Stable Operation Of Power System Research Articles

Federated knowledge distillation for enhanced insulator defect detection in resource‐constrained environments

AbstractInsulator defect detection is crucial for the stable operation of power systems. It has become a mainstream research direction to realise insulator defect detection based on the combination of line images captured by UAVs and deep learning techniques. However, the existing high‐quality insulator defect detection models still face problems such as relying on massive‐labelled data and huge model parameters. Especially on resource‐constrained devices, it becomes a challenge to strike a balance between model lightweighting and performance. Although the knowledge distillation technique provides a solution for model lightweighting, the loss of information in the distillation process leads to the performance degradation of small models, which in turn creates a paradox between lightweighting and performance. Hence, an insulator defect detection method based on federated knowledge distillation is proposed. The method not only realises the lightweighting of the model, but also effectively improves the model performance by collaboratively training the model through the federated learning approach. Moreover, the asynchronous aggregation approach and model freshness mechanism designed in the method further enhance the training efficiency and collaborative effect. The experimental results show that the detection accuracy and efficiency of this paper's method on public datasets are significantly better than the benchmark algorithm.

Research on two‐level energy management based on tiered demand response and energy storage systems

AbstractIn response to the escalating demands of the electricity market for load dispatch optimization and the stable operation of power systems, the design of effective incentive mechanisms to guide user electricity consumption behaviour has become an urgent task. This study addresses the complexity of the power load dispatch system by analysing the characteristics and interrelations of large‐scale user load demand responses. A dual‐layer energy management model was constructed, and a demand response incentive mechanism was designed. Adaptive incentive strategies were formulated according to different electric power user demand response scenarios. Furthermore, an optimal incentive decision‐making technology oriented towards user comfort was proposed, achieving an integrated function of strategy formulation, implementation, analysis, and optimization for power demand response. Through typical applications in core business scenarios such as elasticity of power user demand response, tiered incentive mechanisms, and comprehensive user utility, the model and strategies have been confirmed to optimize the economic benefits of virtual power plants and demand‐side electricity users under the premise of ensuring user comfort. This provides a novel solution for the efficient operation of the power market.

Short-Term Electrical Load Forecasting Using an Enhanced Extreme Learning Machine Based on the Improved Dwarf Mongoose Optimization Algorithm

Accurate short-term electrical load forecasting is crucial for the stable operation of power systems. Given the nonlinear, periodic, and rapidly changing characteristics of short-term power load forecasts, this paper introduces a novel forecasting method employing an Extreme Learning Machine (ELM) enhanced by an improved Dwarf Mongoose Optimization Algorithm (Local escape Dwarf Mongoose Optimization Algorithm, LDMOA). This method addresses the significant prediction errors of conventional ELM models and enhances prediction accuracy. The enhancements to the Dwarf Mongoose Optimization Algorithm include three key modifications: initially, a dynamic backward learning strategy is integrated at the early stages of the algorithm to augment its global search capabilities. Subsequently, a cosine algorithm is employed to locate new food sources, thereby expanding the search scope and avoiding local optima. Lastly, a “madness factor” is added when identifying new sleeping burrows to further widen the search area and effectively circumvent local optima. Comparative analyses using benchmark functions demonstrate the improved algorithm’s superior convergence and stability. In this study, the LDMOA algorithm optimizes the weights and thresholds of the ELM to establish the LDMOA-ELM prediction model. Experimental forecasts utilizing data from China’s 2016 “The Electrician Mathematical Contest in Modeling” demonstrate that the LDMOA-ELM model significantly outperforms the original ELM model in terms of prediction error and accuracy.

A Novel Improved Variational Mode Decomposition-Temporal Convolutional Network-Gated Recurrent Unit with Multi-Head Attention Mechanism for Enhanced Photovoltaic Power Forecasting

Photovoltaic (PV) power forecasting plays a crucial role in optimizing renewable energy integration into the grid, necessitating accurate predictions to mitigate the inherent variability of solar energy generation. We propose a novel forecasting model that combines improved variational mode decomposition (IVMD) with the temporal convolutional network-gated recurrent unit (TCN-GRU) architecture, enriched with a multi-head attention mechanism. By focusing on four key environmental factors influencing PV output, the proposed IVMD-TCN-GRU framework targets a significant research gap in renewable energy forecasting methodologies. Initially, leveraging the sparrow search algorithm (SSA), we optimize the parameters of VMD, including the mode component K-value and penalty factor, based on the minimum envelope entropy principle. The optimized VMD then decomposes PV power, while the TCN-GRU model harnesses TCN’s proficiency in learning local temporal features and GRU’s capability in rapidly modeling sequence data, while leveraging multi-head attention to better utilize the global correlation information within sequence data. Through this design, the model adeptly captures the correlations within time series data, demonstrating superior performance in prediction tasks. Subsequently, the SSA is employed to optimize GRU parameters, and the decomposed PV power mode components and environmental feature attributes are inputted into the TCN-GRU neural network. This facilitates dynamic temporal modeling of multivariate feature sequences. Finally, the predicted values of each component are summed to realize PV power forecasting. Validation using real data from a PV station corroborates that the novel model demonstrates a substantial reduction in RMSE and MAE of up to 55.1% and 54.5%, respectively, particularly evident in instances of pronounced photovoltaic power fluctuations during inclement weather conditions. The proposed method exhibits marked improvements in accuracy compared to traditional PV power prediction methods, underscoring its significance in enhancing forecasting precision and ensuring the secure scheduling and stable operation of power systems.

Dual NWP wind speed correction based on trend fusion and fluctuation clustering and its application in short-term wind power prediction

With the continuous growth of grid-connected installed capacity of wind power, the inevitable gap, volatility and randomness of wind power pose challenges to the stability of real-time operation of power system. Accurate wind power prediction (WPP) can effectively ensure the safe and stable operation of power system. At present, the main input of short-term power prediction based on data-driven model is numerical weather prediction (NWP), and its prediction accuracy leads to the failure to effectively improve the accuracy of short-term power prediction. To solve this problem, this paper proposes a dual NWP wind speed (WS) correction method based on trend fusion and fluctuation clustering. First, the WS trend is used to construct a new input feature, and the NWP WS error distribution is determined to establish a more correct and stable mapping relationship with the NWP WS error. Secondly, the error is decomposed by Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), and the trend and fluctuation components are defined by Pearson coefficient. The trend curve features in the short 24h period were extracted from the two dimensions of time and value, and the trend and fluctuation curve databases under different scenarios were formed by K-Medoids clustering. Finally, the trend component is modified by the Attention-GRU model, and the corresponding trend component is searched and matched from the database to correct the fluctuation component. The NWP WS is modified by the superposition of the two components and the short-term WPP is made. Two wind farms in Mengxi, China were used for example analysis, and the prediction accuracy was improved by 10% and 13.1% respectively, which demonstrated the effectiveness of the proposed method.

Analysis of the Effect of Meteorological Elements on New Energy Power Prediction Based on Machine Learning

Background: With the gradual construction of new power systems, new energy sources, such as wind and photovoltaic power, will gradually dominate positions in the power supply structure, directly leading the new power system to rely heavily on accurate meteorological forecasts. High-precision and high-resolution meteorological forecasts are important technical methods to improve the safe, stable, and economic operation of the new power system. Objective: Since the analysis of meteorological elements is the basis of meteorological forecasting, in this paper, the effect of different meteorological elements including temperature, relative humidity, air pressure, wind speed, wind direction, and radiation on the performance of power forecasting, was analyzed by using 7 machine learning algorithms in 5 provinces in southern China. Methods: About 5 provinces in southern China were selected as the research objects, and 7 typical machine learning algorithms were applied and compared, including support vector machine (SVM), decision tree (DT), random forest (RFR), K-nearest neighbor (KNN), Linear Regression (LR), Ridge Regression (RR), and Lasso Regression (Lasso R). At the same time, the influence of different meteorological elements, such as temperature, relative humidity, air pressure, wind speed, wind direction, and radiation amount, on the prediction performance of wind power and photovoltaic power was considered. Then, the performance of different regression models was further investigated and analyzed. Results: Based on the data of 10 new energy stations in 5 regions, the research on the prediction performance of 7 machine learning methods shows that the performance of models in different regions varies greatly. Among the 10 selected new energy stations, the RFR model and KNR model have superior overall performance. Conclusion: This study shows how variable importance and prediction accuracy depend on regression methods and climatic variables, providing effective methods to assess the interdependence of meteorological variables and the importance of meteorological variables in predicting output power.

Power quality disturbances classification with imbalanced/insufficient samples based on WGAN-GP-SA and DCNN

The accurate identification of power quality disturbance signals (PQDs) is of great importance to ensure the safe and stable operation of power systems. Considering that there are insufficient samples and imbalance samples of power quality disturbance signals in real systems, the hybrid classification method based on WGAN-GP-SA (Wasserstein generative adversarial networks with gradient penalty and Squeeze-and-Excitation block with atrous spatial pyramid pooling module) and DCNN (deep convolutional neural network) is proposed for recognition of PQDs. Firstly, time-frequency features are extracted by combining improved Kalman and continuous wavelet transforms (CWT); secondly, the original training time-frequency maps are expanded by using WGAN-GP-SA, which can learn the distribution of real data and generate similar samples, and PSNR, SSIM, FID and other indexes are introduced for evaluation of generated data; finally, classification experiments are conducted on two data sets using DCNN, and simulation results show that the accuracy is improved by 2.82 % compared with the original data without augmentation. Furthermore, t-distributed stochastic neighbor embedding algorithm (t-SNE) is introduced for visually analysing of classification performance of various datasets, and the visualization indicates the superiority of the hybrid classification method.

Value Evaluation Model of Multi-Temporal Energy Storage for Flexibility Provision in Microgrids

With the advancement of distributed power generation technology and the deepening of the low-carbon transformation of energy structure, a high proportion of renewable energy has become an inevitable trend in future energy systems, especially for microgrids. However, the volatility and uncertainty associated with renewable energy pose significant challenges to the secure and stable operation of power systems, necessitating the exploration of the flexible regulation of resources. Energy storage, as a crucial flexible resource characterized by technological diversity and a variety of regulation capabilities, has been extensively studied and applied. Nonetheless, the high investment costs and limited returns of energy storage technology, coupled with the ambiguous utility in different scenarios under the current electricity market’s framework, complicate its broader application. To thoroughly analyze the utility of energy storage in facilitating flexible adjustments in microgrids, this study developed a composite weight-TODIM (an acronym in Portuguese for interactive and multi-criteria decision making) model for assessing the utility of energy storage that incorporates heterogeneity in the risk preferences. This model enabled a comparative analysis of the utility of energy storage technology across multiple scenarios, taking the risk preferences of decision-makers into account, thereby providing strategic insights for the application of multi-temporal energy storage in microgrids. The feasibility and effectiveness of the model were validated through a case study analysis.

Convolutional Long Short-Term Memory (ConvLSTM)-Based Prediction of Voltage Stability in a Microgrid

The maintenance of an uninterrupted electricity supply to meet demand is of paramount importance for maintaining the stable operation of an electrical power system. Machine learning and deep learning play a crucial role in maintaining that stable operation. These algorithms have the ability to acquire knowledge from past data, enabling them to efficiently identify and forecast potential scenarios of instability in the future. This work presents a hybrid convolutional long short-term memory (ConvLSTM) technique for training and predicting nodal voltage stability in an IEEE 14-bus microgrid. Analysis of the findings shows that the suggested ConvLSTM model exhibits the highest level of precision, reaching a value of 97.65%. Furthermore, the ConvLSTM model has been shown to perform better compared to alternative machine learning and deep learning models such as convolutional neural networks, k-nearest neighbors, and support vector machine models, specifically in terms of accurately forecasting voltage stability. The IEEE 14-bus system tests indicate that the suggested method can quickly and accurately determine the stability status of the system. The comparative analysis obtained the results and further justified the efficiency and voltage stability of the proposed model.

Prediction of wind and PV power by fusing the multi-stage feature extraction and a PSO-BiLSTM model

Accurate prediction of wind and photovoltaic (PV) power is essential to ensure the stable operation of power systems. However, the conventional power prediction methods face the challenges in capturing the stochastic fluctuations of wind and PV power. A wind and PV power prediction method fusing the multi-stage feature extraction and a particle swarm optimization (PSO)-bidirectional long and short-term memory (BiLSTM) model is developed. To illustrate the oscillation and instability of wind and PV power, the symplectic geometry model decomposition (SGMD) is presented to decompose the feature data and obtain multiple feature sub-sequences. Due to the excessive feature decomposition using the conventional methods, such as empirical modal decomposition, the kernel principal component analysis is utilized to reduce the dimensionality of the nonlinear sub-sequences of the wind and PV power. Compared to the traditional LSTM that ignores the inverse-time correlation between power and meteorological features and is sensitive to the model hyper-parameters, a power prediction model based on PSO-BiLSTM is developed. Using the power data from a power station in Xinjiang Province, China, as an example, the experimental results show that wind and PV power can be accurately forecasted using the developed method with high prediction accuracies of 97.9 % and 98.5 %, respectively.

Self‐paced learning long short‐term memory based on intelligent optimization for robust wind power prediction

AbstractGiven the unpredictable and intermittent nature of wind energy, precise forecasting of wind power is crucial for ensuring the safe and stable operation of power systems. To reduce the influence of noise data on the robustness of wind power prediction, a wind power prediction method is proposed that leverages an enhanced multi‐objective sand cat swarm algorithm (MO‐SCSO) and a self‐paced long short‐term memory network (spLSTM). First, the actual wind power data is processed into time series as input and output. Then, the progressive advantage of self‐paced learning is used to effectively solve the instability caused by noisy data during long short‐term memory network (LSTM) training. Following this, the improved MO‐SCSO is employed to iteratively optimize the hyperparameters of spLSTM. Ultimately, a combined MO‐SCSO‐spLSTM model is constructed for wind power prediction. This model is validated with the data of onshore wind farms in Austria and offshore wind farms in Denmark. The experimental results show that compared with the traditional LSTM prediction method, the proposed method has better prediction accuracy and robustness. Specifically, in the onshore and offshore wind power prediction experiments, the proposed method reduces the minimum MAE by 5.44% and 4.96%, respectively, and reduces the MAE range by 4.45% and 17.21%, respectively, which could be conducive to the safe and stable operation of power system.

Construction and Optimization of Power Quality Risk Spillover Trend Prediction Model Based on Deep Learning

This study aims to establish and refine a deep learning-based predictive model for power quality risk spillover trends, thereby addressing the challenges posed by the escalating diversity and adaptability of power systems in the evolution of the renewable energy industry. Initially, the study introduces the concept of power quality risk spillover, referring to the influence exerted by power quality issues in one region on other regions. This influence initiates a chain reaction, ultimately leading to a more widespread deterioration in power quality. Then, the advantages and applications of the deep learning model in power quality risk spillover trend prediction are expounded. During the model development process, we employed deep learning algorithms such as the multilayer perceptron and extended short-term memory network, tailored specifically to the unique characteristics of power quality data. To enhance the model's predictive accuracy and stability, we implemented optimization strategies encompassing data preprocessing, feature engineering, and model integration. Our experimental findings demonstrate that the optimized model exhibits remarkable precision and stability in anticipating power quality risk spillover trends, thereby offering robust support for risk management and ensuring the stable operation of power systems. This study provides a valuable exploration and practice for the application and development of a power quality risk spillover trend prediction model based on deep learning.

Stochastic economic model predictive control for renewable energy and ancillary services trading with storage

The provision of renewable-based ancillary services (AS) is paramount for the stable operation of power systems featuring high renewable penetration. The combined operation of storage with renewables enables aggregators to increase the reliability of their energy and frequency control AS offers. Existing dispatch strategies for the supply of both energy and AS are usually rule-based or involve tracking a technical reference signal, hence economically suboptimal for aggregators. This study proposes a comprehensive decision framework in which first a stochastic optimization derives bids on energy and AS markets, then stochastic economic model predictive control (SEMPC) optimizes the storage dispatch in order to maximize the profit and minimize the storage degradation, as a function of the predicted renewable production and the expected AS activation. The framework is applied to a real-world case study where storage combined with wind power participates in the energy market, the frequency containment market and the frequency restoration reserve market. The SEMPC-based approach increases market revenue by 15% compared to a standard reference-tracking MPC, and reduces storage degradation by 23%. The stochastic formulation lowers the sensitivity of the economic objectives to renewable energy forecast errors, compared to deterministic approaches.

An Algorithm for Calculating the Parameter Selection Area of a Doubly-Fed Induction Generator Based on the Guardian Map Method

Large-scale wind farms incorporating doubly-fed induction generators (DFIGs) are considered a promising direction for modern energy supply systems due to their role in reducing dependence on fossil energy sources. However, the dynamic interactions between DFIGs and AC grids sometimes lead to sub-synchronous oscillation (SSO) that threatens the safe and stable operation of wind power systems. Therefore, it is essential to develop a mathematical model and design an algorithm to quantitatively design the control parameters. Such algorithms are helpful in preventing or mitigating system stability problems coming from wind power connected to the grid and reducing damage to power equipment. The traditional state-space model is mainly established to determine the stable operating point and analyze the influence of parameters on the system operating mode. However, this method does not provide the selection area for the system parameters. To address this shortcoming, this paper introduces a modular state-space model for DFIGs containing series compensation lines and proposes an algorithm for calculating the parameter selection area based on the Guardian map method. First, a detailed modular state-space model based on the virtual synchronous generator (VSG) control is established. The modular model helps to reflect the relationship between state variables and focuses on describing the operating state of DFIGs in wind farms. Second, this paper focuses on the influence of VSG control parameters and compensation capacitance on SSO. It aims to clarify the role of the series compensation level and control parameters on SSO based on VSG control. Then, an algorithm for the parameter selection area based on the Guardian map is proposed and the area of the VSG-controlled DFIG is obtained. Finally, the accuracy and validity of the algorithm are verified by time domain simulation in MATLAB/Simulink and HIL experiment.

Short‐term electric load forecasting based on empirical wavelet transform and temporal convolutional network

AbstractShort‐term load forecasting is the basis of power system operation and analysis and is of great significance for the stable operation of power systems. To solve the problems of insufficient mining of the intrinsic information of load data, randomness, and non‐linearity, and to improve the accuracy of load prediction, the authors propose a short‐term power load prediction model based on empirical wavelet transform (EWT) decomposition and the temporal convolutional network (TCN). First, the Pearson coefficient is used to eliminate the less relevant influencing factors to reduce the complexity of the model. Then, the EWT algorithm is used to decompose the original load signal to fully exploit the load data time domain and frequency domain information, while solving the problems of non‐linearity and randomness. Finally, the decomposed subsequences are input to the TCN network for prediction superposition to obtain the final results. The experimental results show that, compared with the single models TCN, gated recurrent units (GRU), and long short‐term memory (LSTM), and the hybrid models EWT‐GRU, EWT‐LSTM, and VMD‐TCN, the R2 of the short‐term power load forecasting model based on EWT‐TCN is improved by 0.2099%, 0.2519%, 0.3453%, 0.0334%, 0.1766%, and 0.1228%, respectively.

A novel wind power deterministic and interval prediction framework based on the critic weight method, improved northern goshawk optimization, and kernel density estimation

Wind power prediction holds significant importance for the stable operation of power systems and the enhancement of energy utilization efficiency. Interval prediction, capable of providing more uncertain information, has garnered widespread attention. In this study we have designed a hybrid prediction framework for both deterministic and interval prediction. Initially, the original wind power data undergo cleaning using the quartile method and the fuzzy C-means (FCM) clustering algorithm. This approach not only eliminates scattered outliers but also identifies concentrated outliers more effectively. Subsequently, five distinct single prediction models were employed for point predictions. The critic weight method was applied to yield point forecasting results with higher prediction accuracy. Nonparametric kernel density estimation (KDE) and normal distribution (ND) were incorporated to calculate the prediction interval (PI) under varying confidence levels. Finally, an improved northern goshawk optimization (INGO) algorithm was proposed, integrating three enhancement methods: levy flight, sinusoidal mapping, and a reverse learning strategy. This optimization aims to fine-tune the weight coefficients of the aforementioned two interval prediction methods. The resulting PI overcomes the limitations of a single-interval prediction model. To effectively demonstrate the forecasting performance of the proposed prediction framework, two datasets from a wind turbine in northwest China were selected for simulation verification. In deterministic prediction, the designed hybrid forecast model demonstrates a reduction in root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE) by 8.5%, 16.98%, and 11.49%, respectively, compared to other single prediction models. In interval prediction, the prediction interval coverage probability (PICP) is enhanced, while the prediction interval normalized average width (PINAW) is effectively reduced. The designed interval prediction model can reduce the comprehensive evaluation index coverage width-based criterion (CWC) by 10.51%, 9.62%, and 12.95% on average at 95%, 90%, and 80% confidence levels, respectively. Simulation results verified the validity and feasibility of the proposed prediction framework.

Research on Building Power Quality Assessment and Control Technology Based on Online Monitoring

This study is to improve the assessment accuracy and control efficiency of building power quality by adopting online monitoring and integrating multiple technical indicators and control methods. A whole set of power quality technical index system is developed in the study, involving voltage deviation, harmonic voltage/current limit, and so on. The power quality indicators are quantitatively evaluated through standardization and weight determination. The assessment results show that the measured power quality indicators vary within the interval of 0 to 9, which verifies the effectiveness of the assessment system. In terms of control technology, this paper discusses in depth the static reactive power compensation (SVC) device and its role in improving building power quality, and confirms its efficacy in optimizing power quality through simulation experiments. This work not only successfully evaluates the building power quality, but also proposes practical control strategies, which provide theoretical and practical guidance for the stable operation of power systems and the further improvement of power quality.

Ultra-short-term wind power forecasting based on feature weight analysis and cluster dynamic division

Accurate and reliable ultra-short-term wind power forecasting (WPF) is of great significance to the safe and stable operation of power systems, but the current research is difficult to balance the prediction accuracy, timeliness, and applicability at the same time. Therefore, this paper proposes a ultra-short-term WPF model based on feature weight analysis and cluster dynamic division. The model introduces an analytic hierarchy process and an entropy weight method to analyze the subjective and objective weight of the influencing features of wind power, respectively, then the subjective and objective weight ratio is determined by the quantum particle swarm optimization (QPSO) algorithm to obtain a more reasonable comprehensive weight of each feature. On this basis, it uses the K-Medoids algorithm to dynamically divide the wind power clusters into class regions by cycles. Then, the class region is used as the prediction unit to establish the TCN-BiLSTM model based on temporal convolutional networks (TCN) and bi-directional long short-term memory (BiLSTM) for training and prediction and optimizes the hyper-parameters of the model by the QPSO algorithm. Finally, the regional predictions are summed to obtain the final ultra-short-term power prediction. In addition, in order to verify the performance of the model, the actual operation data of a power field in Xinjiang, China, are selected for the example validation. The results show that the proposed model can ensure the prediction accuracy while minimizing the training time of the model and outperforms other existing methods in terms of prediction accuracy, timeliness, and applicability.

A Refined Wind Power Forecasting Method with High Temporal Resolution Based on Light Convolutional Neural Network Architecture

With a large proportion of wind farms connected to the power grid, it brings more pressure on the stable operation of power systems in shorter time scales. Efficient and accurate scheduling, operation control and decision making require high time resolution power forecasting algorithms with higher accuracy and real-time performance. In this paper, we innovatively propose a high temporal resolution wind power forecasting method based on a light convolutional architecture—DC_LCNN. The method starts from the source data and novelly designs the dual-channel data input mode to provide different combinations of feature data for the model, thus improving the upper limit of the learning ability of the whole model. The dual-channel convolutional neural network (CNN) structure extracts different spatial and temporal constraints of the input features. The light global maximum pooling method replaces the flat operation combined with the fully connected (FC) forecasting method in the traditional CNN, extracts the most significant features of the global method, and directly performs data downscaling at the same time, which significantly improves the forecasting accuracy and efficiency of the model. In this paper, the experiments are carried out on the 1 s resolution data of the actual wind field, and the single-step forecasting task with 1 s ahead of time and the multi-step forecasting task with 1~10 s ahead of time are executed, respectively. Comparing the experimental results with the classical deep learning models in the current field, the proposed model shows absolute accuracy advantages on both forecasting tasks. This also shows that the light architecture design based on simple deep learning models is also a good solution in performing high time resolution wind power forecasting tasks.

Research on the new power system dispatching model considering clean energy market and power‐section stabilization

AbstractWith the introduction of dual carbon targets, clean energy is connected to the grid on a large scale, and the stochastic and volatility of its output further affects the stable operation of the new power system. Meanwhile, in order to solve the problem that it is difficult to take into account the participation of clean energy in market‐oriented trading and complete consumption in the construction of power market, the new type of power system source–load balance dispatching model considering the market of clean energy and cross‐section stabilization is proposed. Firstly, a clean energy market price competition model based on the market clearing mechanism is proposed to realize the alternative consumption of clean energy. Secondly, considering the section security of inter‐system power transmission, a new power system source‐load balance two‐level optimization model is established by considering the cross‐section power rate and real‐time trading of clean energy market. Finally, the advantages of the model in enhancing the high proportion of clean energy consumption, rationally clearing the clean energy market and reducing the cross‐section load ratio of the contact line are verified through simulation.