things holds substantial promise for streamlining processes and enhancing efficiency. This research introduces a comprehensive monitoring and energy management model tailored for the University of Cuenca's microgrid system, employing internet of things and ThingSpeak as pivotal technologies. The proposed approach capitalizes on intelligent environments and employs ThingSpeak as a robust platform for presenting and analyzing data. Through the integration of internet of things devices and sensors, the photovoltaic system's parameters, including solar radiation and temperature, are monitored in real time. The collected data undergo analysis using sophisticated models and are presented visually through ThingSpeak, facilitating effective energy management and decision making. The developed monitoring system underwent rigorous testing in a laboratory microgrid setup, where the photovoltaic system is interconnected with other generation and storage systems, as well as the electrical grid. This seamless integration enhances visibility and control over the microgrid's energy production. The results attest to the successful implementation of the monitoring system, highlighting its efficacy in improving the supervision, automation, and analysis of daily energy production. By leveraging internet of things technologies and ThingSpeak, stakeholders gain access to real-time data, enabling them to analyze performance trends and optimize energy resources. This research underscores the practical application of internet of things in enhancing the monitoring and management of energy systems with tangible benefits for stakeholders involved. [ABSTRACT FROM AUTHOR]

The integration of renewable resources in isolated systems can produce instability in the electrical grid due to its intermintency. In today's microgrids, which lack synchronous generation, physical inertia is substituted for inertia emulation. To date, the most effective approach remains the frequency derivative control technique. Nevertheless, within this method, the ability to provide virtual drooping is often disregarded in its design, potentially leading to inadequate development in systems featuring high renewable penetration and low damping. To address this issue, this paper introduces an innovative design and analysis of virtual inertia control to simultaneously mimic droop and inertia characteristics in microgrids. The dynamic frequency response without and with renewable energy sources penetration is comparatively analyzed by simulation. The proposed virtual inertia control employs a derivative technique to measure the rate of change of frequency slope during inertia emulation. Sensitivity mapping is conducted to scrutinize its impact on dynamic frequency response. Finally, the physical battery storage system of the University of Cuenca microgrid is used as a case study under operating conditions. [ABSTRACT FROM AUTHOR]

Wind power generation has undergone significant development in recent decades due to its environmental advantages and its economic competitiveness. However, its increasing level of penetration is not exempt from drawbacks, such as those derived from the fluctuating nature of the wind. To reduce its negative incidence on grid power quality and stability, different techniques have been developed, such as those based on power smoothing. In these techniques, there is a research gap on the adjustment of the time constant that adapts to the needs of the smoothing, avoiding uncertain results, computational efforts and delays in the response of the control. This paper addresses the problem, proposing a novel method for power smoothing in a wind turbine by using a fuzzy-logic-based supercapacitor storage system and time-constant fitting, with a first-order adaptive transfer function. The method considers as input variables the active power generated by the wind turbine and the state of charge of the supercapacitor, both sampled simultaneously. After a computation process, the proposal generates active power set-point values that the supercapacitor must produce to compensate for the intermittency of the wind, seen from the point of connection to the grid. The results were validated experimentally with comprehensive laboratory tests. [ABSTRACT FROM AUTHOR]

In recent years, photovoltaic energy production has experienced significant progress, being integrated into the grid through large-scale distributed systems. The intermittent nature of solar irradiance coupled with the presence of photovoltaic failures causes fluctuations that could compromise the quality and stability of electrical grid. This paper presents a novel photovoltaic power smoothing method in a combination with moving averages and ramp rate to reduce fluctuations with hybrid storage systems (supercapacitors/batteries), the main novelty involves optimizing the number of charging/discharging cycles under PV failures. To achieve this goal, a photovoltaic failure detection method is proposed that uses machine learning to process big data by monitoring the behavior of photovoltaic. The experiments have been done under controlled conditions in the microgrid laboratory of the University of Cuenca. The results show the reduction of the supercapacitor operation with respect to other power smoothing methods. Moreover, the monitoring system is capable of detecting a failure in photovoltaic systems with a root mean squared error of 0.66 and the computational effort is reduced using the new smoothing technique. In this sense, the initial execution time is 4 times lower compared to the moving average method. [Display omitted] [ABSTRACT FROM AUTHOR]

The integration of distributed generation, microgrids, and renewable energy sources has significantly enhanced the resilience of modern electrical grids. However, this transition presents challenges in control, stability, safety, and protection due to low fault currents from renewables. This paper addresses these challenges by proposing novel methodologies to enhance fault detection, classification, and localization in microgrids. The literature review highlights a shift towards intelligent learning methods in microgrid protection systems, improving fault response times and identifying electrical faults, including high impedance faults. Nonetheless, existing methods often neglect high impedance fault detection and the integration of differential protection in clustered microgrids. To fill these gaps, this study presents a methodology combining support vector machines and convolutional neural networks for fault detection in microgrids, integrating differential protection for high impedance fault detection. The paper also proposes approaches to optimize protection in clustered microgrid systems. The effectiveness of the methodology is validated using Opal-RT through comparative analyses of signal decomposition techniques, performance and accuracy of support vector machines and convolutional neural networks, K-Fold validation, and sensitivity analysis. Results demonstrate robustness and high performance, achieving up to 100 % accuracy in fault detection and classification. • DG and RES integration in modern grids and MGs enhances resilience but challenges fault detection due to low fault currents. • Novel SVM-CNN methodology proposed for fault detection, addressing challenges like HIF detection. • Proposed SVM-CNN achieves up to 100 % accuracy in fault detection, including HIF and islanding events. • Results highlight methodology's effectiveness in improving fault response time and accuracy. [ABSTRACT FROM AUTHOR]

The integration of photovoltaic generation systems and variable demand can cause instability in the distribution network, due to power fluctuations and the increase in reactants, particularly in the industrial sector. In response, photovoltaic units have been equipped with local storage systems, which eventually absorb power fluctuations and improve installation performance. However, during this procedure other functionalities that energy storage could provide are neglected. Consequently, this study provides a multi-mode energy monitoring and management model that enables voltage regulation, frequency regulation and reactive power compensation through the optimal operation of energy storage systems. With this objective, a smoothing control algorithm is developed that interacts with parameters of the electrical grid at the common connection point and also allows the compensation of reactive power based on an industrial demand profile. This strategy uses the Long short-term memory neural network of historical demand data prior to energy consumption with a relatively low RMSE of 1.2e-09. The results are previously validated in a development environment using a real-time OPAL-RT simulator and tests in the electrical Microgrid laboratory at the University of Cuenca. This configuration allows establishing a demand forecasting model that improves the supervision, automation and analysis of daily energy production. A series of results are provided and analyzed that demonstrate that the new tool allows taking advantage of the provision of multimode functionalities, achieving optimal voltage regulation and improving power quality by reducing the total harmonic distortion THD (V) and THD (I) indices by 0.5. % and 2 % respectively. [ABSTRACT FROM AUTHOR]

The power output obtained from the hydrokinetic renewable system fluctuates with changes in weather conditions, which could cause adverse effects on the voltage, frequency and stability of the electrical grid. In this article, an evaluation of power smoothing is performed for a renewable hydrokinetic on grid system using a supercapacitor. The power fluctuations are mitigated and smoothed by the proposed energy control and supplied to the utility grid and household load. Moreover, this paper studies the impact of the temporal resolution of data sampling with respect to the self-consumption of prosumers under technical, economic and environmental parameters using Matlab/Simulink software. The simulation results show that the fluctuations of the hydrokinetic turbine output power can be significantly mitigated, using the supercapacitor based storage system for different temporal resolutions reducing up to 90% of power peaks and power fluctuations produced by the hydrokinetic turbine and the load. Besides, the use of supercapacitors allows increasing the self-consumption of prosumers up to 17.27% for time resolutions of 1 min. Finally, the proposed control reduces up to 0.54 kgCO 2 /day at cost of energy 0.15 USD/kWh. [Display omitted] [ABSTRACT FROM AUTHOR]

The power fluctuations produced by electric vehicles represent a drawback in large-scale residential applications. In addition to that, short power peaks could pose a risk to the stability of the electrical grid. For this reason, this study presents a feasibility analysis for a residential system composed of electric vehicle chargers. The objective is focused on smoothing the power fluctuations produced by the charge by a supercapacitor through adequate energy control; in addition, selfconsumption is analyzed. Data sampling intervals are also analyzed; the modeling was performed in Matlab software. The results show that there are errors of up to 9% if the data are measured at different sampling intervals. On the other hand, if the supercapacitor is considered, the system saves 59.87% of the energy purchased from the utility grid per day, and the self-consumption of electricity by prosumers can increase up to 73%. Finally, the hydrokinetic/supercapacitor/grid system would save up to 489.1 USD/year in the cost of purchasing electricity from the grid and would increase by 492.75 USD/year for the sale electricity. [ABSTRACT FROM AUTHOR]

• The paper proposes combining DWT and RBFNN for fault detection in microgrids. • The approach achieves precise fault detection, notably for high-resistance single-phase-to-ground faults, with minimal error. • RBFNN and GRNN excel in accuracy and performance, while SVM handles high-dimensional datasets efficiently. • RBFNN exhibits high correlation coefficients, validating its robustness in fault classification. • RBFNN is the optimal choice for microgrid fault detection, balancing accuracy, training time, and simplicity. Microgrids are essential for integrating renewable energy sources into the power grid. However, fault detection is challenging due to bidirectional energy flow. Traditional relay-based systems struggle in microgrids, primarily because of limited fault currents from grid-connected renewable energy inverters. To address these challenges, this paper proposes a new methodology for fault detection and classification in a renewable microgrid. The main contributions encompass two key aspects. Firstly, it enhances fault detection performance in microgrids characterized by nonlinear relationships, including photovoltaic, hydrokinetic, and variable electric load systems. Secondly, the combination of the discrete wavelet transform with various types of neural networks and supervised learning techniques provides a robust methodology for fault detection and classification. The proposed approach is evaluated using an IEEE-5 feeder test bed representing a realistic ring network configuration. The results show that the radial basis function neural network model exhibited promising outcomes, yielding a low prediction error of 1.31 e-31, highlighting its practical potential for enhancing system reliability and performance. Furthermore, various test cases were conducted by altering the ground resistance to train the neural networks, demonstrating the effectiveness of this neural network in accurately identifying fault conditions. Additionally, this research achieved promising outcomes with other models, including support vector machine and nonlinear autoregressive with external input, emphasizing the adaptability of these models in fault detection. [ABSTRACT FROM AUTHOR]

Photovoltaic and hydrokinetic systems are increasing their penetration in electrical distribution systems. This leads to problems of power fluctuations due to the intermittence of renewable sources that could compromise the stability and quality of the power grid. To address this issue, this paper presents a feasibility study of three power smoothing methods for a photovoltaic-hydrokinetic system using laboratory equipment to optimally replicate the real behavior of this type of hybrid system. The proposed algorithms are based on a hybrid storage system with supercapacitors and lithium-ion batteries, several analyzes are presented based on technical and economic parameters. The results demonstrate the feasibility of power smoothing methods for real systems, the comparison between the algorithms highlights the characteristics of the Enhanced Linear Exponential Smoothing Method, reducing the energy cost and regulating the point of common coupling voltage. Moreover, the sensitivity studies show that the energy exchange with the utility grid is affected according to the variations in the capacity of the batteries and the response to power smoothing can decrease or improve depending on the size of the supercapacitors. [Display omitted] • Photovoltaic and hydrokinetic systems in electrical distribution systems. • Problems of power fluctuations due to the intermittence of renewable sources. • Stability and quality of the power grid. • A hybrid storage system with supercapacitors and lithium-ion batteries. • Enhanced Linear Exponential Smoothing Method. [ABSTRACT FROM AUTHOR]