• Energy Research

The large−scale integration of wind power and PV cells into electric grids alleviates the problem of an energy crisis. However, this is also responsible for technical and management problems in the power grid, such as power fluctuation, scheduling difficulties, and reliability reduction. The microgrid concept has been proposed to locally control and manage a cluster of local distributed energy resources (DERs) and loads. If the net load power can be accurately predicted, it is possible to schedule/optimize the operation of battery energy storage systems (BESSs) through economic dispatch to cover intermittent renewables. However, the load curve of the microgrid is highly affected by various external factors, resulting in large fluctuations, which makes the prediction problematic. This paper predicts the net electric load of the microgrid using a deep neural network to realize a reliable power supply as well as reduce the cost of power generation. Considering that the backpropagation (BP) neural network has a good approximation effect as well as a strong adaptation ability, the load prediction model of the BP deep neural network is established. However, there are some defects in the BP neural network, such as the prediction effect, which is not precise enough and easily falls into a locally optimal solution. Hence, a genetic algorithm (GA)−reinforced deep neural network is introduced. By optimizing the weight and threshold of the BP network, the deficiency of the BP neural network algorithm is improved so that the prediction effect is realized and optimized. The results reveal that the error reduction in the mean square error (MSE) of the GA–BP neural network prediction is 2.0221, which is significantly smaller than the 30.3493 of the BP neural network prediction. Additionally, the error reduction is 93.3%. The error reductions of the root mean square error (RMSE) and mean absolute error (MAE) are 74.18% and 51.2%, respectively.

The large−scale integration of wind power and PV cells into electric grids alleviates the problem of an energy crisis. However, this is also responsible for technical and management problems in the power grid, such as power fluctuation, scheduling difficulties, and reliability reduction. The microgrid concept has been proposed to locally control and manage a cluster of local distributed energy resources (DERs) and loads. If the net load power can be accurately predicted, it is possible to schedule/optimize the operation of battery energy storage systems (BESSs) through economic dispatch to cover intermittent renewables. However, the load curve of the microgrid is highly affected by various external factors, resulting in large fluctuations, which makes the prediction problematic. This paper predicts the net electric load of the microgrid using a deep neural network to realize a reliable power supply as well as reduce the cost of power generation. Considering that the backpropagation (BP) neural network has a good approximation effect as well as a strong adaptation ability, the load prediction model of the BP deep neural network is established. However, there are some defects in the BP neural network, such as the prediction effect, which is not precise enough and easily falls into a locally optimal solution. Hence, a genetic algorithm (GA)−reinforced deep neural network is introduced. By optimizing the weight and threshold of the BP network, the deficiency of the BP neural network algorithm is improved so that the prediction effect is realized and optimized. The results reveal that the error reduction in the mean square error (MSE) of the GA–BP neural network prediction is 2.0221, which is significantly smaller than the 30.3493 of the BP neural network prediction. Additionally, the error reduction is 93.3%. The error reductions of the root mean square error (RMSE) and mean absolute error (MAE) are 74.18% and 51.2%, respectively.

An interface converter (IC) is used in an AC-DC hybrid microgrid (HMG) and its main tasks are frequency regulation in the AC side, adjusting the DC voltage, and controlling the power flow between AC/DC sides based on the droop control method. The IC should be capable of providing ancillary services such as reactive power supply and compensation of unbalanced and harmonic components in the AC side. However, the use of the IC to provide ancillary services occupies its capacity, which may interfere with the main tasks of the IC. In addition, it is shown in this paper that in unbalanced conditions, the effective power capacity of the IC is reduced by considering the current limit of the converter. In this case, the converter may not be able to perform the main task and provide all the necessary ancillary services at the same time, otherwise, it may be exposed to an overcurrent condition. Therefore, an efficient strategy is needed to manage the IC converter capacity to facilitate optimal use of the entire IC capacity even in unbalanced conditions. Given this challenge, this paper proposes an intelligent strategy for managing the IC capacity, which prioritizes the realization of the main task and the provision of ancillary services. The proposed strategy is evaluated, and its effectiveness is proven by simulation results in Matlab/Simulink.

An interface converter (IC) is used in an AC-DC hybrid microgrid (HMG) and its main tasks are frequency regulation in the AC side, adjusting the DC voltage, and controlling the power flow between AC/DC sides based on the droop control method. The IC should be capable of providing ancillary services such as reactive power supply and compensation of unbalanced and harmonic components in the AC side. However, the use of the IC to provide ancillary services occupies its capacity, which may interfere with the main tasks of the IC. In addition, it is shown in this paper that in unbalanced conditions, the effective power capacity of the IC is reduced by considering the current limit of the converter. In this case, the converter may not be able to perform the main task and provide all the necessary ancillary services at the same time, otherwise, it may be exposed to an overcurrent condition. Therefore, an efficient strategy is needed to manage the IC converter capacity to facilitate optimal use of the entire IC capacity even in unbalanced conditions. Given this challenge, this paper proposes an intelligent strategy for managing the IC capacity, which prioritizes the realization of the main task and the provision of ancillary services. The proposed strategy is evaluated, and its effectiveness is proven by simulation results in Matlab/Simulink.

In this letter, impedance emulation is exploited for synthesizing inertia in autonomous microgrids. An intelligent grid-forming inverter (GFI) is proposed that facilitates sufficient degrees of freedom for adaptive impedance shaping. The latter adaptively changes the effective bandwidth of the inverter's voltage controller, in response to disturbances for inertia synthesis. Deep reinforcement learning is utilized to tackle the lack of explicit quantitative relation between impedance shaping and inertia. Simulation results prove the effectiveness of the method.

In this letter, impedance emulation is exploited for synthesizing inertia in autonomous microgrids. An intelligent grid-forming inverter (GFI) is proposed that facilitates sufficient degrees of freedom for adaptive impedance shaping. The latter adaptively changes the effective bandwidth of the inverter's voltage controller, in response to disturbances for inertia synthesis. Deep reinforcement learning is utilized to tackle the lack of explicit quantitative relation between impedance shaping and inertia. Simulation results prove the effectiveness of the method.

Microgrids mainly rely on distributed energy resources (DER) unable to generate electricity at the expected voltage and frequency. This necessitates the usage of inverters acting as a conditioning interface between the DER and microgrid, hence the name inverter-interfaced distributed generators (IIDG). On the other hand, the fast response of the primary control of inverters causes unconventional behavior of IIDGs under fault conditions, which can severely affect all parts of relaying, that is, fault sensing and polarization and faulted phase selection. This issue becomes more pronounced when an inverter-based microgrid operates in autonomous mode. This paper analyzes the root causes of such unconventional responses that challenge the traditional protection schemes. At first, the inverter control strategies including current limiting are briefly discussed. Then, the paper is continued by analyzing the response of an IIDG feeding its local load to balanced and unbalanced faults, where MATLAB/SIMULINK is used for simulation studies. It is shown how the constraints set by the control strategy itself and current limiter affect the response of IIDGs to fault conditions and consequently, their equivalent models under fault conditions. The findings presented in the paper clearly show that protective functions face difficulties in coping with fault conditions in IIDG-based microgrids due to their different equivalent models during fault period. These studies in turn help modify existing protection schemes or devise new ones applicable to this concept.

Microgrids mainly rely on distributed energy resources (DER) unable to generate electricity at the expected voltage and frequency. This necessitates the usage of inverters acting as a conditioning interface between the DER and microgrid, hence the name inverter-interfaced distributed generators (IIDG). On the other hand, the fast response of the primary control of inverters causes unconventional behavior of IIDGs under fault conditions, which can severely affect all parts of relaying, that is, fault sensing and polarization and faulted phase selection. This issue becomes more pronounced when an inverter-based microgrid operates in autonomous mode. This paper analyzes the root causes of such unconventional responses that challenge the traditional protection schemes. At first, the inverter control strategies including current limiting are briefly discussed. Then, the paper is continued by analyzing the response of an IIDG feeding its local load to balanced and unbalanced faults, where MATLAB/SIMULINK is used for simulation studies. It is shown how the constraints set by the control strategy itself and current limiter affect the response of IIDGs to fault conditions and consequently, their equivalent models under fault conditions. The findings presented in the paper clearly show that protective functions face difficulties in coping with fault conditions in IIDG-based microgrids due to their different equivalent models during fault period. These studies in turn help modify existing protection schemes or devise new ones applicable to this concept.

The application of arresters is critical for the safe operation of electric grids against lightning. Arresters limit the consequences of lightning-induced over-voltages. However, surge arrester protection in electric grids is challenging due to the intrinsic complexities of distribution grids, including overhead lines and power components such as transformers. In this paper, an optimal arrester placement technique is developed by proposing a multi-objective function that includes technical, safety and risk, and economic indices. However, an effective placement model demands a comprehensive and accurate modeling of an electric grid’s components. In this light, appropriate models of a grid’s components including an arrester, the earth, an oil-immersed transformer, overhead lines, and lightning-induced voltage are developed. To achieve accurate models, high-frequency transient mathematical models are developed for the grid’s components. Notably, to have an accurate model of the arrester, which critically impacts the performance of the arrester placement technique, a new arrester model is developed and evaluated based on real technical data from manufacturers such as Pars, Tridelta, and Siemens. Then, the proposed model is compared with the IEEE, Fernandez, and Pinceti models. The arrester model is incorporated in an optimization problem considering the performance of the over-voltage protection and the risk, technical, and economic indices, and it is solved using the particle swarm optimization (PSO) and Monte Carlo (MC) techniques. To validate the proposed arrester model and the placement technique, real data from the Chopoghloo feeder in Bahar, Hamedan, Iran, are simulated. The feeder is expanded over three different geographical areas, including rural, agricultural plain, and mountainous areas.