New energy distribution network intelligent regulation and control method and system based on twinborn simulation

Abstract

The invention discloses a new energy distribution network intelligent regulation and control method and system based on twinborn simulation, and relates to the technical field of distribution network intelligent regulation and control, and the method comprises the steps: connecting a regional distribution network, and receiving a distribution network regulation and control scheme of a future time zone; carrying out twinborn simulation to obtain a distribution network simulation data stream; a distribution network risk analysis dual channel is introduced, and multi-dimensional risk analysis is carried out; performing optimization compensation to obtain a first result of new energy distribution network optimization; performing interference analysis to obtain a distribution network passive interference analysis result; and performing compensation optimization to obtain a second new energy distribution network optimization result. According to the invention, the technical problem of low new energy distribution network regulation and control safety and efficiency caused by insufficient simulation and optimization of a regional power distribution network regulation and control scheme in the prior art is solved, and simulation and optimization of the regional power distribution network regulation and control scheme containing new energy and conventional energy are realized through twin simulation. And the safety and efficiency of new energy distribution network regulation and control are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control of distribution networks, and specifically to a method and system for intelligent control of new energy distribution networks based on twin simulation. Background Art

[0002] As the penetration rate of new energy in distribution networks continues to increase, the regional distribution network structure, which includes new energy distribution networks and conventional energy distribution networks, is becoming increasingly complex. Traditional distribution network control methods are unable to effectively deal with the risks brought about by fluctuations in new energy output and access shocks. In addition, there is a lack of comprehensive risk analysis and optimization methods for situations where abnormalities and failures in conventional energy distribution networks affect new energy distribution networks, resulting in low security and efficiency in distribution network control.

[0003] The existing technology has insufficient simulation and optimization of regional distribution network control schemes, resulting in technical problems such as low safety and efficiency of new energy distribution network control. Summary of the Invention

[0004] This application provides a method and system for intelligent control of new energy distribution networks based on twin simulation, which is used to solve the technical problem that the existing technology lacks simulation and optimization of regional distribution network control schemes, resulting in low safety and efficiency of new energy distribution network control.

[0005] In view of the above problems, this application provides a new energy distribution network intelligent control method and system based on twin simulation.

[0006] The first aspect of the present application provides a method for intelligent control of a new energy distribution network based on twin simulation, the method comprising: Connect to the regional distribution network and receive the distribution network control plan for the future time zone, wherein the regional distribution network includes a new energy distribution network and a conventional energy distribution network; perform twin simulation on the regional distribution network according to the distribution network control plan to obtain a distribution network simulation data stream; introduce a dual channel for distribution network risk analysis, and perform multi-dimensional risk analysis on the new energy distribution network and the conventional energy distribution network respectively in combination with the distribution network simulation data stream to obtain a first distribution network risk matrix and a second distribution network risk matrix; optimize and compensate the new energy distribution network control plan within the distribution network control plan according to the first distribution network risk matrix to obtain a first result of new energy distribution network optimization; perform interference analysis on the new energy distribution network according to the second distribution network risk matrix to obtain a distribution network passive interference analysis result; perform compensation optimization on the first result of new energy distribution network optimization according to the distribution network passive interference analysis result to obtain a second result of new energy distribution network optimization.

[0007] In one possible implementation method, the first distribution network risk analysis channel embedded in the distribution network risk analysis dual channel is activated, and the first distribution network risk analysis channel includes the output fluctuation risk prediction model, power supply quality risk prediction model and access impact risk prediction model corresponding to the new energy distribution network; the new energy distribution network simulation data is input into the output fluctuation risk prediction model to obtain the output fluctuation risk coefficient; the new energy distribution network simulation data is input into the power supply quality risk prediction model to obtain the power supply quality risk coefficient; the new energy distribution network simulation data is input into the access impact risk prediction model to obtain the access impact risk coefficient, and the first distribution network risk matrix is ​​constructed in combination with the output fluctuation risk coefficient and the power supply quality risk coefficient.

[0008] In one possible implementation, the second distribution network risk analysis channel embedded in the distribution network risk analysis dual channel is activated, and the second distribution network risk analysis channel includes a distribution network anomaly detection model and a distribution network fault risk prediction model corresponding to the conventional energy distribution network; conventional energy distribution network simulation data is input into the distribution network anomaly detection model to obtain a distribution network anomaly detection result; the distribution network anomaly detection result is input into the distribution network fault risk prediction model to obtain a distribution network fault risk prediction result, and the distribution network anomaly detection result is combined with the matrix to generate the second distribution network risk matrix.

[0009] In one possible implementation, according to the new energy distribution network risk factors, new energy distribution network risk constraints are set, and the new energy distribution network risk factors include output fluctuation risk, power supply quality risk and access impact risk; if the first distribution network risk matrix does not meet the new energy distribution network risk constraints, the new energy distribution network control plan is adjusted according to the new energy distribution network risk constraints to obtain a first new energy distribution network control group; weights are allocated according to the new energy distribution network risk factors to obtain a global distribution network risk analysis function; global distribution network risk optimization is performed on the first new energy distribution network control group according to the global distribution network risk analysis function to establish a second new energy distribution network control group; distribution network control efficiency maximization optimization is performed according to the second new energy distribution network control group to generate the first new energy distribution network optimization result.

[0010] In one possible implementation, adjustments are made according to the new energy distribution network regulation and control plan to obtain a new energy distribution network regulation decision set, wherein each new energy distribution network regulation decision in the new energy distribution network regulation decision set meets the new energy distribution network task in the future time zone; the Pth new energy distribution network regulation decision is extracted according to the new energy distribution network regulation decision set, where P is a positive integer; twin simulation is performed on the new energy distribution network according to the Pth new energy distribution network regulation decision to obtain Pth decision distribution network simulation data; the Pth decision distribution network simulation data is input into the first channel of distribution network risk analysis to obtain a Pth distribution network risk analysis result; if the Pth distribution network risk analysis result meets the new energy distribution network risk constraint, the Pth new energy distribution network regulation decision is set as the Pth distribution network optimization strategy, and the Pth distribution network optimization strategy is added to the first regulation group of the new energy distribution network.

[0011] In one possible implementation, the distribution network risk analysis results corresponding to each distribution network optimization strategy within the first regulation group of the new energy distribution network are input into the global distribution network risk analysis function to obtain each global distribution network risk coefficient; it is determined whether each global distribution network risk coefficient is less than a global distribution network risk threshold to obtain each global distribution network risk judgment result; and the first regulation group of the new energy distribution network is optimized and screened according to the each global distribution network risk judgment result to generate the second regulation group of the new energy distribution network.

[0012] In one possible implementation, a propagation prediction is performed on the second distribution network risk matrix according to the regional distribution network model to obtain a distribution network risk propagation prediction result; a grid-connected fluctuation interference analysis is performed on the new energy distribution network according to the distribution network risk propagation prediction result to obtain a grid-connected fluctuation interference feature; a power supply quality interference analysis is performed on the new energy distribution network according to the distribution network risk propagation prediction result to obtain a power supply quality interference feature; a fault interference analysis is performed on the new energy distribution network according to the distribution network risk propagation prediction result to obtain a distribution network fault interference feature; and the grid-connected fluctuation interference feature, the power supply quality interference feature and the distribution network fault interference feature are integrated to generate the distribution network passive interference analysis result.

[0013] In one possible implementation, three-dimensional modeling is performed based on the regional distribution network to obtain a regional distribution network model; the regional distribution network model is simulated and regulated according to the distribution network regulation plan to obtain a distribution network simulation data set; the distribution network simulation data set is cleaned and sorted to obtain the distribution network simulation data stream, which includes new energy distribution network simulation data and conventional energy distribution network simulation data.

[0014] In one possible implementation, the distribution network control plan includes the new energy distribution network control plan and the conventional energy distribution network control plan corresponding to the conventional energy distribution network.

[0015] The second aspect of the present application provides a new energy distribution network intelligent control system based on twin simulation, the system comprising: A distribution network control scheme receiving module is used to connect to the regional distribution network and receive the distribution network control scheme for the future time zone, wherein the regional distribution network includes a new energy distribution network and a conventional energy distribution network; a distribution network simulation data stream acquisition module is used to perform twin simulation of the regional distribution network according to the distribution network control scheme to obtain a distribution network simulation data stream; a multi-dimensional risk analysis module is used to introduce a dual-channel distribution network risk analysis, and perform multi-dimensional risk analysis on the new energy distribution network and the conventional energy distribution network respectively in combination with the distribution network simulation data stream to obtain a first distribution network risk matrix and a second distribution network risk matrix; an optimal compensation module is used to perform optimal compensation for the new energy distribution network control scheme within the distribution network control scheme according to the first distribution network risk matrix to obtain a first result of new energy distribution network optimization; an interference analysis module is used to perform interference analysis on the new energy distribution network according to the second distribution network risk matrix to obtain a distribution network passive interference analysis result; a compensation optimization module is used to perform compensation optimization on the first result of new energy distribution network optimization according to the distribution network passive interference analysis result to obtain a second result of new energy distribution network optimization.

[0016] One or more technical solutions provided in this application have at least the following technical effects or advantages: Connect to the regional distribution network and receive the distribution network control plan for the future time zone; perform twin simulation on the regional distribution network to obtain a distribution network simulation data stream; introduce a dual channel for distribution network risk analysis, and perform multi-dimensional risk analysis on the new energy distribution network and the conventional energy distribution network in combination with the distribution network simulation data stream to obtain a first distribution network risk matrix and a second distribution network risk matrix; optimize and compensate the new energy distribution network control plan within the distribution network control plan based on the first distribution network risk matrix to obtain a first result of new energy distribution network optimization; perform interference analysis on the new energy distribution network to obtain a distribution network passive interference analysis result; perform compensation optimization on the first result of new energy distribution network optimization to obtain a second result of new energy distribution network optimization. This achieves the technical effect of simulating and optimizing the regional distribution network control plan containing new energy and conventional energy through twin simulation, thereby improving the safety and efficiency of new energy distribution network control. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1A schematic diagram of the process flow of the intelligent control method for the new energy distribution network based on twin simulation provided in an embodiment of the present application; Figure 2 Schematic diagram of the structure of the new energy distribution network intelligent control system based on twin simulation provided in the embodiment of this application.

[0019] Description of the accompanying symbols: distribution network control plan receiving module 10, distribution network simulation data flow acquisition module 20, multi-dimensional risk analysis module 30, optimization compensation module 40, interference analysis module 50, compensation optimization module 60. DETAILED DESCRIPTION

[0020] This application provides a new energy distribution network intelligent control method and system based on twin simulation, which is used to solve the technical problem that the existing technology lacks simulation and optimization of regional distribution network control schemes, resulting in low safety and efficiency of new energy distribution network control.

[0021] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative work are within the scope of protection of this application.

[0022] Example 1, as Figure 1 As shown, the present application provides a new energy distribution network intelligent control method based on twin simulation, the method comprising: Step S100: connecting to a regional distribution network and receiving a distribution network control plan for a future time zone, wherein the regional distribution network includes a new energy distribution network and a conventional energy distribution network.

[0023] Specifically, a connection is established with the regional distribution network including new energy distribution networks and conventional energy distribution networks through the communication interface, and the distribution network control plan for the future time zone (such as 08:00-10:00 the next day) is received based on the time series scheduling protocol. The plan covers new energy distribution network control plans (such as photovoltaic power station output adjustment plans, energy storage charging and discharging strategies) and conventional energy distribution network control plans (such as coal-fired power plant output instructions, transformer tap adjustment parameters), and performs format check and integrity verification on the control plan to ensure that the data complies with the IEC61970 standard specifications, providing an accurate initial control instruction set for subsequent twin simulation.

[0024] Step S200: Perform twin simulation on the regional distribution network according to the distribution network control plan to obtain a distribution network simulation data stream.

[0025] Specifically, a three-dimensional model is first constructed based on the regional distribution network's topology, equipment parameters, and operating rules. This model accurately reflects the characteristics of the actual distribution network. This model includes components such as photovoltaic arrays and energy storage devices in the renewable energy distribution network, as well as transformers and transmission lines in the conventional energy distribution network. Next, various control instructions from the received distribution network control plan (such as output regulation parameters for renewable energy power generation equipment and operating state switching instructions for conventional power sources) are input into the regional distribution network model. Simulation control is then performed on the model to simulate the distribution network's operation under the future time zone control plan. This generates a distribution network simulation dataset containing information such as equipment operating parameters and grid power flow distribution. Finally, according to pre-set data cleaning rules, the distribution network simulation dataset is denoised and formatted uniformly to remove outliers and redundant data. This results in a distribution network simulation data stream containing both renewable energy and conventional energy distribution network simulation data, providing reliable data support for subsequent risk analysis and control plan optimization.

[0026] Step S300: introducing a dual channel for distribution network risk analysis, and performing multi-dimensional risk analysis on the new energy distribution network and the conventional energy distribution network respectively in combination with the distribution network simulation data stream to obtain a first distribution network risk matrix and a second distribution network risk matrix.

[0027] Specifically, the system activates the dual distribution network risk analysis channels embedded in the system, leveraging distribution network simulation data streams to conduct multi-dimensional risk analysis for both new energy and conventional energy distribution networks. For new energy distribution networks, the first distribution network risk analysis channel is activated. This channel integrates the output fluctuation risk prediction model, the power supply quality risk prediction model, and the access impact risk prediction model. The new energy distribution network simulation data is fed into each model, and the output fluctuation risk coefficient, power supply quality risk coefficient, and access impact risk coefficient are calculated. Based on these three risk coefficients, a first distribution network risk matrix is ​​constructed to represent the risk distribution of the new energy distribution network. For conventional energy distribution networks, the second distribution network risk analysis channel is activated, encompassing a distribution network anomaly detection model and a distribution network fault risk prediction model. The conventional energy distribution network simulation data is first fed into the distribution network anomaly detection model to obtain distribution network anomaly detection results, such as voltage over-limit and current imbalance. These results are then fed into the distribution network fault risk prediction model to obtain a predicted fault probability. Combined with the anomaly detection results, this is matrixed to generate a second distribution network risk matrix reflecting the potential risks of the conventional energy distribution network.

[0028] Step S400: performing optimal compensation on the new energy distribution network control scheme within the distribution network control scheme according to the first distribution network risk matrix to obtain a first result of the new energy distribution network optimization.

[0029] Specifically, risk constraints for the new energy distribution network are set based on three risk factors: output fluctuation risk, power quality risk, and access shock risk. If the first distribution network risk matrix fails to meet these risk constraints, the new energy distribution network control plan is adjusted to generate a new energy distribution network regulation decision set that meets the new energy distribution network requirements for the future time zone. From this decision set, the Pth decision (P is a positive integer) is extracted. A twin simulation of the new energy distribution network is performed to obtain the Pth decision distribution network simulation data, which is input into the first channel of the distribution network risk analysis. If the Pth distribution network risk analysis result meets the risk constraints, the decision is set as the Pth distribution network optimization strategy and added to the first regulation group of the new energy distribution network. Subsequently, a global distribution network risk analysis function is constructed by assigning weights to each risk factor based on its importance. The distribution network risk analysis results corresponding to each distribution network optimization strategy within the first regulation group are input into this function to calculate the global distribution network risk coefficient. By judging whether each coefficient is less than the global distribution network risk threshold, the first regulation group is optimized and screened to generate the second regulation group of the new energy distribution network. Finally, the second regulation group is optimized to maximize the distribution network control efficiency, thereby generating the first result of the new energy distribution network optimization.

[0030] Step S500: performing interference analysis on the new energy distribution network according to the second distribution network risk matrix to obtain a distribution network passive interference analysis result.

[0031] Specifically, a propagation prediction of the second distribution network risk matrix was first conducted based on the regional distribution network model. The transmission path of risks from the conventional energy distribution network to the new energy distribution network was simulated, resulting in a distribution network risk propagation prediction result. Based on this result, interference analysis of the new energy distribution network was conducted from three dimensions: First, a grid-connection fluctuation interference analysis was conducted to analyze the impact of voltage fluctuations and frequency offsets caused by abnormalities in the conventional energy distribution network on the grid-connection stability of the new energy distribution network, and to extract the grid-connection fluctuation interference characteristics. Second, a power supply quality interference analysis was conducted to study the interference of harmonic distortion, voltage sag, and other factors caused by faults in the conventional energy distribution network on the power supply quality of the new energy distribution network, and to obtain the power supply quality interference characteristics. Third, a fault interference analysis was conducted to predict the cascading failure risk caused by faults in the conventional energy distribution network on the new energy distribution network through the grid topology, and to obtain the distribution network fault interference characteristics. Finally, the three types of interference characteristics were integrated and analyzed to generate a distribution network passive interference analysis result that comprehensively reflects the passive interference impact of the conventional energy distribution network on the new energy distribution network, providing a basis for subsequent compensation optimization.

[0032] Step S600: performing compensation optimization on the first result of the new energy distribution network optimization according to the distribution network passive interference analysis result to obtain a second result of the new energy distribution network optimization.

[0033] Specifically, based on the obtained results of the passive interference analysis of the distribution network, the impact of the grid-connected fluctuation interference characteristics, power supply quality interference characteristics, and distribution network fault interference characteristics on the operation of the new energy distribution network is comprehensively considered, and the first result of the new energy distribution network optimization is compensated and optimized. In response to the fluctuations in new energy output that may be caused by the risk propagation of conventional energy distribution networks, the charging and discharging strategies of the energy storage device are adjusted to smooth out the fluctuations; in response to power supply quality interference, the control parameters of the new energy inverter are optimized to improve the harmonic resistance capability; in response to the risk of fault interference, a fault isolation and reconstruction strategy is added to the new energy distribution network control scheme. By converting passive interference factors into constraints on the control parameters, the control strategy in the first optimization result is iteratively corrected, and finally a second result of the new energy distribution network optimization is generated that takes into account both active risk prevention and control and passive interference adaptation, ensuring that the control scheme can still maintain stable operation under abnormal conditions of the conventional energy distribution network.

[0034] In one possible implementation, step S100 further includes: Step S110: The distribution network control plan includes the new energy distribution network control plan and the conventional energy distribution network control plan corresponding to the conventional energy distribution network.

[0035] Specifically, the distribution network control plan consists of two parts: the first is a new energy distribution network control plan developed for new energy distribution networks. This plan primarily addresses output control of new energy generation equipment, charging and discharging strategies for energy storage systems, and the operation of new energy grid-connected switches, ensuring efficient absorption and stable integration of new energy. The second is a conventional energy distribution network control plan for conventional energy distribution networks. This plan includes control measures such as output scheduling of conventional generators, transformer tap adjustment, and switching on and off of reactive power compensation equipment to ensure the safe and stable operation of conventional energy distribution networks. Together, these two types of control plans constitute a complete regional distribution network control strategy, enabling coordinated and optimized control of the entire regional distribution network.

[0036] In one possible implementation, step S200 further includes: Step S210: Perform three-dimensional modeling based on the regional distribution network to obtain a regional distribution network model.

[0037] Step S220: performing simulation control on the regional distribution network model according to the distribution network control plan to obtain a distribution network simulation data set.

[0038] Step S230: cleaning and combing the distribution network simulation data set to obtain the distribution network simulation data stream, which includes new energy distribution network simulation data and conventional energy distribution network simulation data.

[0039] Specifically, 3D modeling software (such as AutoCAD, PSCAD / EMTDC, etc.) is used to accurately model the topological structure, equipment spatial layout and electrical connection relationship of the regional distribution network based on the electrical wiring diagram, equipment parameters (such as transformer capacity, line impedance, characteristics of new energy power generation equipment, etc.) and geographic information of the regional distribution network. A 3D regional distribution network model that can reflect the physical and operating characteristics of the actual distribution network is constructed, providing an accurate digital twin foundation for subsequent simulation and regulation.

[0040] Using power system simulation software (such as DIgSILENT, MATLAB / Simulink, etc.), various control instructions in the distribution network control plan (such as renewable energy power generation output adjustment, energy storage system charging and discharging control, conventional power output scheduling, etc.) are input into the constructed regional distribution network model to simulate the operating status of the regional distribution network under different control strategies in future time zones. Electrical quantity data such as node voltage, line current, power flow, equipment load, etc. are collected to form a distribution network simulation data set containing various operating scenarios, providing rich simulation data support for subsequent data cleaning and risk analysis.

[0041] Data cleaning algorithms (such as outlier detection based on statistical analysis, missing value interpolation, etc.) are used to process the distribution network simulation data set, eliminate abnormal data caused by simulation errors, fill in missing data, and standardize and normalize the data. According to the classification standards of new energy distribution networks and conventional energy distribution networks, the cleaned valid data are sorted into new energy distribution network simulation data and conventional energy distribution network simulation data, and finally a structurally standardized distribution network simulation data stream is formed to provide high-quality data support for subsequent multi-dimensional risk analysis.

[0042] In one possible implementation, step S300 further includes: Step S310: activating the first distribution network risk analysis channel embedded in the distribution network risk analysis dual-channel, wherein the first distribution network risk analysis channel includes an output fluctuation risk prediction model, a power supply quality risk prediction model, and an access impact risk prediction model corresponding to the new energy distribution network.

[0043] Step S320: inputting the new energy distribution network simulation data into the output fluctuation risk prediction model to obtain the output fluctuation risk coefficient.

[0044] Step S330: inputting the new energy distribution network simulation data into the power supply quality risk prediction model to obtain a power supply quality risk coefficient.

[0045] Step S340: Inputting the new energy distribution network simulation data into the access impact risk prediction model to obtain the access impact risk coefficient, and constructing the first distribution network risk matrix in combination with the output fluctuation risk coefficient and the power supply quality risk coefficient.

[0046] Specifically, the first distribution network risk analysis channel embedded in the dual distribution network risk analysis channel is activated. This channel integrates three types of risk prediction models built for the characteristics of new energy distribution networks: the output fluctuation risk prediction model is based on the historical operating data and real-time monitoring parameters of new energy power generation equipment (such as photovoltaic and wind power), combined with meteorological forecast data, to dynamically evaluate the risk of unstable output caused by changes in natural conditions or equipment performance degradation; the power supply quality risk prediction model predicts possible power supply quality problems such as voltage deviation, frequency fluctuation or harmonic exceeding the standard by analyzing the voltage, current waveform and harmonic components of the new energy access point; the access impact risk prediction model targets the new energy grid connection or expansion scenario, and simulates its instantaneous impact effect on the distribution of distribution network current, short-circuit capacity and voltage stability. The three together constitute a risk assessment system covering the entire operation link of the new energy distribution network.

[0047] Cleaned and sorted simulation data for the renewable energy distribution network (including real-time output power of photovoltaic / wind power equipment, historical output series, and meteorological data for the corresponding time period, such as sunlight intensity, wind speed and direction, and equipment operating status parameters) is input into the output fluctuation risk prediction model. Based on a hybrid LSTM-GARCH algorithm, the model first uses a long short-term memory (LSTM) network to learn the temporal features of the input data, capturing the dependencies and changing trends of renewable energy output over time, and then predicting output values ​​for future time periods. Simultaneously, the generalized autoregressive conditional heteroskedasticity (GARCH) model is used to analyze the conditional variance of output fluctuations and characterize the time-varying characteristics of fluctuations. The model calculates the degree of deviation between the predicted output and the actual simulated data, and, in combination with historical fluctuation patterns and the uncertainty of current meteorological conditions, outputs a risk coefficient that characterizes the degree of renewable energy output fluctuation. This coefficient reflects the likelihood and magnitude of deviation from expectations under the current regulation plan, providing key output fluctuation risk assessment data for the subsequent construction of the first distribution network risk matrix.

[0048] Simulated data from the new energy distribution network (including node voltage amplitude / phase, current waveforms, and active / reactive power) is fed into the power supply quality risk prediction model. This model, based on an improved S-transform and fuzzy analytic hierarchy process (AHP), first decomposes the voltage / current signals in the time-frequency domain using the S-transform to extract characteristic parameters such as harmonic distortion (e.g., 2nd-50th harmonic content), voltage sag duration / amplitude, and frequency offset. The AHP then constructs a risk assessment matrix, comparing these characteristic parameters with national standard limits (e.g., GB / T14549-1993) and standardizing them. A membership function is used to calculate the risk membership of each parameter. This is then weighted and summed using expert-preset weight vectors (e.g., 0.4 for harmonic distortion, 0.35 for voltage sag, and 0.25 for frequency offset) to generate a power quality risk coefficient ranging from 0 to 1. Larger values ​​indicate higher risks of voltage deviation and harmonic overshoot, providing a quantitative assessment basis for the power supply quality dimension of the primary distribution network risk matrix.

[0049] Simulated data from the new energy distribution network (covering new energy grid connection topology parameters, equipment rated capacity, load distribution characteristics, and short-circuit current baseline values) is fed into the access impact risk prediction model. This model uses a short-circuit current sensitivity algorithm based on power flow tracing and the Newton-Raphson method to solve the distribution network power flow equation before and after new energy connection. This model calculates node voltage offsets and short-circuit current increase ratios, and combines this with a sensitivity matrix to generate an access impact risk coefficient ranging from 0 to 1 (a larger value indicates a greater impact on distribution network stability from the grid connection operation). This coefficient is then normalized with the output fluctuation risk coefficient and the power supply quality risk coefficient, and mapped to a three-dimensional risk matrix using preset weights (e.g., 0.35 for output fluctuation, 0.35 for power quality, and 0.3 for access impact). The matrix's rows represent risk types (output fluctuation, power quality, and access impact), while its columns represent key nodes in the distribution network (e.g., new energy grid connection points and load centers). The matrix element values ​​are weighted composites of the three risk coefficients. Ultimately, a first distribution network risk matrix is ​​constructed, encompassing all-dimensional risk indicators, enabling a visual and quantitative representation of the potential risks of new energy distribution networks.

[0050] In one possible implementation, step S300 further includes: Step S350: activating the second distribution network risk analysis channel embedded in the distribution network risk analysis dual-channel, wherein the second distribution network risk analysis channel includes a distribution network anomaly detection model and a distribution network fault risk prediction model corresponding to the conventional energy distribution network.

[0051] Step S360: inputting conventional energy distribution network simulation data into the distribution network anomaly detection model to obtain distribution network anomaly detection results.

[0052] Step S370: inputting the distribution network anomaly detection result into the distribution network fault risk prediction model to obtain a distribution network fault risk prediction result, and performing matrix sorting in combination with the distribution network anomaly detection result to generate the second distribution network risk matrix.

[0053] Specifically, the second distribution network risk analysis channel embedded in the distribution network risk analysis dual channel is activated. This channel integrates two types of models built for the characteristics of conventional energy distribution networks: the distribution network anomaly detection model is based on the improved isolation forest algorithm, which performs unsupervised learning on electrical quantities such as voltage, current, and power factor in conventional energy distribution network simulation data, and identifies abnormal operating conditions such as voltage exceeding the limit, three-phase current imbalance, and harmonic exceeding the standard; the distribution network fault risk prediction model adopts a fusion architecture of Bayesian network and fault mechanism model, with historical fault data, equipment aging parameters and real-time anomaly detection results as input, and predicts the probability and impact range of faults such as transformer inter-turn short circuit and excessive line sag through conditional probability reasoning. The two work together to form a risk assessment system covering anomaly identification and fault prediction of conventional energy distribution networks.

[0054] Cleaned and streamlined conventional energy distribution network simulation data (including real-time operating parameters such as busbar voltage amplitude and phase, line three-phase current, power factor, and transformer oil temperature) is fed into the distribution network anomaly detection model. Based on an improved isolation forest algorithm, this model uses a binary tree ensemble to perform unsupervised learning on high-dimensional electrical quantity data. This model automatically identifies anomalies that differ significantly from the majority of samples. First, baseline thresholds are set for typical anomalies such as voltage over-limit (e.g., 10kV busbar voltage exceeding ±7% of rated value), three-phase current imbalance (exceeding 15%), and power factor below 0.9. The isolation forest algorithm then uses path length calculation to uncover hidden anomaly patterns. The model ultimately outputs distribution network anomaly detection results, including anomaly type (voltage, current, or power), anomaly location (specific busbar or line number), and anomaly severity (minor, medium, or severe), providing accurate anomaly data support for subsequent fault risk prediction.

[0055] The distribution network anomaly detection results (including anomaly type, location, and severity) are input into a distribution network fault risk prediction model. This model utilizes a Bayesian network architecture that integrates a fault mechanism model. First, based on historical fault data, a fault probability transfer matrix for transformers, lines, and other equipment is constructed (e.g., the conditional probability of a transformer interturn short circuit due to a voltage overshoot). Bayesian reasoning is then used to calculate the fault risk probability of each component, combining equipment aging parameters (e.g., line age and insulation aging) with real-time anomaly data. Subsequently, the fault risk prediction results (including fault location, probability, and impact range) are combined with the anomaly detection results in a matrix format. The matrix uses conventional energy distribution network equipment (transformers, busbars, and lines) as the row dimension and anomaly type (voltage / current / power) and fault risk level (low / medium / high) as the column dimension. The matrix elements are weighted by anomaly severity and fault probability (e.g., voltage overshoot severity × 0.6 + interturn short circuit probability × 0.4). This ultimately generates a second distribution network risk matrix that represents the risk distribution of the conventional energy distribution network, providing a quantitative basis for subsequent analysis of its interference propagation to the new energy distribution network.

[0056] In one possible implementation, step S400 further includes: Step S410: setting new energy distribution network risk constraints according to new energy distribution network risk factors, wherein the new energy distribution network risk factors include output fluctuation risk, power supply quality risk, and access impact risk.

[0057] Step S420: If the first distribution network risk matrix does not satisfy the new energy distribution network risk constraint, the new energy distribution network control plan is adjusted according to the new energy distribution network risk constraint to obtain a first adjustment group of the new energy distribution network.

[0058] Step S430: performing weight allocation according to the new energy distribution network risk factors to obtain a global distribution network risk analysis function.

[0059] Step S440: performing global distribution network risk optimization on the first regulation group of the new energy distribution network according to the global distribution network risk analysis function, and establishing a second regulation group of the new energy distribution network.

[0060] Step S450: maximizing the distribution network control efficiency according to the second regulation group of the new energy distribution network, and generating the first result of the new energy distribution network optimization.

[0061] Specifically, corresponding risk constraints are set for the three major risk factors of the new energy distribution network: for the output fluctuation risk, based on the characteristics of the new energy power generation equipment and the stability requirements of the power grid, the output fluctuation amplitude is set not to exceed ±15% of the rated value (for example, the 10-minute output change rate of the photovoltaic power station is ≤10% of the rated power); the power supply quality risk constraint limits the harmonic distortion rate to ≤5%, and the voltage deviation to ≤±7% of the rated voltage; the access impact risk constraint stipulates that when the new energy is connected to the grid, the voltage sag amplitude at the grid connection point is ≤10%, and the short-circuit current increase is ≤20% of the rated value. By establishing a risk threshold matrix, quantitative control of the three types of risks, namely output fluctuation, power supply quality and access impact, is achieved, providing clear risk boundary conditions for the optimal compensation of subsequent control plans.

[0062] If risk indicators in the first distribution network risk matrix (e.g., output fluctuation risk coefficient > 0.6, power quality risk coefficient > 0.5) exceed the set risk constraint thresholds, the control scheme adjustment mechanism is activated. First, based on the new energy distribution network risk constraints, the original control scheme's parameters, such as the new energy generation output plan and energy storage charging and discharging strategy, are adjusted to generate multiple control decisions that meet the new energy distribution network requirements for the future time zone, forming a new energy distribution network control decision set. Next, the Pth decision (P is a positive integer) is sequentially extracted from this decision set. A twin simulation of the new energy distribution network is performed to obtain the Pth decision distribution network simulation data. This data is then input into the first channel of the distribution network risk analysis. If the Pth distribution network risk analysis result meets the risk constraints, the Pth distribution network optimization strategy is set and added to the first new energy distribution network control group. Through this cyclic screening process, the first new energy distribution network control group, consisting of all optimization strategies that meet the risk constraints, is ultimately obtained.

[0063] By comprehensively considering the impact of three types of new energy distribution network risk factors—output fluctuation risk, power supply quality risk, and access impact risk—on the safe and stable operation of the distribution network, the weight of each risk factor is determined using the Analytic Hierarchy Process (AHP) or an expert decision-making system. For example, the analysis determined that the output fluctuation risk weight is 0.4, the power supply quality risk weight is 0.35, and the access impact risk weight is 0.25. This then leads to the construction of a global distribution network risk analysis function, F(R)=w1R1+w2R2+w3R3, where w1, w2, and w3 represent the weights of the three risk factors, and R1, R2, and R3 represent the output fluctuation risk coefficient, power supply quality risk coefficient, and access impact risk coefficient, respectively. This function comprehensively quantifies the overall risk level of the new energy distribution network and provides a mathematical model for subsequent global distribution network risk optimization.

[0064] The risk analysis results (output fluctuation risk coefficient, power quality risk coefficient, and access impact risk coefficient) for each distribution network optimization strategy within the first regulation group of the new energy distribution network are input into the global distribution network risk analysis function to calculate the global distribution network risk coefficient for each strategy. By setting a global distribution network risk threshold (e.g., 0.5), each coefficient is individually determined to be less than the threshold, selecting optimization strategies with lower risk coefficients and eliminating high-risk strategies. This establishes a second regulation group of the new energy distribution network composed of low-risk optimization strategies, enabling further risk optimization screening of the first regulation group and providing a safer strategy set for subsequent optimization and maximizing regulation efficiency.

[0065] For the low-risk control strategy in the second regulation group of the new energy distribution network, with the distribution network control efficiency (including new energy utilization rate, control response speed, equipment loss and other indicators) as the optimization goal, the particle swarm optimization algorithm is used to establish a control efficiency evaluation model to quantitatively evaluate the control efficiency of each strategy under different operating scenarios, such as calculating the improvement ratio of new energy power generation utilization rate, control instruction response time, transformer loss reduction and other indicators. From these, the strategy combination that can meet the global distribution network risk constraints and maximize the control efficiency is selected to generate the first result of the new energy distribution network optimization, ensuring that the control plan reaches the optimal operating state under the premise of controllable risks.

[0066] In one possible implementation, step S420 further includes: Step S421: performing adjustment according to the new energy distribution network control plan to obtain a new energy distribution network adjustment decision set, wherein each new energy distribution network adjustment decision in the new energy distribution network adjustment decision set satisfies the new energy distribution network task in the future time zone.

[0067] Step S422: extracting the Pth new energy distribution network regulation decision according to the new energy distribution network regulation decision set, where P is a positive integer.

[0068] Step S423: Perform twin simulation on the new energy distribution network according to the P-th decision of adjusting the new energy distribution network to obtain P-th decision distribution network simulation data.

[0069] Step S424: inputting the P-th decision distribution network simulation data into the first channel of distribution network risk analysis to obtain the P-th distribution network risk analysis result.

[0070] Step S425: If the P-th distribution network risk analysis result meets the new energy distribution network risk constraint, the new energy distribution network adjustment P-th decision is set as the P-th distribution network optimization strategy, and the P-th distribution network optimization strategy is added to the new energy distribution network first adjustment group.

[0071] Specifically, for existing regulation plans that don't meet the risk constraints of the renewable energy distribution network, multiple adjustments are made to the regulation parameters of the renewable energy distribution network based on risk factors such as output fluctuation, power quality, and access impact. These adjustments include modifying the active output limit of photovoltaic power plants, adjusting the charge and discharge power thresholds of energy storage systems, and optimizing the switching timing of renewable energy grid-connected switches. This generates multiple different renewable energy distribution network regulation decisions, which together constitute the renewable energy distribution network regulation decision set. Each regulation decision in this decision set is verified through simulation to ensure that it meets the renewable energy distribution network mission requirements for future time zones, such as ensuring renewable energy power generation absorption targets and maintaining the distribution network voltage stability range. This provides diverse decision options for subsequent screening of optimization strategies that meet risk constraints.

[0072] From the generated set of new energy distribution network regulation decisions, extract the Pth decision (P is a positive integer) in the order of decision generation, for example, extract the first and second decisions in sequence, so as to perform subsequent twin simulation and risk analysis on each regulation decision one by one, ensuring that each decision can be independently evaluated to see whether it meets the new energy distribution network risk constraints, laying the foundation for screening out distribution network optimization strategies that meet the requirements.

[0073] The control parameters in the Pth decision (such as the adjustment value of renewable energy power generation output, energy storage charging and discharging strategy, etc.) are input into the regional distribution network model to simulate the operating status of the renewable energy distribution network under this decision, thereby obtaining the Pth decision distribution network simulation data containing electrical quantities such as node voltage, line current, and renewable energy output, providing simulation data support for the actual operating status for subsequent risk analysis.

[0074] The simulated data for the P-th decision distribution network (including operational data such as output, voltage, and current of the renewable energy distribution network under the P-th regulation decision) obtained through twin simulation is input into the first channel of the distribution network risk analysis. Within this channel, the output fluctuation risk prediction model, the power supply quality risk prediction model, and the access impact risk prediction model analyze the simulated data separately. The output fluctuation risk prediction model calculates a power fluctuation risk coefficient, reflecting the instability of renewable energy output; the power supply quality risk prediction model analyzes voltage and current data to generate a power quality risk coefficient, indicating the quality of power supply; and the access impact risk prediction model assesses the impact of renewable energy access on the distribution network, generating an access impact risk coefficient. These three risk coefficients collectively constitute the P-th distribution network risk analysis results, providing a basis for determining whether the regulation decision meets the renewable energy distribution network risk constraints.

[0075] If the output fluctuation risk factor, power quality risk factor, and access impact risk factor in the P-th distribution network risk analysis result all meet the set new energy distribution network risk constraints (for example, output fluctuation amplitude ≤ ±10% of rated value, harmonic distortion rate ≤ 5%), the P-th new energy distribution network regulation decision is determined to be an effective risk reduction strategy, set as the P-th distribution network optimization strategy, and added to the first regulation group of the new energy distribution network. This operation gradually builds a regulation group composed of multiple optimization strategies by screening regulation decisions that meet the risk constraints, providing a strategy set for subsequent global risk optimization and regulation efficiency optimization.

[0076] In one possible implementation, step S440 further includes: Step S441: inputting the distribution network risk analysis result corresponding to each distribution network optimization strategy in the first regulation group of the new energy distribution network into the global distribution network risk analysis function to obtain each global distribution network risk coefficient.

[0077] Step S442: Determine whether the risk coefficient of each global distribution network is less than the global distribution network risk threshold, and obtain the risk judgment result of each global distribution network.

[0078] Step S443: Optimizing and screening the first regulation group of the new energy distribution network according to the risk judgment results of each global distribution network to generate the second regulation group of the new energy distribution network.

[0079] Specifically, for each distribution network optimization strategy in the first regulation group of the new energy distribution network, the corresponding distribution network risk analysis results, namely the output fluctuation risk coefficient, power quality risk coefficient, and access impact risk coefficient, were extracted. These coefficients were then substituted into the global distribution network risk analysis function. This function performs a weighted calculation on each risk coefficient, using preset weights (for example, a weight of 0.4 for output fluctuation risk, 0.35 for power quality risk, and 0.25 for access impact risk) to derive a global distribution network risk coefficient for each strategy. This quantitatively assesses the comprehensive risk level of each optimization strategy, providing data support for the subsequent screening of low-risk strategies.

[0080] Each global distribution network risk coefficient calculated using the global distribution network risk analysis function is compared against a pre-set global distribution network risk threshold (e.g., 0.5) to determine whether each global distribution network risk coefficient is less than the threshold. If a strategy's global distribution network risk coefficient is less than the threshold, the strategy's overall risk level is considered acceptable; otherwise, the risk is considered excessively high. This judgment process yields a global distribution network risk assessment result for each distribution network optimization strategy, providing a clear basis for subsequent screening of low-risk strategies.

[0081] Based on the obtained global distribution network risk judgment results, the distribution network optimization strategies in the first regulation group of the new energy distribution network are screened, the strategies with a global distribution network risk coefficient less than the global distribution network risk threshold are retained, and the strategies with a risk coefficient not less than the threshold are eliminated, thereby generating a second regulation group of the new energy distribution network composed of low-risk strategies, providing a more risk-controllable strategy set for the subsequent optimization of maximizing the distribution network regulation efficiency.

[0082] In one possible implementation, step S500 further includes: Step S510: performing propagation prediction on the second distribution network risk matrix according to the regional distribution network model to obtain a distribution network risk propagation prediction result.

[0083] Step S520: performing grid-connection fluctuation interference analysis on the new energy distribution network according to the distribution network risk propagation prediction result to obtain grid-connection fluctuation interference characteristics.

[0084] Step S530: performing power supply quality interference analysis on the new energy distribution network according to the distribution network risk propagation prediction result to obtain power supply quality interference characteristics.

[0085] Step S540: performing fault interference analysis on the new energy distribution network according to the distribution network risk propagation prediction result to obtain distribution network fault interference characteristics.

[0086] Step S550: integrating the grid-connected fluctuation interference feature, the power supply quality interference feature, and the distribution network fault interference feature to generate the distribution network passive interference analysis result.

[0087] Specifically, leveraging the established regional distribution network model, a propagation forecast is conducted for the risk distribution of conventional energy distribution networks within the second distribution network risk matrix. By simulating the risk evolution of conventional energy distribution networks under different operating conditions and combining power flow calculations and fault simulation techniques, the propagation path, impact scope, and severity of risks within the regional distribution network are analyzed. This results in a distribution network risk propagation forecast that visually demonstrates the potential impact of conventional energy distribution network risks on new energy distribution networks.

[0088] Based on the distribution network risk propagation prediction results, we analyze the grid-connection fluctuation interference of new energy distribution networks. By analyzing the impact of conventional energy distribution network risk propagation on the new energy grid connection process, we extract characteristic parameters such as voltage deviation, frequency fluctuation amplitude, and power factor change rate during grid connection. This allows us to obtain grid-connection fluctuation interference characteristics that can characterize the impact of conventional energy distribution network risks on the grid connection stability of new energy distribution networks, providing key data support for subsequent comprehensive assessments of interference impacts.

[0089] Based on the distribution network risk propagation prediction results, the power supply quality interference of the new energy distribution network is analyzed. By analyzing the impact of the risk propagation of the conventional energy distribution network on the power supply quality of the new energy distribution network, characteristic parameters such as voltage sag amplitude, harmonic distortion rate, and voltage imbalance are extracted, thereby obtaining power supply quality interference characteristics that can characterize the impact of the conventional energy distribution network risk on the power supply quality of the new energy distribution network, providing key data support for the subsequent comprehensive assessment of the interference impact.

[0090] Based on the distribution network risk propagation prediction results, fault interference analysis is carried out on the new energy distribution network. By analyzing the impact of fault risk propagation of conventional energy distribution networks on new energy distribution networks, characteristic parameters such as short-circuit current amplitude, fault duration, and protection device action characteristics are extracted, thereby obtaining distribution network fault interference characteristics that can characterize the impact of conventional energy distribution network fault risks on new energy distribution network equipment and operations, providing key data support for subsequent comprehensive assessment of interference impacts and optimization of control plans.

[0091] This multi-dimensional fusion combines features such as grid voltage deviation and frequency offset obtained through grid fluctuation interference analysis, harmonic distortion rate and voltage sag amplitude obtained through power quality interference analysis, and short-circuit current amplitude and fault duration obtained through fault interference analysis. Using methods such as feature weighted fusion or matrix operations, the impact and interrelationships of various interference features are comprehensively analyzed. Ultimately, a distribution network passive interference analysis result is generated that fully reflects the passive interference impact of conventional energy distribution networks on new energy distribution networks. This provides a complete interference assessment basis for subsequent compensation optimization of the first result of new energy distribution network optimization.

[0092] Example 2 is based on the same inventive concept as the new energy distribution network intelligent control method based on twin simulation in the previous embodiment. Figure 2 As shown, this application provides a new energy distribution network intelligent control system based on twin simulation. The system and method embodiments in the embodiments of this application are based on the same inventive concept. Among them, the system includes: The distribution network control plan receiving module 10 is used to connect to the regional distribution network and receive the distribution network control plan of the future time zone. The regional distribution network includes a new energy distribution network and a conventional energy distribution network.

[0093] The distribution network simulation data stream acquisition module 20 is used to perform twin simulation on the regional distribution network according to the distribution network control plan to obtain the distribution network simulation data stream.

[0094] The multi-dimensional risk analysis module 30 is used to introduce a dual-channel distribution network risk analysis, and perform multi-dimensional risk analysis on the new energy distribution network and the conventional energy distribution network respectively in combination with the distribution network simulation data flow to obtain a first distribution network risk matrix and a second distribution network risk matrix.

[0095] The optimization compensation module 40 is used to optimize and compensate the new energy distribution network control scheme within the distribution network control scheme according to the first distribution network risk matrix to obtain a first result of the new energy distribution network optimization.

[0096] The interference analysis module 50 is used to perform interference analysis on the new energy distribution network according to the second distribution network risk matrix to obtain a distribution network passive interference analysis result.

[0097] The compensation optimization module 60 is configured to perform compensation optimization on the first optimization result of the new energy distribution network according to the distribution network passive interference analysis result to obtain a second optimization result of the new energy distribution network.

[0098] Furthermore, the system is also used to implement the following functions: Activate the first distribution network risk analysis channel embedded in the distribution network risk analysis dual-channel, the distribution network risk analysis first channel includes the output fluctuation risk prediction model, power supply quality risk prediction model and access impact risk prediction model corresponding to the new energy distribution network; input the new energy distribution network simulation data into the output fluctuation risk prediction model to obtain the output fluctuation risk coefficient; input the new energy distribution network simulation data into the power supply quality risk prediction model to obtain the power supply quality risk coefficient; input the new energy distribution network simulation data into the access impact risk prediction model to obtain the access impact risk coefficient, and construct the first distribution network risk matrix in combination with the output fluctuation risk coefficient and the power supply quality risk coefficient.

[0099] Furthermore, the system is also used to implement the following functions: Activate the second distribution network risk analysis channel embedded in the distribution network risk analysis dual-channel, the second distribution network risk analysis channel includes the distribution network anomaly detection model and the distribution network fault risk prediction model corresponding to the conventional energy distribution network; input the conventional energy distribution network simulation data into the distribution network anomaly detection model to obtain the distribution network anomaly detection result; input the distribution network anomaly detection result into the distribution network fault risk prediction model to obtain the distribution network fault risk prediction result, combine the distribution network anomaly detection result for matrix sorting, and generate the second distribution network risk matrix.

[0100] Furthermore, the system is also used to implement the following functions: According to the new energy distribution network risk factors, new energy distribution network risk constraints are set, and the new energy distribution network risk factors include output fluctuation risk, power supply quality risk and access impact risk; if the first distribution network risk matrix does not meet the new energy distribution network risk constraints, the new energy distribution network control plan is adjusted according to the new energy distribution network risk constraints to obtain a first new energy distribution network control group; weights are allocated according to the new energy distribution network risk factors to obtain a global distribution network risk analysis function; global distribution network risk optimization is performed on the first new energy distribution network control group according to the global distribution network risk analysis function to establish a second new energy distribution network control group; distribution network control efficiency maximization optimization is performed according to the second new energy distribution network control group to generate the first new energy distribution network optimization result.

[0101] Furthermore, the system is also used to implement the following functions: Adjustment is performed according to the new energy distribution network control plan to obtain a new energy distribution network adjustment decision set, where each new energy distribution network adjustment decision in the new energy distribution network adjustment decision set meets the new energy distribution network task in the future time zone; the Pth new energy distribution network adjustment decision is extracted according to the new energy distribution network adjustment decision set, where P is a positive integer; twin simulation is performed on the new energy distribution network according to the Pth new energy distribution network adjustment decision to obtain Pth decision distribution network simulation data; the Pth decision distribution network simulation data is input into the first channel of distribution network risk analysis to obtain a Pth distribution network risk analysis result; if the Pth distribution network risk analysis result meets the new energy distribution network risk constraint, the Pth new energy distribution network adjustment decision is set as the Pth distribution network optimization strategy, and the Pth distribution network optimization strategy is added to the first adjustment group of the new energy distribution network.

[0102] Furthermore, the system is also used to implement the following functions: The distribution network risk analysis results corresponding to each distribution network optimization strategy in the first regulation group of the new energy distribution network are input into the global distribution network risk analysis function to obtain each global distribution network risk coefficient; it is determined whether each global distribution network risk coefficient is less than a global distribution network risk threshold to obtain each global distribution network risk judgment result; the first regulation group of the new energy distribution network is optimized and screened according to the each global distribution network risk judgment result to generate the second regulation group of the new energy distribution network.

[0103] Furthermore, the system is also used to implement the following functions: Perform propagation prediction on the second distribution network risk matrix according to the regional distribution network model to obtain a distribution network risk propagation prediction result; perform grid-connected fluctuation interference analysis on the new energy distribution network according to the distribution network risk propagation prediction result to obtain grid-connected fluctuation interference characteristics; perform power supply quality interference analysis on the new energy distribution network according to the distribution network risk propagation prediction result to obtain power supply quality interference characteristics; perform fault interference analysis on the new energy distribution network according to the distribution network risk propagation prediction result to obtain distribution network fault interference characteristics; and integrate the grid-connected fluctuation interference characteristics, the power supply quality interference characteristics and the distribution network fault interference characteristics to generate the distribution network passive interference analysis result.

[0104] Furthermore, the system is also used to implement the following functions: Three-dimensional modeling is performed based on the regional distribution network to obtain a regional distribution network model; the regional distribution network model is simulated and regulated according to the distribution network regulation plan to obtain a distribution network simulation data set; the distribution network simulation data set is cleaned and sorted to obtain the distribution network simulation data stream, which includes new energy distribution network simulation data and conventional energy distribution network simulation data.

[0105] Furthermore, the system is also used to implement the following functions: The distribution network control plan includes the new energy distribution network control plan and the conventional energy distribution network control plan corresponding to the conventional energy distribution network.

[0106] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0107] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0108] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A new energy distribution network intelligent control method based on twin simulation, characterized by: The method comprises: Connecting to a regional distribution network and receiving a distribution network control plan for a future time zone, wherein the regional distribution network includes a new energy distribution network and a conventional energy distribution network; Performing twin simulation on the regional distribution network according to the distribution network control plan to obtain a distribution network simulation data stream; Introducing a dual-channel distribution network risk analysis, combining the distribution network simulation data stream to perform multi-dimensional risk analysis on the new energy distribution network and the conventional energy distribution network, respectively, to obtain a first distribution network risk matrix and a second distribution network risk matrix; performing optimal compensation for the new energy distribution network control scheme within the distribution network control scheme according to the first distribution network risk matrix to obtain a first result of new energy distribution network optimization; Performing interference analysis on the new energy distribution network according to the second distribution network risk matrix to obtain a distribution network passive interference analysis result; The first result of the new energy distribution network optimization is compensated and optimized according to the distribution network passive interference analysis result to obtain a second result of the new energy distribution network optimization.

2. The method for intelligent control of new energy distribution network based on twin simulation according to claim 1, characterized in that: A dual-channel distribution network risk analysis is introduced, and multi-dimensional risk analysis is performed on the new energy distribution network and the conventional energy distribution network respectively in combination with the distribution network simulation data flow, including: Activate the first distribution network risk analysis channel embedded in the distribution network risk analysis dual channel, wherein the first distribution network risk analysis channel includes an output fluctuation risk prediction model, a power supply quality risk prediction model, and an access impact risk prediction model corresponding to the new energy distribution network; Inputting the new energy distribution network simulation data into the output fluctuation risk prediction model to obtain the output fluctuation risk coefficient; Inputting the new energy distribution network simulation data into the power supply quality risk prediction model to obtain a power supply quality risk coefficient; The new energy distribution network simulation data is input into the access impact risk prediction model to obtain the access impact risk coefficient, and the first distribution network risk matrix is ​​constructed by combining the output fluctuation risk coefficient and the power supply quality risk coefficient.

3. The method for intelligent control of new energy distribution network based on twin simulation according to claim 1, characterized in that: A dual-channel distribution network risk analysis is introduced, and multi-dimensional risk analysis is performed on the new energy distribution network and the conventional energy distribution network respectively in combination with the distribution network simulation data flow, including: Activate the second distribution network risk analysis channel embedded in the distribution network risk analysis dual channel, wherein the second distribution network risk analysis channel includes a distribution network anomaly detection model and a distribution network fault risk prediction model corresponding to the conventional energy distribution network; Inputting conventional energy distribution network simulation data into the distribution network anomaly detection model to obtain distribution network anomaly detection results; The distribution network anomaly detection result is input into the distribution network fault risk prediction model to obtain a distribution network fault risk prediction result, and the distribution network anomaly detection result is combined with matrix sorting to generate the second distribution network risk matrix.

4. The method for intelligent control of new energy distribution network based on twin simulation according to claim 1, characterized in that: The first distribution network risk matrix is ​​used to optimize and compensate the new energy distribution network control scheme within the distribution network control scheme to obtain a first result of the new energy distribution network optimization, including: Setting new energy distribution network risk constraints based on new energy distribution network risk factors, including output fluctuation risk, power supply quality risk, and access impact risk; If the first distribution network risk matrix does not satisfy the new energy distribution network risk constraint, adjusting the new energy distribution network control plan according to the new energy distribution network risk constraint to obtain a first new energy distribution network adjustment group; Perform weight allocation according to the new energy distribution network risk factors to obtain a global distribution network risk analysis function; Performing global distribution network risk optimization on the first regulation group of the new energy distribution network according to the global distribution network risk analysis function to establish a second regulation group of the new energy distribution network; The distribution network control efficiency is maximized and optimized according to the second regulation group of the new energy distribution network to generate the first result of the new energy distribution network optimization.

5. The method for intelligent control of new energy distribution network based on twin simulation according to claim 4 is characterized in that: The new energy distribution network regulation plan is adjusted according to the new energy distribution network risk constraint to obtain a first regulation group of the new energy distribution network, including: Performing adjustments according to the new energy distribution network control plan to obtain a new energy distribution network adjustment decision set, wherein each new energy distribution network adjustment decision in the new energy distribution network adjustment decision set satisfies the new energy distribution network task in the future time zone; Extracting the P-th decision on the new energy distribution network regulation according to the new energy distribution network regulation decision set, where P is a positive integer; Performing twin simulation on the new energy distribution network according to the new energy distribution network adjustment P-th decision to obtain the P-th decision distribution network simulation data; Inputting the P-th decision distribution network simulation data into the first channel of distribution network risk analysis to obtain a P-th distribution network risk analysis result; If the P-th distribution network risk analysis result meets the new energy distribution network risk constraint, the new energy distribution network adjustment P-th decision is set as the P-th distribution network optimization strategy, and the P-th distribution network optimization strategy is added to the new energy distribution network first adjustment group.

6. The method for intelligent control of new energy distribution network based on twin simulation according to claim 4, characterized in that: Performing global distribution network risk optimization on the first regulation group of the new energy distribution network according to the global distribution network risk analysis function to establish a second regulation group of the new energy distribution network includes: Inputting the distribution network risk analysis results corresponding to each distribution network optimization strategy in the first regulation group of the new energy distribution network into the global distribution network risk analysis function to obtain each global distribution network risk coefficient; Determine whether the risk coefficient of each global distribution network is less than the global distribution network risk threshold, and obtain the risk judgment result of each global distribution network; The first regulation group of the new energy distribution network is optimized and screened according to the risk judgment results of each global distribution network to generate the second regulation group of the new energy distribution network.

7. The method for intelligent control of new energy distribution network based on twin simulation according to claim 1, characterized in that: Performing interference analysis on the new energy distribution network according to the second distribution network risk matrix to obtain a distribution network passive interference analysis result, including: Performing a propagation prediction on the second distribution network risk matrix according to the regional distribution network model to obtain a distribution network risk propagation prediction result; Performing grid-connection fluctuation interference analysis on the new energy distribution network according to the distribution network risk propagation prediction result to obtain grid-connection fluctuation interference characteristics; Performing power supply quality interference analysis on the new energy distribution network based on the distribution network risk propagation prediction result to obtain power supply quality interference characteristics; Performing fault interference analysis on the new energy distribution network according to the distribution network risk propagation prediction result to obtain distribution network fault interference characteristics; The grid-connected fluctuation interference feature, the power supply quality interference feature and the distribution network fault interference feature are integrated to generate the distribution network passive interference analysis result.

8. The method for intelligent control of new energy distribution network based on twin simulation according to claim 1, characterized in that: Performing twin simulation on the regional distribution network according to the distribution network control scheme to obtain a distribution network simulation data stream, including: Perform three-dimensional modeling on the regional distribution network to obtain a regional distribution network model; Performing simulation control on the regional distribution network model according to the distribution network control plan to obtain a distribution network simulation data set; The distribution network simulation data set is cleaned and sorted to obtain the distribution network simulation data stream, which includes new energy distribution network simulation data and conventional energy distribution network simulation data.

9. The method for intelligent control of new energy distribution network based on twin simulation according to claim 1, characterized in that: The distribution network control plan includes the new energy distribution network control plan and the conventional energy distribution network control plan corresponding to the conventional energy distribution network.

10. A new energy distribution network intelligent control method based on twin simulation is characterized by: The method comprises: A distribution network control plan receiving module is used to connect to a regional distribution network and receive a distribution network control plan for a future time zone, wherein the regional distribution network includes a new energy distribution network and a conventional energy distribution network; A distribution network simulation data stream acquisition module is used to perform twin simulation on the regional distribution network according to the distribution network control plan to obtain a distribution network simulation data stream; A multi-dimensional risk analysis module is used to introduce a dual-channel distribution network risk analysis module, and to perform multi-dimensional risk analysis on the new energy distribution network and the conventional energy distribution network respectively in combination with the distribution network simulation data stream to obtain a first distribution network risk matrix and a second distribution network risk matrix; an optimization compensation module, configured to optimize and compensate the new energy distribution network control scheme within the distribution network control scheme according to the first distribution network risk matrix, and obtain a first result of the new energy distribution network optimization; An interference analysis module, configured to perform interference analysis on the new energy distribution network according to the second distribution network risk matrix to obtain a distribution network passive interference analysis result; The compensation optimization module is used to perform compensation optimization on the first result of the new energy distribution network optimization according to the distribution network passive interference analysis result to obtain a second result of the new energy distribution network optimization.

Images