A power quality monitoring and active management system for new energy access distribution network based on the Internet of Things

Abstract

The present invention provides a power quality monitoring and active management system for new energy access distribution network based on the Internet of Things, the system comprising a perception and acquisition module, a transmission processing module, an active management module, a control execution module and an interaction support module; the perception and acquisition module is used for real-time monitoring of power quality parameters of key nodes and new energy access points of the distribution network; the transmission processing module is used for preliminarily processing the collected power quality parameters and uploading them to the cloud through the Internet of Things technology; the active management module is used for generating intelligent management strategies in the cloud in combination with the power quality parameter content; the control execution module is used for executing the generated intelligent management strategies; the interaction support module is used for providing a visual monitoring interface to complete the interaction between the system and the user; the present invention realizes real-time monitoring and precise active management of the power quality of the distribution network by integrating the Internet of Things technology and the intelligent management strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network monitoring systems, and in particular to a power quality monitoring and active management system for a new energy access distribution network based on the Internet of Things. Background Art

[0002] With the rapid development of smart grids and new energy, distribution networks are facing increasingly complex operating environments and power quality issues. In particular, the large-scale access of new energy sources such as wind power and photovoltaics has increased grid load volatility, which has had a significant impact on power quality. Traditional distribution network monitoring methods mainly rely on manual inspections and regular maintenance, which is not only costly, but also unable to capture power quality issues in real time and accurately. Therefore, how to achieve real-time monitoring, intelligent analysis and governance of distribution network power quality has become the key to improving grid operation efficiency and ensuring power supply.

[0003] After consulting the relevant disclosed technical solutions, the technology with publication number CN115118010B proposes a distribution network monitoring system based on 5g Internet of Things, including that the distribution network is connected to several distribution network terminals through cables, the processing module is provided with a conversion circuit and a processor, the data acquisition module monitors the power consumption data of the distribution network in real time 24 hours a day, the protection module can play a protective role when the power consumption data of the distribution network is abnormal, the inspection module uses drone inspection to transmit back the captured video, uses video monitoring to supervise the distribution system, transmits back diagnostic data, and realizes a panoramic view of the distribution network. The distribution network monitoring system can measure the distribution data and the distribution network video image, and use 5G technology to transmit data, and timely protect the distribution network when a fault occurs. 5G communication is not limited by the number of channels and the grid structure of the power grid. 5G communication is used to exchange information between multiple protection terminals in the power grid area, and the response is faster, which improves the use effect of the monitoring system; however, the scheme mainly focuses on data acquisition and real-time monitoring. Although fault protection and video supervision can be realized, it lacks the generation and optimization of active governance strategies for power quality. Summary of the invention

[0004] The purpose of the present invention is to propose a power quality monitoring and active management system for new energy access distribution network based on the Internet of Things to address the current deficiencies.

[0005] The present invention adopts the following technical solution:

[0006] A power quality monitoring and active management system for new energy access distribution network based on the Internet of Things, the system comprises a perception and acquisition module, a transmission processing module, an active management module, a control execution module and an interaction support module; the perception and acquisition module is used for real-time monitoring of power quality parameters of key nodes of the distribution network and new energy access points; the transmission processing module is used for preliminarily processing the collected power quality parameters and uploading them to the cloud through the Internet of Things technology; the active management module is used for generating intelligent management strategies in the cloud in combination with the power quality parameter content; the control execution module is used for executing the generated intelligent management strategies; the interaction support module is used for providing a visual monitoring interface to complete the interaction between the system and the user.

[0007] The perception and acquisition module includes a sensor array unit and a status monitoring unit; the sensor array unit is composed of a sensor array deployed at key nodes of the distribution network and new energy access nodes, and the sensor array is used to collect power quality indicators in real time; the status monitoring unit is used to perform preliminary analysis and processing on the power quality indicators at the edge end to obtain abnormal information of the power quality indicators; the power quality parameters include power quality indicators and abnormal information.

[0008] The transmission processing module includes a data preprocessing unit, an encryption packaging unit and a communication transmission unit; the data preprocessing unit is used to perform preprocessing operations on the power quality parameters to ensure the integrity and accuracy of the power quality parameters; the encryption packaging unit is used to securely encrypt and package the preprocessed power quality parameters; the communication transmission unit is used to transmit the encrypted and packaged power quality parameters to the subsequent processing module through Internet of Things communication.

[0009] Furthermore, the active governance module completes the generation of governance strategies through a strategy generation model; the establishment process of the strategy generation model is as follows:

[0010] S11: Acquire historical governance strategy data through a third-party database; the historical governance strategy data includes power quality parameter governance strategy and governance effect data; the governance strategy is specifically the executed governance plan and its specific parameters; the governance effect data is specifically the quantitative improvement result of abnormal information of power quality indicators after executing the governance strategy;

[0011] S12: Establish a strategy generation model framework based on deep learning; wherein the model input of the strategy generation model framework is power quality parameters, and the model output is governance strategy and governance effect data;

[0012] S13: converting the historical governance policy data into feature data that can be input into the policy generation model, and dividing the converted feature data into a training set and a validation set in proportion;

[0013] S14: Use the training set to train and optimize the strategy generation model;

[0014] S15: Use the validation set to verify the accuracy and applicability of the strategy generation model.

[0015] Furthermore, the active governance module also includes a simulation analysis unit and a model optimization unit; the simulation analysis unit is used to establish and run a simulation model and verify the governance strategy by running the simulation model; the model optimization unit is used to optimize the strategy and generate the output result of the model in combination with the verification result of the simulation analysis unit during the training process of the model.

[0016] Furthermore, during the training process, the simulation analysis unit inputs the power quality indicators and governance strategies in the training set into the running simulation model, so that the running simulation model outputs the power quality indicators after simulating the governance strategies; by combining the power quality indicators output by the running simulation model and the corresponding power quality indicator abnormal information in the training set, the quantitative improvement results of the power quality indicator abnormal information are obtained as the verification results of the simulation analysis unit, and the verification results are the governance effect data output by the simulation analysis unit.

[0017] Furthermore, the model optimization unit adjusts the optimization target of the loss function in the simulation model training process by introducing the verification result of the simulation analysis unit, thereby optimizing the output result of the strategy generation model; the loss function is as follows:

[0018] L=α1·L strategy +α2·L simulation ;

[0019] Among them, L is the total loss function of the strategy generation model, L strategy Generate error loss for the policy; L simulation is the simulation verification error loss; α1 is the dynamic weight of the strategy generation error loss, and α2 is the dynamic weight of the simulation verification error loss.

[0020] Furthermore, the active management module completes the generation of the current intelligent management strategy by inputting the power quality parameters acquired in real time into the established strategy generation model.

[0021] Beneficial effects achieved by the present invention:

[0022] The present invention realizes real-time monitoring and intelligent management of power quality in distribution network by combining Internet of Things technology with deep learning model; the perception and collection module can collect power quality parameters in real time, and realize preliminary abnormal information processing through edge computing to ensure the accuracy and integrity of data; through the transmission processing module, the collected data can be safely transmitted to the cloud, ensuring the security and real-time of data transmission; the active management module generates intelligent management strategy based on historical management strategy data using deep learning model, and verifies its effectiveness through simulation analysis unit to ensure the accuracy and applicability of management strategy; the model optimization unit adjusts the loss function of the strategy generation model in combination with the simulation analysis results to further improve the effect of strategy generation; thus, the present invention can provide efficient and accurate power quality management strategy for distribution network, and improve the stability and operation efficiency of power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0024] Figure 1 It is a schematic diagram of the overall module of the present invention.

[0025] Figure 2 A flow chart is established for the strategy generation model of the present invention.

[0026] Figure 3 Schematic diagram of the working process of the strategy analysis unit of the present invention. DETAILED DESCRIPTION

[0027] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with its embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention; for those skilled in the art, other systems, methods and / or features of the present embodiment will become apparent after reviewing the following detailed description; it is intended that all such additional systems, methods, features and advantages are included in this specification; included within the scope of the present invention and protected by the appended claims; additional features of the disclosed embodiments are described in the following detailed description, and these features will be apparent from the following detailed description.

[0028] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right" and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, it is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or component referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and cannot be understood as limitations on this patent. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0029] Embodiment 1:

[0030] like Figure 1 As shown, this embodiment provides a power quality monitoring and active management system for new energy access distribution network based on the Internet of Things, the system includes a perception collection module, a transmission processing module, an active management module, a control execution module and an interaction support module; the perception collection module is used to monitor the power quality parameters of key nodes and new energy access points of the distribution network in real time; the transmission processing module is used to perform preliminary processing on the collected power quality parameters and upload them to the cloud through the Internet of Things technology; the active management module is used to generate an intelligent management strategy in the cloud in combination with the power quality parameter content; the control execution module is used to execute the generated intelligent management strategy; the interaction support module is used to provide a visual monitoring interface to complete the interaction between the system and the user;

[0031] The sensing acquisition module includes a sensor array unit and a state monitoring unit; the sensor array unit is composed of a sensor array deployed at key nodes of the distribution network and new energy access nodes, and the sensor array is used to collect power quality indicators in real time; the state monitoring unit is used to perform preliminary analysis and processing on the power quality indicators at the edge end to obtain abnormal information of the power quality indicators; the power quality parameters include power quality indicators and abnormal information;

[0032] Furthermore, the power quality indicators include, but are not limited to, data such as voltage, current, frequency, harmonics of the distribution network, and output power and fluctuation rate of new energy power generation equipment;

[0033] Furthermore, the state monitoring unit completes the preliminary analysis of potential abnormalities of power quality indicators through a method combining data filtering, statistical feature extraction, threshold judgment and a simple machine learning model in the prior art;

[0034] Furthermore, the transmission processing module includes a data preprocessing unit, an encryption packaging unit and a communication transmission unit; the data preprocessing unit is used to perform preprocessing operations on the power quality parameters to ensure the integrity and accuracy of the power quality parameters; the encryption packaging unit is used to perform secure encryption packaging on the preprocessed power quality parameters; the communication transmission unit is used to transmit the encrypted and packaged power quality parameters to the subsequent processing module through Internet of Things communication;

[0035] Further, such as Figure 2 As shown, the active governance module completes the generation of governance strategies through a strategy generation model; the establishment process of the strategy generation model is as follows:

[0036] S11: Acquire historical governance strategy data through a third-party database; the historical governance strategy data includes power quality parameter governance strategy and governance effect data; the governance strategy is specifically the executed governance plan and its specific parameters; the governance effect data is specifically the quantitative improvement result of abnormal information of power quality indicators after executing the governance strategy;

[0037] S12: Establish a strategy generation model framework based on deep learning; wherein the model input of the strategy generation model framework is power quality parameters, and the model output is governance strategy and governance effect data;

[0038] S13: converting the historical governance policy data into feature data that can be input into the policy generation model, and dividing the converted feature data into a training set and a validation set in proportion;

[0039] S14: Use the training set to train and optimize the strategy generation model;

[0040] S15: Use the validation set to verify the accuracy and applicability of the strategy generation model;

[0041] Specifically, the governance effect data is obtained by quantitative calculation and integration by comparing the abnormal information of the power quality indicators before the governance strategy is implemented and the abnormal information of the power quality indicators after the governance strategy is implemented; for example, by calculating the improvement degree of the abnormal information, such as the percentage of harmonic content reduction or the voltage deviation reduction value, these improved parameters are quantified, weighted and normalized to form a quantitative improvement result, so as to reflect the actual effect of the governance strategy on power quality optimization;

[0042] Furthermore, the active governance module also includes a simulation analysis unit and a model optimization unit; the simulation analysis unit is used to establish and run a simulation model, and verify the governance strategy by running the simulation model; the model optimization unit is used to optimize the strategy and generate the output result of the model in combination with the verification result of the simulation analysis unit during the training process of the model;

[0043] Specifically, the simulation analysis unit establishes an operation simulation model based on the physical characteristic mathematical model of the power system and the access of new energy; the physical characteristic mathematical model includes but is not limited to the power flow equation, the device characteristic description and the simulation of the output characteristic of the new energy device; the power flow equation is used to calculate the voltage, current and power distribution of the grid node to ensure that the simulation can reflect the actual operation status of the distribution network and the transmission network; the device characteristic description includes modeling the dynamic characteristics of reactive compensation equipment, filters, voltage regulating equipment, etc., to capture the response behavior of the equipment under different operating conditions; the new energy equipment model is to simulate the output characteristics and volatility of photovoltaic, wind power, etc., and to build a nonlinear dynamic model of power output in combination with environmental variables;

[0044] Furthermore, during the training process, the simulation analysis unit inputs the power quality indicators and governance strategies in the training set into the running simulation model, so that the running simulation model outputs the power quality indicators after simulating the governance strategies; by combining the power quality indicators output by the running simulation model and the corresponding power quality indicator abnormal information in the training set, the quantitative improvement results of the power quality indicator abnormal information are obtained as the verification results of the simulation analysis unit, and the verification results are the governance effect data output by the simulation analysis unit;

[0045] Furthermore, the model optimization unit adjusts the optimization target of the loss function in the simulation model training process by introducing the verification result of the simulation analysis unit, thereby optimizing the output result of the strategy generation model; the loss function is as follows:

[0046] L=α1·L strategy +α2·L simulation ;

[0047] Among them, L is the total loss function of the strategy generation model, L strategy Generate error loss for the policy; L simulation is the simulation verification error loss; α1 is the dynamic weight of the strategy generation error loss, and α2 is the dynamic weight of the simulation verification error loss; satisfying:

[0048] L strategy =‖y actual -y pred ‖ 2 ;

[0049] Among them, y actual is the governance effect data in the historical governance strategy data, y pred Governance effect data output by the strategy generation model during training;

[0050] L simulation =‖y actual -y sim ‖ 2 ;

[0051] Among them, y sim Verification results of the simulation analysis unit;

[0052]

[0053] Among them, k is the sensitivity coefficient of dynamic weight adjustment, which is used to control the influence of loss difference on weight adjustment and is set by pre-experiment;

[0054] Furthermore, the active governance module completes the generation of the current intelligent governance strategy by inputting the power quality parameters obtained in real time into the established strategy generation model;

[0055] This solution generates accurate governance strategies based on historical governance strategy data by establishing a strategy generation model; establishes an operation simulation model by combining the physical characteristics of the power system and new energy access, and dynamically adjusts the optimization target of the strategy generation model in the process of training the strategy generation model by combining the verification results of the operation simulation model output and the actual output of the strategy generation model; thereby achieving dual guarantees for strategy generation accuracy and applicability; by introducing a dynamic weight mechanism, the parts with larger errors are optimized first, improving the model training efficiency and adaptability; thereby ensuring that the generated governance strategy not only meets the optimal effect of historical data, but also has practical applicability and reliability under complex operating conditions;

[0056] Furthermore, the control execution module receives the intelligent management strategy generated by the active management module and converts it into specific equipment control instructions; including but not limited to real-time control of reactive compensation equipment, filters and voltage regulating equipment in the distribution network, to achieve optimal adjustment of the power quality of the distribution network; at the same time, monitor the execution status and operation effect of the equipment to ensure the accuracy and safety of the implementation of the management strategy.

[0057] Embodiment 2:

[0058] This embodiment should be understood to include at least all the features of any of the above embodiments, and further improve upon them;

[0059] This embodiment provides a power quality monitoring and active management system for new energy access distribution network based on the Internet of Things, the system includes a perception collection module, a transmission processing module, an active management module, a control execution module and an interaction support module; the perception collection module is used to monitor the power quality parameters of key nodes and new energy access points of the distribution network in real time; the transmission processing module is used to perform preliminary processing on the collected power quality parameters and upload them to the cloud through the Internet of Things technology; the active management module is used to generate an intelligent management strategy in the cloud in combination with the power quality parameter content; the control execution module is used to execute the generated intelligent management strategy; the interaction support module is used to provide a visual monitoring interface to complete the interaction between the system and the user;

[0060] Furthermore, the interactive support module includes a data visualization unit, a strategy analysis unit and an improvement reminder unit; the data visualization unit is used to provide real-time monitoring and display of all parameters and governance strategy machine execution status in the system through a visual monitoring interface; the strategy analysis unit is used to provide users with maintenance inspection reminders for various areas of the distribution network in combination with the execution status of historical governance strategies; the improvement reminder unit is used to visually display the distribution network areas that need to be focused on for users in combination with the output results of the strategy analysis unit;

[0061] Further, such as Figure 3 As shown, the specific working process of the strategy analysis unit is as follows:

[0062] S21: Establish an analysis cycle and obtain the execution information of the historical governance strategy of the distribution network within the analysis cycle; the execution information includes the execution time, frequency and governance effect data of the governance strategy;

[0063] S22: For a certain area in the distribution network, calculate the regional priority attention coefficient:

[0064]

[0065] Among them, S is the regional priority attention coefficient, f is the execution frequency of the governance strategy in the region during the analysis period, and E eff is the normalized coefficient of the average improvement in the governance effect of the region during the analysis period, which is obtained through the governance effect data of the region during the analysis period; γ is the amplification coefficient, which is used to control the impact of the average improvement in the governance effect on the regional priority attention coefficient and is set through pre-experimental settings;

[0066] S23: The above step is performed on all areas in the distribution network to generate a regional priority attention coefficient for each area in the distribution network. A larger regional priority attention coefficient indicates that the area requires more attention from the user and maintenance inspection operations are performed;

[0067] Furthermore, the improved reminder unit establishes a visualized distribution network area attention map, thereby visually displaying the distribution network areas that need to be focused on for the user; specifically, the improved reminder unit marks the color depth of different areas in the distribution network area attention map in combination with the regional priority attention coefficients of each distribution network area, thereby visually displaying the governance priority levels of different areas for the user; for a certain area in the distribution network area attention map:

[0068] V = S·v;

[0069] Among them, V is the marking color depth of the area. The darker the color, the higher the governance priority level of the area. v is the basic color marking coefficient.

[0070] In this embodiment, some functional implementation codes of the strategy analysis unit and the improvement reminder unit are as follows:

[0071]

[0072] print(df[['region','attention_score']])

[0073] #Visual distribution network area attention map

[0074] #Use Matplotlib to draw a simple area map, the color depth of the area is related to the attention score

[0075] fig,ax=plt.subplots(figsize=(8,6))

[0076] #Set color mapping

[0077] cmap = plt.cm.viridis #You can choose a different color map, 'viridis' is a common color map

[0078] # Draw a rectangle for each area, the color depth is based on the priority attention coefficient

[0079] for idx,row in df.iterrows():

[0080] ax.barh(row['region'],row['attention_score'],color=cmap(row['attention_score'] / max(df['attention_score'])))

[0081] #Add title and labels

[0082] ax.set_title("Distribution Network Area Focus Map",fontsize=16)

[0083] ax.set_xlabel("Regional priority coefficient",fontsize=12)

[0084] ax.set_ylabel("area",fontsize=12)

[0085] # Display the color bar

[0086] cbar=plt.colorbar(plt.cm.ScalarMappable(cmap=cmap),ax=ax)

[0087] cbar.set_label('Follow rating',fontsize=12)

[0088] # Display the graph

[0089] plt.show().

[0090] This solution uses the strategy analysis unit combined with the execution of historical governance strategies in various distribution network areas to accurately identify areas where governance is frequent and ineffective, and generates distribution network area attention maps through improved reminder units to provide users with key attention and maintenance suggestions; it helps users quickly identify problem areas in a visual way and improves the efficiency and intelligence of power grid governance.

[0091] The contents disclosed above are only preferred feasible embodiments of the present invention, and do not limit the protection scope of the present invention. Therefore, all equivalent technical changes made using the contents of the present invention specification and drawings are included in the protection scope of the present invention. In addition, the elements therein can be updated as technology develops.

Claims

1. A power quality monitoring and active management system for new energy access distribution network based on the Internet of Things, characterized in that: The system includes a perception collection module, a transmission processing module, an active governance module, a control execution module and an interactive support module; the perception collection module is used to monitor the power quality parameters of key nodes of the distribution network and new energy access points in real time; The transmission processing module is used to perform preliminary processing on the collected power quality parameters and then upload them to the cloud through the Internet of Things technology; the active governance module is used to generate intelligent governance strategies in the cloud based on the power quality parameter content; The control execution module is used to execute the generated intelligent governance strategy; the interaction support module is used to provide a visual monitoring interface to complete the interaction between the system and the user; The sensing and acquisition module includes a sensor array unit and a state monitoring unit; the sensor array unit is composed of a sensor array deployed at key nodes of the distribution network and new energy access nodes, and the sensor array is used to collect power quality indicators in real time; The state monitoring unit is used to perform preliminary analysis and processing on the power quality index at the edge end to obtain abnormal information of the power quality index; the power quality parameter includes the power quality index and abnormal information; The transmission processing module includes a data preprocessing unit, an encryption packaging unit and a communication transmission unit; the data preprocessing unit is used to perform preprocessing operations on the power quality parameters to ensure the integrity and accuracy of the power quality parameters; the encryption packaging unit is used to perform secure encryption packaging on the preprocessed power quality parameters; The communication transmission unit is used to transmit the encrypted and packaged power quality parameters to the subsequent processing module through Internet of Things communication.

2. According to the Internet of Things-based new energy access distribution network power quality monitoring and active management system of claim 1, it is characterized in that: The active governance module completes the generation of governance strategies through a strategy generation model; the establishment process of the strategy generation model is as follows: S11: Acquire historical governance strategy data through a third-party database; the historical governance strategy data includes power quality parameter governance strategy and governance effect data; the power quality parameter governance strategy is specifically the executed governance plan and its specific parameters; the governance effect data is specifically the quantitative improvement result of abnormal information of power quality indicators after executing the governance strategy; S12: Establish a strategy generation model framework based on deep learning; wherein the model input of the strategy generation model framework is power quality parameters, and the model output is governance strategy and governance effect data; S13: converting the historical governance policy data into feature data that can be input into the policy generation model, and dividing the converted feature data into a training set and a validation set in proportion; S14: Use the training set to train and optimize the strategy generation model; S15: Use the validation set to verify the accuracy and applicability of the strategy generation model.

3. According to claim 2, a power quality monitoring and active management system for new energy access distribution network based on the Internet of Things is characterized in that: The active governance module also includes a simulation analysis unit and a model optimization unit; the simulation analysis unit is used to establish a running simulation model and verify the governance strategy by running the simulation model; The model optimization unit is used to generate the output result of the model by combining the verification result optimization strategy of the simulation analysis unit during the training process of the model.

4. According to claim 3, a power quality monitoring and active management system for new energy access distribution network based on the Internet of Things is characterized in that: During the training process, the simulation analysis unit inputs the power quality index and the governance strategy in the training set into the running simulation model, so that the running simulation model outputs the power quality index after simulating the governance strategy; By combining the power quality indicators output by the running simulation model and the corresponding power quality indicator abnormal information in the training set, the quantitative improvement results of the power quality indicator abnormal information are obtained as the verification results of the simulation analysis unit. The verification results are the governance effect data output by the simulation analysis unit.

5. According to the Internet of Things-based new energy access distribution network power quality monitoring and active management system of claim 3, it is characterized in that: The model optimization unit adjusts the optimization target of the loss function in the simulation model training process by introducing the verification result of the simulation analysis unit, thereby optimizing the output result of the strategy generation model; the loss function is as follows: L=α1·L strategy +α2·L simulation ; Among them, L is the total loss function of the strategy generation model, L strategy Generate error loss for the policy; L simulation is the simulation verification error loss; α1 is the dynamic weight of the strategy generation error loss, and α2 is the dynamic weight of the simulation verification error loss.

6. According to the Internet of Things-based new energy access distribution network power quality monitoring and active management system of claim 2, it is characterized in that: The active management module completes the generation of the current intelligent management strategy by inputting the power quality parameters obtained in real time into the established strategy generation model.

Images