Search

To prevent grounding accidents caused by forgetting to remove the temporary grounding wires and the contact of trees with the distribution network, a multi-point synchronous temporary grounding wire detection device based on convolutional neural networks is developed. The developed device can judge the type of groundings on the test line quickly and locate the ground points accurately during the cut-out. Three-phase alternating current (AC) signals with a specific frequency are injected at multiple points on the line by multiple groups of the device controlled by Raspberry Pi 3B + and embedded Android. The device can achieve the approximate location through the impedance ranging method and the accurate location by integrating the data from multiple points. The trained EfficientNet-B0 algorithm is utilized to predict the grounding positions. The tested results of the prototype verify the accuracy and rapidity of grounding diagnosis and positioning.

The work proposes high-dimensional multiple fractional-order optimization algorithm (HMFOA) to tune the controller parameters of the rotor side converter of doubly-fed induction generator-based wind turbines to achieve higher control performance. The case studies are verified in eight benchmark mathematical optimization problems; the results illustrate that the proposed optimizer has fast convergence speed, high computational precision, and avoidance of falling into local optimums. Compared to four other algorithms, the results show that HMFOA obtains the optimal parameters of controllers and achieves more accurate power point tracking capability and certain fault ride-through capability, which verifies the feasibility and effectiveness of the algorithm.

With the rapid development of industry, the increasing discharge of sewage causes the detection of water quality to be of increasing importance. Potassium dichromate titration is one of the most important testing methods in water quality detection; the ability to accurately identify the titration end-point of potassium dichromate is currently a research challenge. To identify titration end-point quickly and accurately, this study proposes a ResNet14Attention network, which utilizes residual modules that focus on original image information and an attention mechanism that focuses highly on classification targets. The proposed ResNet14Attention network is compared with 12 convolutional neural networks such as ResNet series networks, VGG, and GoogLeNet. The results of comparison experiments reveal that only the proposed ResNet14Attention network has the highest training and testing accuracy of 100% among all convolutional neural networks in the comparison experiment; the proposed ResNet14Attention network has the highest training speed compared to all the networks that over 90% accuracy.

As the core components of electric vehicles, the safety of the electric system, including motors, batteries, and electronic control systems, has always been of great concern. To provide early warning of electric-system failure and troubleshoot the problem in time, this study proposes a novel energy-vehicle electric-system failure-classification method, which is named Pearson-ShuffleDarkNet37-SE-Fully Connected-Net (PSDSEF). Firstly, the raw data were preprocessed and dimensionality reduction was performed after the Pearson correlation coefficient; then, data features were extracted utilizing ShuffleNet and an improved DarkNet37-SE network based on DarkNet53; secondly, the inserted squeeze-and-excitation networks (SE-Net) channel attention were able to obtain more fault-related target information; finally, the prediction results of the ShuffleNet and DarkNet37-SE networks were aggregated with a fully connected neural network to output the classification results. The experimental results showed that the proposed PSDSEF-based electric vehicles electric-system fault-classification method achieved an accuracy of 97.22%, which is better than other classical convolutional neural networks with the highest accuracy of 92.19% (ResNet101); the training time is faster than the average training time of the comparative networks. The proposed PSDSEF has the advantage of high classification accuracy and small number of parameters.

This work proposes a parallel multi-layer Monte Carlo optimization algorithm (PMMCOA) that optimizes proportional–integral parameters for a doubly fed induction generator-based wind turbine controller. The PMMCOA, an improved form of the Monte Carlo algorithm, realizes the optimization process via a parallel multi-layer structure. The PMMCOA includes rough search layers, precise search layers, and re-precise search layers. Each layer of the PMMCOA adopts a multi-region and multi-granularity approach to increase the diversity and randomness of the search samples. The PMMCOA is employed to tune the controller parameters for achieving maximum power point tracking and improving generation efficiency. The controller fitness function reflects the sum of the rotor angular velocity error and the reactive power error. Compared with the five metaheuristic algorithms, the PMMCOA has a higher global convergence and more accurate power tracking ability.

With the massive development of various new energy sources, the balance of supply and demand in the power grid faces a considerable challenge. A reliable way is to perform demand-side management on energies. For demand-side management, monitoring the load connected to power distribution networks is necessary. This paper proposes deep flexible transmitter networks to quickly monitor the load when the load is connected to power distribution networks. The proposed algorithm combines flexible transmitter networks and deep backpropagation neural networks. After measuring the waveforms of loads, the algorithm is trained by the measured operational data. The testing results show that the proposed deep flexible transmitter networks can accurately monitor the load connected to power distribution networks. Compared with the deep backpropagation neural networks, the proposed algorithm improves the monitoring accuracy by more than 5%. The speed of the proposed algorithm is verified in experiments. After testing on embedded devices, the proposed algorithm can satisfy the requirements of edge computing systems.

Founded on bounded rationality and limited information, evolutionary game theory has been preliminarily applied in many fields, such as electricity market (EM). To address the complex behavioral decision-making issues in the more-common three-population multi-strategy evolutionary game (3PmSEG) scenarios in EM. This paper explores the long-term evolutionarily stable equilibrium (ESE) characteristics of general 3PmSEG systems with the aim of systematically investigating the evolution process of long-term on-grid bidding of a generation-side EM based on these features. First, the long-term ESE characteristics of general three-population two-strategy and three-strategy evolutionary games are thoroughly investigated. Complete relative net payoff (RNP) parameters are defined for these games. Then, the modeling idea of general 3PmSEGs is elaborated. Research shows that the game can be guided to evolve toward an expected long-term ESE point by properly adjusting its RNP parameters. To verify this, finally, the long-term on-grid bidding of power generation is investigated for a tripartite generation-side EM. The case study reveals that effective government supervision can effectively promote new energy accommodation of the market. Overall, the models developed in this paper are relatively universal and practical, which can provide some theoretical and methodological references for complex evolutionary game issues in related fields.

In recent years, the rapid development of artificial intelligence, especially deep learning technology, makes machine learning have application scenarios in the fields of power system stability analysis, coordination along with scheduling and load forecasting. This paper designs an emotional deep learning programming controller (EDLPC) for automatic voltage control of power systems. The designed EDLPC contains an emotional deep neural network (EDNN) structure and an artificial emotional Q-learning algorithm. Besides, a specially defined proportional-integral-derivative (PID) controller is added to the deep neural networks (DNNs) structure as the actuator of an EDNN to realize the automatic tuning of PID controller parameters. In terms of control, the controller combines the advantages of the EDNN and PID controller, meanwhile adopts a reinforcement learning algorithm to optimize the parameters. From the perspective of reinforcement learning, embedding prior knowledge into the output instructions of EDNN is helpful to weaken the fitting problem in the training process. Compared with the outputs of the DNN and Q-learning algorithm under the two cases, the EDLPC could gain the highest control performance with smaller voltage deviations. The simulation results verify the feasibility and effectiveness of the proposed method for automatic voltage control of power systems.

Microgrid energy management is a typical discrete non-linear optimization problem that is usually solved by off-line optimization, day-ahead demand-side management, and long-term dynamic optimization scheduling strategy. However, due to the intermittent distributed generation and time-varying load in microgrids, more attention should be paid to the real-time optimal scheduling of the overall operation of energy to ensure the dynamic balance of supply and demand in microgrids. Combining demand-side response with real-time power price, this paper applies the strategy to microgrid energy management and proposes a distributed energy real-time management model of microgrid based on demand-side response function. A deep adaptive dynamic programming optimization algorithm is also proposed for the model. The real-time interaction between microgrid operators and users is realized. The closed-loop feedback control structure of the proposed model ensures the real-time optimization control strategy. Therefore, the proposed energy management model and control strategy can realize intra-day dispatching in microgrids. The real-time performance and effectiveness of the proposed energy management model and control strategy are also verified by numerical simulation. Finally, since the proposed model is approximate, whether the solution obtained by the algorithm is the optimal or satisfactory solution of the optimization strategy set is a lack of theoretical support. Therefore, according to the approximation theorem of bounded rationality, the application conditions of the model in power markets are proposed. It is proved that the proposed model meets the application conditions, and is a specific application of bounded rationality approaching complete rationality in the power market. It is also proved that the best solution is involved in the satisfactory solution set of the model. Thus, the control strategy is a rational and feasible optimal management control strategy, which provides a theoretical basis for its further implementation.

This article proposes a coordinated optimization and control algorithm for coordinated secondary voltage control (CSVC) in multi-generator power systems. Firstly, to obtain a smaller voltage deviation and avoid the curse of dimensionality simultaneously, an artificial emotional reinforcement learning (AERL) is applied to automatic voltage regulation (AVR). Secondly, to obtain a smaller fitness value with lesser random for the decentralized independent variables optimization problem of the CSVC, a complex-valued encoding dragonfly algorithm (CDA) is proposed. Thirdly, the CDA and the AERL are coordinated for the CSVC and the AVR in multi-generator power systems. To verify the control performance of the AERL and the convergence of the proposed CDA, three simulation cases, i.e., IEEE 57-bus, 118-bus and 300-bus systems, are considered. The simulation results show that the CDA-AERL effectively obtains the smallest control objectives and the convergence for the CSVC in multi-generator power systems.

The asymptotically stable equilibrium points of asymmetric evolutionary games for multiple groups with multiple game strategies are obtained. The evolution of four groups and more multiple groups in open electricity market are described by the replicator dynamics. Multiple game strategies of the power generation enterprises in open electricity market are studied. Besides, the corresponding asymptotic stability conditions are given by the Lyapunov stability criterion.

Deep neural networks of deep learning algorithms can be applied into regressions and classifications. While the regression performances and classification performances of the deep neural networks are depending on the hyper-parameters of the deep neural networks. To mitigate the adverse effect of the hyper-parameters for the deep learning algorithms, this paper proposes deep forest regression for the short-term load forecasting of power systems. Deep forest regression includes two procedures, i.e., multi-grained scanning procedure and cascade forest procedure. These two procedures can be effectively trained by two completely random forests and two random forests with the default configuration. Then, the deep forest regression is applied into the short-term load forecasting of power systems. The forecasting performances of deep forest regression are compared with that of numerous intelligent algorithms and conventional regression algorithms under the model with the data of previous 7-day, 21-day, and 40-day. Besides, the forecasting performances of deep forest regression with different parameters are compared. The numerical results show that the deep forest regression with default configured parameters can increase the accuracy of the short-term forecasting and mitigate the influences of the experiences for the configuration of the hyper-parameters of deep learning model.

An adaptive distributed consensus protocol (ADCP) for the automatic generation control of large-scale interconnected power systems is proposed in this paper. An updated strategy of the parameters of the ADCP is designed. Furthermore, the stability of the proposed ADCP is analyzed. A four-area power system that all the areas are connected in the large-scale interconnected power system is simulated in this paper. Comparing with the simulation results obtained by three control protocols, i.e., none protocol, distributed consensus protocol, and the proposed ADCP, the ADCP can obtain higher control performance. The feasibility and effectiveness of the ADCP are verified through the simulation results.

To reduce occurrences of emergency situations in large-scale interconnected power systems with large continuous disturbances, a preventive strategy for the automatic generation control (AGC) of power systems is proposed. To mitigate the curse of dimensionality that arises in conventional reinforcement learning algorithms, deep forest is applied to reinforcement learning. Therefore, deep forest reinforcement learning (DFRL) as a preventive strategy for AGC is proposed in this paper. The DFRL method consists of deep forest and multiple subsidiary reinforcement learning. The deep forest component of the DFRL is applied to predict the next systemic state of a power system, including emergency states and normal states. The multiple subsidiary reinforcement learning component, which includes reinforcement learning for emergency states and reinforcement learning for normal states, is applied to learn the features of the power system. The performance of the DFRL algorithm was compared to that of 10 other conventional AGC algorithms on a two-area load frequency control power system, a three-area power system, and the China Southern Power Grid. The DFRL method achieved the highest control performance. With this new method, both the occurrences of emergency situations and the curse of dimensionality can be simultaneously reduced.

With the promotion and development of clean energy, it is challenging to ensure the optimization of control performance in frequency control of the hydropower-photovoltaic hybrid microgrid system caused by the output power fluctuation of photovoltaic power generation. In this study, an optimal load frequency controller (LFC) for a hydropower-photovoltaic hybrid microgrid system was designed to improve the dynamic response when the load and photovoltaic output power are perturbed based on the off-policy integral reinforcement learning algorithm. First, a mechanism model of the hydropower-photovoltaic hybrid microgrid system was established. Next, the LFC problem was transformed into a zero-sum game control problem based on the characteristics of the power system. Subsequently, three neural networks were employed to approximate the Nash equilibrium solution of the zero-sum game with historical input and output data when the system dynamics are completely unknown. Finally, simulation experiments were conducted to verify the effectiveness and optimality of the proposed method. The introduction of this method provides a new perspective for frequency control for the hydropower-photovoltaic hybrid microgrid system. [ABSTRACT FROM AUTHOR]

Solar energy has emerged as a key solution in the global transition to renewable energy sources, driven by environmental concerns and climate change. This is largely due to its cleanliness, availability, and cost-effectiveness. The precise assessment of hidden factors within photovoltaic (PV) models is critical for effectively exploiting the potential of these systems. This study employs a novel approach to parameter estimation, utilizing the electric eel foraging optimizer (EEFO), recently documented in the literature, to address such engineering issues. The EEFO emerges as a competitive metaheuristic methodology that plays a crucial role in enabling precise parameter extraction. In order to maintain scientific integrity and fairness, the study utilizes the RTC France solar cell as a benchmark case. We incorporate the EEFO approach, together with Newton-Raphson method, into the parameter tuning process for three PV models: single-diode, double-diode, and three-diode models, using a common experimental framework. We selected the RTC France solar cell for the single-diode, double-diode, and three-diode models because of its significant role in the field. It serves as a reliable evaluation platform for the EEFO approach. We conduct a thorough evaluation using statistical, convergence, and elapsed time studies, demonstrating that EEFO consistently achieves low RMSE values. This indicates that EEFO is capable of accurately estimating the current-voltage characteristics. The system's smooth convergence behavior further reinforces its efficacy. Comparing the EEFO with competing methodologies reinforces its competitive advantage in optimizing solar PV model parameters, showcasing its potential to greatly enhance the usage of solar energy. [ABSTRACT FROM AUTHOR]