Virtual power plant cloud platform data transmission regulation and control system

Abstract

The invention discloses a virtual power plant cloud platform data transmission regulation and control system, which comprises a data acquisition module, an edge calculation module, a cloud platform regulation and control module and an instruction execution module, the data acquisition module is in communication connection with the edge computing module, the cloud platform regulation and control module is in communication connection with the edge computing module, and the instruction execution module is in communication connection with the cloud platform regulation and control module; the data acquisition module is used for collecting data of distributed energy equipment in real time, the edge calculation module is used for performing primary processing on the collected data, and the cloud platform regulation and control module is used for performing deep analysis and optimization processing on the data uploaded by the edge calculation module. And the instruction execution module is used for executing the instruction sent by the cloud platform regulation and control module. According to the invention, primary processing is carried out at a data source through the edge calculation module, the data processing time is effectively shortened, the new energy consumption rate is improved, and the communication cost is synchronously reduced.

Description

Technical Field

[0001] This invention belongs to the field of virtual power plant energy dispatch and data transmission technology, specifically relating to a virtual power plant cloud platform data transmission control system. Background Technology

[0002] With the deepening of electricity market reform, the demand for distributed energy access has surged, and the frequency of electricity market transactions has increased significantly. Virtual power plants, as an emerging energy management model, integrate distributed energy resources to achieve flexible control of the power system, becoming an important means of solving the energy supply and demand balance problem. However, existing virtual power plant data transmission and control technologies still have many shortcomings and urgently need improvement.

[0003] 1. Processing delays due to multi-source heterogeneous data: Virtual power plants involve various distributed energy devices such as charging piles, photovoltaics, and energy storage, resulting in multi-source heterogeneous data. Significant differences in data formats, sampling frequencies, and transmission protocols among different devices increase the difficulty of data processing, prolong processing time, and hinder real-time control.

[0004] 2. Data faces security threats such as cyberattacks and data breaches during transmission. Existing technologies are inadequate in areas such as data encryption, authentication, and access control, failing to effectively guarantee the security and integrity of data transmission, which may lead to power system malfunctions or the leakage of user information.

[0005] 3. The collaboration efficiency between edge devices and the cloud platform needs improvement. Edge devices have limited capabilities in data preprocessing and local decision-making, requiring large amounts of data to be uploaded to the cloud platform for processing, increasing network bandwidth pressure and data transmission latency. Simultaneously, the cloud platform's real-time monitoring and command issuance to edge devices are not timely enough, affecting the overall control effect of the virtual power plant.

[0006] 4. Lack of unified standards and specifications: Currently, the virtual power plant field lacks unified data transmission standards and control specifications. Incompatibility between equipment and systems from different manufacturers is poor, making interconnection and collaborative operation difficult. This not only increases the difficulty and cost of system integration but also limits the large-scale promotion and application of virtual power plants.

[0007] Therefore, the present invention provides a virtual power plant cloud platform data transmission control system to solve the problems mentioned in the background art. Summary of the Invention

[0008] To address the problems raised in the background art, the objective of this invention is to provide a data transmission and control system for a virtual power plant cloud platform.

[0009] To achieve the above-mentioned technical objectives, the technical solution adopted by the present invention is as follows:

[0010] A virtual power plant cloud platform data transmission and control system includes a data acquisition module, an edge computing module, a cloud platform control module, and an instruction execution module;

[0011] The data acquisition module is communicatively connected to the edge computing module, the cloud platform control module is communicatively connected to the edge computing module, and the instruction execution module is communicatively connected to the cloud platform control module.

[0012] The data acquisition module is used to collect data from distributed energy devices in real time. The edge computing module is used to perform preliminary processing on the collected data. The cloud platform control module is used to perform in-depth analysis and optimization processing on the data uploaded by the edge computing module. The instruction execution module is used to execute the instructions issued by the cloud platform control module.

[0013] Furthermore, the data acquisition module includes a 5G communication unit and an RS485 interface, and is connected to the distributed energy equipment through the 5G communication unit or the RS485 interface.

[0014] Further specifying, the distributed energy equipment includes charging piles, photovoltaic inverters, and energy storage batteries.

[0015] Furthermore, the edge computing module communicates with the cloud platform control module via the MQTT protocol, and the data acquisition module performs preliminary processing on the acquired data at the data source, including data cleaning, filtering, and aggregation operations.

[0016] Furthermore, the edge computing module is equipped with an edge computing threshold, and corresponding processing is performed when the data exceeds the threshold;

[0017] The data thresholds include photovoltaic output greater than 120% of rated power and load power fluctuation greater than 20% within 10 seconds;

[0018] The handling measures include primary measures and secondary measures. The primary measure is that the edge computing module sends a frequency reduction command to the data acquisition module, and the corrected data is still uploaded to the cloud platform control module.

[0019] The secondary measures are as follows: the edge computing module sends a cut-off command to the execution module to cut off the communication link of the abnormal data source, and at the same time switches to temporary power supply from the energy storage device. The execution module then uploads an emergency alarm to the cloud platform control module.

[0020] Furthermore, the cloud platform control module uses reinforcement learning optimization algorithms to perform in-depth analysis and optimization of the data uploaded by the edge computing module, generates energy dispatch instructions, and communicates bidirectionally with the edge computing module and the instruction execution module;

[0021] The edge computing module also includes a three-level data processing unit: a preprocessing unit, a feature engineering unit, and a scene analysis unit. These units are used to perform in-depth analysis on the uploaded data. The preprocessing unit removes high-frequency noise using wavelet transform and aligns multi-source heterogeneous data based on GPS timestamps. The feature engineering unit extracts time-domain, frequency-domain, and semantic features, compressing the data dimension to 10% of its original size. The scene analysis unit calls an analysis model that matches the application scenario and outputs scenario-based control indicators.

[0022] The scenario analysis unit predicts the power curve for the next 15 minutes using an improved LSTM neural network, with a MAE ≤ 3%. Based on the prediction results, the PSO algorithm is used to solve the optimal scheduling strategy, with the objective function being to minimize network loss and maximize renewable energy consumption. The isolated forest algorithm is then used to verify the anomalies in the optimization results.

[0023] Furthermore, the instruction execution module is connected to the distributed energy equipment via a PLC control device, controls the operating status of the distributed energy equipment according to the instructions issued by the cloud platform control module, and feeds back the execution results to the cloud platform control module.

[0024] Further specifying, the operation status control of the distributed energy equipment includes adjusting the charging power of the charging pile and the charging and discharging strategy of the energy storage device through the instruction execution module; the instruction execution module adjusts the charging pile and the energy storage device through the following steps:

[0025] Step 1: Receive optimization instructions from the cloud platform control module, including the target power of the charging pile and the energy storage charging and discharging threshold;

[0026] Step 2: Send a PWM control signal to the charging pile controller via the CAN bus to adjust the rectifier output voltage;

[0027] Step 3: Control the energy storage inverter via Modbus RTU protocol and dynamically adjust the charging and discharging current according to the grid frequency deviation.

[0028] Furthermore, the data acquisition module includes a multi-protocol gateway for converting between different communication protocols, ensuring that the data acquisition module can communicate with various distributed energy devices. The multi-protocol gateway supports Modbus RTU / TCP, MQTT, and IEC 61850 protocol conversion.

[0029] A data transmission control method based on a virtual power plant cloud platform includes the following steps:

[0030] S1: Collect distributed resource data at a data sampling frequency of 10Hz through a multi-protocol gateway.

[0031] S2: The edge computing module performs preliminary processing on the collected data. The edge preprocessing delay is ≤200ms. An edge computing threshold is set. When the data exceeds the threshold, corresponding processing is performed. The data thresholds include photovoltaic output greater than 120% of the rated power and load power fluctuation greater than 20% within 10 seconds.

[0032] The handling measures include primary measures and secondary measures. The primary measure is that the edge computing module sends a frequency reduction command to the data acquisition module, and the corrected data is still uploaded to the cloud platform control module.

[0033] The secondary measures are as follows: the edge computing module sends a cut-off command to the execution module to cut off the communication link of the abnormal data source, and at the same time switches to temporary power supply from the energy storage device. The execution module then uploads an emergency alarm to the cloud platform control module.

[0034] S3: The cloud platform control module uses optimization algorithms such as reinforcement learning to perform in-depth analysis on the data uploaded by the edge computing module and generate the optimal energy dispatching scheme.

[0035] The edge computing module includes a three-level data processing unit: a preprocessing unit, a feature engineering unit, and a scene analysis unit. These units perform in-depth analysis of uploaded data. The preprocessing unit removes high-frequency noise using wavelet transform and aligns multi-source heterogeneous data based on GPS timestamps. The feature engineering unit extracts time-domain, frequency-domain, and semantic features, compressing the data dimensionality to 10% of its original size. The scene analysis unit calls an analysis model matching the application scenario and outputs scenario-based control indicators.

[0036] S4: The cloud platform control module sends the generated scheduling instructions to the instruction execution module via the network.

[0037] S5: After executing the instruction, the instruction execution module feeds back the execution result to the cloud platform control module. The cloud platform control module then corrects and optimizes the scheduling scheme based on the feedback information.

[0038] The beneficial effects of this invention are:

[0039] Compared to existing technologies, this invention demonstrates significant advantages in several key technical indicators and brings considerable comprehensive benefits: Regarding data processing latency, existing technologies suffer from long latency due to the difficulty in processing multi-source heterogeneous data, while this invention effectively shortens data processing time by performing preliminary processing at the data source through an edge computing module. The system's precise regulation of distributed energy resources improves the renewable energy absorption rate and better adapts to the volatility of renewable energy generation. Furthermore, optimized data transmission strategies and the adoption of efficient communication protocols reduce communication costs.

[0040] In addition, the present invention has significantly improved edge-cloud collaboration efficiency and data transmission security. The efficient collaboration between edge devices and cloud platforms ensures the timely issuance of energy dispatching instructions and real-time data feedback. Attached Figure Description

[0041] The present invention can be further illustrated by the non-limiting embodiments given in the accompanying drawings;

[0042] Figure 1 This is a system module diagram of an embodiment of a virtual power plant cloud platform data transmission control system according to the present invention;

[0043] Figure 2 This is a partial system module diagram of the edge computing module in an embodiment of a virtual power plant cloud platform data transmission control system of the present invention;

[0044] Figure 3 This is a flowchart illustrating the steps of an embodiment of a virtual power plant cloud platform data transmission control system according to the present invention.

[0045] The main component symbols are explained as follows: data acquisition module 101, edge computing module 102, cloud platform control module 103, and instruction execution module 104. Detailed Implementation

[0046] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be further described below with reference to the accompanying drawings and embodiments. The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0047] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0048] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0049] like Figure 1 As shown, a virtual power plant cloud platform data transmission control system of the present invention includes a data acquisition module 101, an edge computing module 102, a cloud platform control module 103, and an instruction execution module 104.

[0050] The data acquisition module 101 is communicatively connected to the edge computing module 102, the cloud platform control module 103 is communicatively connected to the edge computing module 102, and the instruction execution module 104 is communicatively connected to the cloud platform control module 103.

[0051] The data acquisition module 101 is used to collect data from distributed energy devices in real time. The edge computing module 102 is used to perform preliminary processing on the collected data. The cloud platform control module 103 is used to perform in-depth analysis and optimization processing on the data uploaded by the edge computing module 102. The instruction execution module 104 is used to execute the instructions issued by the cloud platform control module 103.

[0052] In the practical application of this embodiment, the data acquisition module 101 includes a 5G communication unit and an RS485 interface, and is connected to the distributed energy equipment through the 5G communication unit or the RS485 interface.

[0053] In practical applications of this embodiment, the distributed energy equipment includes charging piles, photovoltaic inverters, and energy storage batteries.

[0054] In the practical application of this embodiment, the edge computing module 102 communicates with the cloud platform control module 103 through the MQTT protocol, and the data acquisition module 101 performs preliminary processing on the acquired data at the data source, including data cleaning, filtering and aggregation operations.

[0055] The data acquisition module 101 performs preliminary processing on the acquired data, specifically including: filtering outliers (such as negative values ​​or over-range data caused by sensor failure) using the 3σ criterion; using moving average filtering to suppress high-frequency noise; and dynamically normalizing the data to the [0,1] interval; converting the native protocol data into JSON format; compressing the data using the LZ77 algorithm; and retaining the timestamp and device ID fields; configuring non-volatile memory to enable breakpoint resumption. If the network is interrupted, the data is temporarily stored in the non-volatile memory, and the cached data is retransmitted according to the timestamp after the network is restored.

[0056] In the practical application of this embodiment, the edge computing module 102 is equipped with an edge computing threshold, and corresponding processing is performed when the data exceeds the threshold;

[0057] The data thresholds include photovoltaic output greater than 120% of rated power and load power fluctuation greater than 20% within 10 seconds;

[0058] The processing measures include primary measures and secondary measures. The primary measure is that the edge computing module 102 sends a frequency reduction command to the data acquisition module 101, and the corrected data is still uploaded to the cloud platform control module 103.

[0059] The secondary measures are as follows: the edge computing module 102 sends a cut-off command to the execution module 104 to cut off the communication link of the abnormal data source, and at the same time switches to temporary power supply from the energy storage device. The execution module 104 then uploads an emergency alarm to the cloud platform control module.

[0060] In the practical application of this embodiment, the cloud platform control module 103 uses reinforcement learning optimization algorithm to perform in-depth analysis and optimization processing on the data uploaded by the edge computing module 102, generates energy dispatch instructions, and conducts bidirectional communication with the edge computing module 102 and the instruction execution module 104.

[0061] The edge computing module 102 also includes a three-level data processing unit, namely a preprocessing unit, a feature engineering unit, and a scene analysis unit, for performing in-depth analysis on the uploaded data. The preprocessing unit removes high-frequency noise through wavelet transform and aligns multi-source heterogeneous data based on GPS timestamps. The feature engineering unit extracts time-domain, frequency-domain, and semantic features, compressing the data dimension to 10% of the original size. The scene analysis unit calls an analysis model that matches the application scenario and outputs scenario-based control indicators.

[0062] The scenario analysis unit predicts the power curve for the next 15 minutes using an improved LSTM neural network, with a MAE ≤ 3%. Based on the prediction results, the PSO algorithm (improved particle swarm optimization algorithm) is used to solve the optimal scheduling strategy, with the objective function being to minimize network loss and maximize renewable energy consumption. The optimization results are then checked for anomalies using the isolated forest algorithm.

[0063] The algorithm collaboration process includes the following steps:

[0064] The feature engineering unit outputs a 128-dimensional feature vector (including preprocessed real-time data and historical trend features); the scenario analysis unit generates a distributed power output / load prediction curve for the next 15 minutes using an LSTM model; the scenario analysis unit uses the PSO algorithm with the prediction curve as input to solve the optimal scheduling strategy (such as energy storage charging and discharging power, distributed power output command) locally in the edge computing module 102; the scenario analysis unit verifies the optimization results based on the isolated forest algorithm, and if an anomaly is identified (such as the strategy causing line overload), the PSO algorithm is triggered to re-optimize.

[0065] In the practical application of this embodiment, the instruction execution module 104 is connected to the distributed energy device through the PLC control device, controls the operating status of the distributed energy device according to the instructions issued by the cloud platform control module 103, and feeds back the execution results to the cloud platform control module 103.

[0066] In the practical application of this embodiment, the operation status control of the distributed energy equipment includes adjusting the charging power of the charging pile and the charging and discharging strategy of the energy storage device through the instruction execution module 104; the instruction execution module 104 adjusts the charging pile and the energy storage device through the following steps:

[0067] Step 1: Receive optimization instructions from the cloud platform control module, including the target power of the charging pile and the energy storage charging and discharging threshold;

[0068] Step 2: Send a PWM control signal to the charging pile controller via the CAN bus to adjust the rectifier output voltage;

[0069] Step 3: Control the energy storage inverter via Modbus RTU protocol and dynamically adjust the charging and discharging current according to the grid frequency deviation.

[0070] In the practical application of this embodiment, the data acquisition module 101 includes a multi-protocol gateway for converting between different communication protocols, ensuring that the data acquisition module 101 can communicate with various distributed energy devices. The multi-protocol gateway supports Modbus RTU / TCP, MQTT, and IEC 61850 protocol conversion.

[0071] A data transmission control method based on a virtual power plant cloud platform includes the following steps:

[0072] S1: Collect distributed resource data at a data sampling frequency of 10Hz through a multi-protocol gateway.

[0073] S2: The edge computing module 102 performs preliminary processing on the collected data. The edge preprocessing delay is ≤200ms. An edge computing threshold is set. When the data exceeds the threshold, corresponding processing is performed. The data thresholds include photovoltaic output greater than 120% of rated power and load power fluctuation greater than 20% within 10 seconds.

[0074] The processing measures include primary measures and secondary measures. The primary measure is that the edge computing module 102 sends a frequency reduction command to the data acquisition module 101, and the corrected data is still uploaded to the cloud platform control module 103.

[0075] The secondary measures are as follows: the edge computing module 102 sends a cut-off command to the execution module 104 to cut off the communication link of the abnormal data source, and at the same time switches to temporary power supply from the energy storage device. The execution module 104 uploads an emergency alarm to the cloud platform control module.

[0076] S3: The cloud platform control module 103 uses optimization algorithms such as reinforcement learning to perform in-depth analysis on the data uploaded by the edge computing module 102 and generate the optimal energy scheduling scheme.

[0077] The edge computing module 102 includes a three-level data processing unit: a preprocessing unit, a feature engineering unit, and a scene analysis unit. These units are used to perform in-depth analysis of uploaded data. The preprocessing unit removes high-frequency noise using wavelet transform and aligns multi-source heterogeneous data based on GPS timestamps. The feature engineering unit extracts time-domain, frequency-domain, and semantic features, compressing the data dimension to 10% of its original size. The scene analysis unit calls an analysis model matching the application scenario and outputs scenario-based control indicators.

[0078] S4: The cloud platform control module 103 sends the generated scheduling instructions to the instruction execution module 104 via the network.

[0079] S5: After the instruction execution module executes instruction 104, it feeds back the execution result to the cloud platform control module 103. The cloud platform control module 103 then corrects and optimizes the scheduling scheme based on the feedback information.

[0080] The working principle of this invention is as follows:

[0081] The virtual power plant cloud platform data transmission and control system of this invention features a collaborative workflow among its various modules, forming an efficient data transmission and control mechanism. The data acquisition module 101, acting as the system's front end, acquires real-time data from distributed energy devices such as charging piles, photovoltaic inverters, and energy storage batteries. The data acquisition module 101 connects to different devices via a 5G communication unit and an RS485 interface, utilizing a multi-protocol gateway to ensure comprehensive data acquisition. The acquired data is transmitted to the edge computing module 102. This module performs preliminary processing at the data source, filtering outliers, cleaning noisy data, and aggregating data according to preset edge computing thresholds. For example, when abnormal fluctuations in the current data of a charging pile are detected, the edge computing module 102 will promptly mark and process the data, reducing the computational burden on the cloud platform control module 103.

[0082] The preprocessed data is uploaded to the cloud platform control module 103 via the MQTT protocol. The cloud platform control module 103 uses optimization algorithms such as reinforcement learning to perform in-depth analysis of the data, combining factors such as electricity market prices and energy demand forecasts to generate optimal energy dispatch instructions. For example, during peak electricity consumption periods, the cloud platform adjusts the discharge strategy of energy storage devices based on real-time data to prioritize meeting high load demands.

[0083] After the instruction is generated, the cloud platform control module 103 sends the instruction to the instruction execution module 104. The instruction execution module 104 connects to the energy equipment through control devices such as PLCs to control the charging power of the charging piles and the charging and discharging of the energy storage devices. At the same time, the execution module feeds back the execution results to the cloud platform control module 103, which then corrects and optimizes the scheduling plan based on the feedback information.

[0084] To ensure stable system operation, the cloud platform control module 103 of this system also employs several key technologies, including edge-cloud collaborative encryption technology to ensure data security during transmission and storage, preventing data leakage and network attacks. It also includes dynamic bandwidth allocation technology to flexibly adjust network bandwidth according to data transmission needs, improving data transmission efficiency and ensuring stable system operation under different network environments.

[0085] Example 1: Industrial Park Scene

[0086] The industrial park utilizes a distributed photovoltaic (PV) system combined with energy storage and industrial loads, and this system plays a crucial role. The data acquisition module 101 collects real-time data from 30 PV inverters, 10 sets of energy storage batteries, and 50 industrial motors. The PV inverter data reflects the solar power generation, the energy storage battery data shows its charge / discharge status, and the industrial motor data can be used to analyze the park's electricity load.

[0087] The edge computing module 101 performs preliminary processing on the collected data, filtering outliers and reducing the computational burden on the cloud platform control module 103. Based on this data, and considering the park's electricity demand and grid conditions, the cloud platform control module 103 generates an optimal energy dispatch plan. For example, when sunlight is abundant, photovoltaic power is prioritized, and excess energy is stored in energy storage batteries; during peak electricity demand periods, the energy stored in the batteries is released, reducing reliance on the grid. In this way, the system effectively reduces the park's peak load by 15%, improves energy efficiency, and lowers electricity costs.

[0088] Example 2: Urban Scene

[0089] In the city, a system combining building air conditioning, charging piles, and distributed energy storage is used, connecting 1,000 air conditioners and 500 charging piles in 20 buildings. The data acquisition module 101 continuously acquires the operating status of the air conditioners, the charging status of the charging piles, and the power information of the distributed energy storage.

[0090] The edge computing module 101 preprocesses the data, and the cloud platform control module 103 dynamically adjusts the air conditioning temperature threshold based on electricity price signals and user comfort constraints. For example, during peak electricity price periods, the air conditioning temperature setpoint is appropriately increased, while ensuring that the indoor temperature remains within the user's acceptable comfort range; during off-peak electricity price periods, the air conditioning temperature setpoint is decreased, while simultaneously charging charging piles and distributed energy storage. Through this control strategy, both the user's basic needs are met, and the overall energy consumption of the building is reduced, achieving a win-win situation for both economic benefits and user experience.

[0091] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A data transmission and control system for a virtual power plant cloud platform, characterized in that: It includes a data acquisition module (101), an edge computing module (102), a cloud platform control module (103), and an instruction execution module (104); The data acquisition module (101) is communicatively connected to the edge computing module (102), the cloud platform control module (103) is communicatively connected to the edge computing module (102), and the instruction execution module (104) is communicatively connected to the cloud platform control module (103). The data acquisition module (101) is used to collect data from distributed energy devices in real time. The edge computing module (102) is used to perform preliminary processing on the collected data. The cloud platform control module (103) is used to perform in-depth analysis and optimization processing on the data uploaded by the edge computing module (102). The instruction execution module (104) is used to execute the instructions issued by the cloud platform control module (103).

2. The virtual power plant cloud platform data transmission control system according to claim 1, characterized in that: The data acquisition module (101) includes a 5G communication unit and an RS485 interface, and is connected to the distributed energy equipment through the 5G communication unit or the RS485 interface.

3. A virtual power plant cloud platform data transmission control system according to claim 1 or 2, characterized in that: The distributed energy equipment includes charging piles, photovoltaic inverters, and energy storage batteries.

4. The virtual power plant cloud platform data transmission control system according to claim 1, characterized in that: The edge computing module (102) communicates with the cloud platform control module (103) via the MQTT protocol. The data acquisition module (101) performs preliminary processing on the acquired data at the data source, including data cleaning, filtering and aggregation operations.

5. The virtual power plant cloud platform data transmission control system according to claim 4, characterized in that: The edge computing module (102) is equipped with an edge computing threshold, and when the data exceeds the threshold, corresponding processing is performed; The data thresholds include photovoltaic output greater than 120% of rated power and load power fluctuation greater than 20% within 10 seconds; The processing measures include primary measures and secondary measures. The primary measure is that the edge computing module (102) sends a frequency reduction command to the data acquisition module (101), and the corrected data is still uploaded to the cloud platform control module (103). The secondary measures are as follows: the edge computing module (102) sends a cut-off command to the execution module (104) to cut off the communication link of the abnormal data source, and at the same time switches to the temporary power supply of the energy storage device. The execution module (104) uploads an emergency alarm to the cloud platform control module.

6. The virtual power plant cloud platform data transmission control system according to claim 1, characterized in that: The cloud platform control module (103) uses reinforcement learning optimization algorithm to perform in-depth analysis and optimization processing on the data uploaded by the edge computing module (102), generates energy dispatch instructions, and communicates bidirectionally with the edge computing module (102) and the instruction execution module (104). The edge computing module (102) also includes a three-level data processing unit, namely a preprocessing unit, a feature engineering unit, and a scene analysis unit, which are used to perform in-depth analysis on the uploaded data. The preprocessing unit removes high-frequency noise through wavelet transform and aligns multi-source heterogeneous data based on GPS timestamps. The feature engineering unit extracts time-domain, frequency-domain, and semantic features and compresses the data dimension to 10% of the original size. The scene analysis unit calls the analysis model that matches the application scenario and outputs scenario-based control indicators. The scenario analysis unit predicts the power curve for the next 15 minutes using an improved LSTM neural network, with a MAE ≤ 3%. Based on the prediction results, the PSO algorithm is used to solve the optimal scheduling strategy, with the objective function being to minimize network loss and maximize renewable energy consumption. The isolated forest algorithm is then used to verify the anomalies in the optimization results.

7. The virtual power plant cloud platform data transmission control system according to claim 1, characterized in that: The instruction execution module (104) is connected to the distributed energy device through the PLC control device. According to the instructions issued by the cloud platform control module (103), it controls the operating status of the distributed energy device and feeds back the execution results to the cloud platform control module (103).

8. The virtual power plant cloud platform data transmission control system according to claim 1, characterized in that: The operation status control of the distributed energy equipment includes adjusting the charging power of the charging pile and the charging and discharging strategy of the energy storage equipment through the instruction execution module (104); the instruction execution module (104) adjusts the charging pile and the energy storage equipment through the following steps: Step 1: Receive optimization instructions from the cloud platform control module, including the target power of the charging pile and the energy storage charging and discharging threshold; Step 2: Send a PWM control signal to the charging pile controller via the CAN bus to adjust the rectifier output voltage; Step 3: Control the energy storage inverter via Modbus RTU protocol and dynamically adjust the charging and discharging current according to the grid frequency deviation.

9. The virtual power plant cloud platform data transmission control system according to claim 1, characterized in that: The data acquisition module (101) includes a multi-protocol gateway for converting between different communication protocols, ensuring that the data acquisition module (101) can communicate with various distributed energy devices. The multi-protocol gateway supports Modbus RTU / TCP, MQTT, and IEC61850 protocol conversion.

10. A data transmission control method based on a virtual power plant cloud platform, characterized in that, Includes the following steps: S1: Collect distributed resource data at a data sampling frequency of 10Hz through a multi-protocol gateway; S2: The edge computing module (102) performs preliminary processing on the collected data. The edge preprocessing delay is ≤200ms. The edge computing threshold is set. When the data exceeds the threshold, corresponding processing is performed. The data thresholds include photovoltaic output greater than 120% of rated power and load power fluctuation greater than 20% within 10 seconds. The processing measures include primary measures and secondary measures. The primary measure is that the edge computing module (102) sends a frequency reduction command to the data acquisition module (101), and the corrected data is still uploaded to the cloud platform control module (103). The secondary measures are as follows: the edge computing module (102) sends a cut-off command to the execution module (104) to cut off the communication link of the abnormal data source, and at the same time switches to the temporary power supply of the energy storage device. The execution module (104) uploads an emergency alarm to the cloud platform control module. S3: The cloud platform control module (103) uses optimization algorithms such as reinforcement learning to perform in-depth analysis on the data uploaded by the edge computing module (102) and generate the optimal energy scheduling scheme; The edge computing module (102) includes three levels of data processing units: a preprocessing unit, a feature engineering unit, and a scene analysis unit. These units are used to perform in-depth analysis on the uploaded data. The preprocessing unit removes high-frequency noise using wavelet transform and aligns multi-source heterogeneous data based on GPS timestamps. The feature engineering unit extracts time-domain, frequency-domain, and semantic features, compressing the data dimension to 10% of its original size. The scene analysis unit calls an analysis model that matches the application scenario and outputs scenario-based control indicators. S4: The cloud platform control module (103) sends the generated scheduling instructions to the instruction execution module (104) via the network; S5: After the instruction execution module executes the instruction (104), it feeds back the execution result to the cloud platform control module (103). The cloud platform control module (103) corrects and optimizes the scheduling scheme based on the feedback information.

Images