District level smart energy control method and system based on state regulation and control of red, yellow and green lamps

Abstract

The invention belongs to the technical field of power system intelligent regulation and control and new energy, and relates to a district level smart energy control method and system based on red, yellow and green three-color lamp state regulation and control, and the system collects data through a data collection module and transmits the data to an intelligent fusion terminal; the photovoltaic output trend prediction module processes the collected data and outputs a photovoltaic output prediction trend; the three-color state judgment module calculates a reverse load rate and dynamically judges the state of the current transformer area; the regulation and control strategy management module stores a regulation and control strategy library and generates a specific equipment control instruction according to input state signal matching; the power execution module receives an equipment control instruction, drives a power device to adjust load power and controls the three-color LED lamp group to display a corresponding state; and the monitoring feedback optimization module monitors the operation parameters after the regulation and control instruction is executed, evaluates the regulation and control effect, and feeds back the data to the photovoltaic output trend prediction module for optimization. According to the invention, the cooperative operation level of the district-level system can be effectively improved.

Description

Technical Field

[0001] This invention relates to the fields of intelligent power system control and new energy technology, specifically to a distribution area-level intelligent energy control method and system based on the status control of red, yellow and green indicator lights. Background Technology

[0002] In existing technologies, power equipment still suffers from problems such as low visualization, reliance on human experience for status judgment, and inability to achieve proactive control in terms of operational status monitoring and display.

[0003] To address this, utility model patent CN214755155U discloses a control panel for a medium-voltage gas-insulated switchgear that dynamically displays the working status of busbars. The control panel includes a control cabinet, and the control cabinet includes a control panel. The control panel is characterized by LED light strips for displaying the working status of the busbars. These LED light strips consist of three strips; each strip represents one phase, and the strips are 3mm wide. The three strips display yellow, green, and red colors respectively. The three strips are arranged in the order of yellow, green, and red from top, middle, and bottom, and left, middle, and right respectively. The light strips are positioned according to the location of the busbars within the control cabinet. The control panel displays the working status of the busbars within the control cabinet. A 30mm circular LED light is installed at the closing port; the green light indicates the circuit is open, with three phases: A, B, and C. Each phase of the busbar inside the control cabinet is equipped with three sensors: an upper bushing sensor, a vacuum switch tube lower port sensor, and a lower busbar bushing end sensor. The sensors generate secondary voltage signals, which are transmitted from the cabinet via aviation connectors. Each phase has three sensors; the sensors are connected to the LED strips; each sensor controls a section of the LED strip. Temperature sensors are installed on the copper busbars at the incoming, isolating, and outgoing ends of each phase inside the switch cabinet. The temperature on the copper busbars is transmitted via secondary wires through aviation connectors and finally displayed on the panel, enabling real-time display of the cabinet temperature.

[0004] The above technical solutions have made progress in improving the visualization of equipment status, but the following technical problems still exist: Limited to local status display and alarms, it lacks proactive control capabilities and is not suitable for comprehensive assessment of the overall operating status of the transformer area and execution of control strategies; it also lacks the ability to coordinate and optimize with the transformer area-level system, and cannot achieve dynamic power regulation and energy optimization management.

[0005] In view of this, it is very necessary to provide a smart energy control method and system at the substation level based on the state regulation of red, yellow and green lights, so as to solve the above-mentioned defects in the prior art. Summary of the Invention

[0006] The purpose of this invention is to address the technical problems in existing transformer substation control strategies, which are limited to local status display and alarms, lack active control capabilities, are unsuitable for comprehensive evaluation of the overall operating status of transformer substations, and lack collaborative optimization capabilities with transformer substation systems, thus failing to achieve dynamic power regulation and energy optimization management. This invention provides a transformer substation-level smart energy control method and system based on the status control of red, yellow, and green indicator lights to solve the aforementioned technical problems in the prior art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: In a first aspect, the present invention provides a district-level smart energy control method based on the state regulation of red, yellow, and green LED lights, comprising the following steps: Step S1: Data acquisition step, collecting device data through a multi-protocol compatible gateway and uploading the collected device data to the intelligent converged terminal; Step S2: The photovoltaic power output trend prediction step, based on the LSTM-GARCH hybrid model, uses meteorological data and historical photovoltaic power output data to generate a photovoltaic power output prediction curve with a granularity of the next 15 minutes; Step S3: The three-color operation status judgment step. Based on the real-time load data and photovoltaic output prediction curve, calculate the reverse load rate, dynamically determine and output the red light, yellow light or green light status. Step S4: The step of generating the control strategy matching, based on the determined three-color state, selects the corresponding strategy from the preset strategy library and generates control instructions; Step S5: Power execution and status indication steps, execute control commands, adjust equipment power, and drive the tri-color LED light group to display the current status of the station area with corresponding colors and brightness; Step S6: The step of effect monitoring and strategy optimization involves collecting operational data after adjustment, evaluating the effect, and feeding it back to the LSTM-GARCH hybrid model for optimization.

[0008] Secondly, the present invention also provides a district-level smart energy control system based on the state regulation of red, yellow, and green LED lights, comprising: The data acquisition module collects data through a multi-protocol compatible gateway and transmits it to the intelligent converged terminal; The photovoltaic output trend prediction module, based on the LSTM-GARCH hybrid model, processes the collected meteorological data and historical photovoltaic output data to output the photovoltaic output prediction trend. The three-color status judgment module calculates the reverse load rate based on real-time load data and photovoltaic output prediction trends, and dynamically judges the current status of the transformer area. The control strategy management module is used to store the control strategy library and generate specific equipment control commands based on the input status signals. The power execution module is used to receive equipment control commands, drive power devices to adjust load power, and control the tri-color LED light group to display the corresponding status. The monitoring feedback optimization module is used to monitor the operating parameters after the control commands are executed, evaluate the control effect, and feed the data back to the photovoltaic output trend prediction module for optimization.

[0009] The modules work together to achieve smart energy operation in the transformer substation, from data perception, intelligent prediction, status judgment, strategy generation to precise execution and closed-loop optimization.

[0010] The beneficial effects of this invention are as follows: This invention achieves unified perception of multi-source operating information within a transformer substation by collecting and centrally processing equipment data in real time. It breaks through the application limitations of only having local status display and alarm, and provides a continuous and complete data foundation for the comprehensive evaluation of the overall operating status of the transformer substation.

[0011] This invention incorporates meteorological information and historical photovoltaic power output data to obtain the trend of photovoltaic power change over a short time scale, enabling the operation of the power distribution area to make forward-looking judgments and creating conditions for proactive power regulation and energy arrangement.

[0012] This invention integrates load data with photovoltaic forecast results for calculation, and determines three operating states—red, yellow, and green—based on the reverse load rate. This provides an intuitive expression of the overall operating level and risk level of the transformer substation, enhancing the comprehensiveness and applicability of the substation operating status assessment.

[0013] This invention generates control commands based on an automatic matching strategy of three-color operating status, thereby achieving dynamic power regulation and energy optimization management at the substation level and improving the system's coordinated control capabilities.

[0014] This invention adjusts the power of the equipment in real time and simultaneously drives a tri-color LED light group to display the current operating status, so that the control results are consistent with the status indication, thereby enhancing the visualization of the operating status of the transformer area and the intuitiveness of the control execution.

[0015] This invention continuously collects and evaluates the operational data after regulation, and uses the evaluation results to update the prediction model and regulation strategy, thereby achieving rolling optimization of the regulation effect and improving the stability and continuous optimization capability of the transformer area under complex operating conditions.

[0016] This invention constructs a district-level smart energy control method based on red, yellow, and green status indicators. It organically integrates multi-source operation data acquisition, photovoltaic output prediction, operation status determination, control strategy generation, power execution, and effect feedback. This enables continuous perception and proactive intervention of the overall operation status of the district, going beyond simple local status display and alarms. Through state-driven energy storage charging and discharging and flexible load adjustment, the district is equipped with dynamic power regulation and energy optimization management capabilities. It can continuously evaluate the control effect and perform rolling optimization during operation, thereby improving the collaborative operation level, operational safety, and energy utilization efficiency of the district-level system.

[0017] Therefore, it is evident that the present invention has outstanding substantive features and significant progress compared with the prior art, and the beneficial effects of its implementation are also obvious. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0019] Figure 1 This is a flowchart of a district-level smart energy control method based on the status regulation of red, yellow, and green LED lights; Figure 2 This is a schematic diagram of a district-level smart energy control system based on the status regulation of red, yellow, and green LED lights. Detailed Implementation

[0020] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. The following embodiments are explanations of the present invention, but the present invention is not limited to the following implementation methods.

[0021] Example 1: like Figure 1 As shown, this embodiment provides a district-level smart energy control method based on the state regulation of red, yellow, and green LED lights, which includes the following steps: Step S1: Data acquisition step, collecting device data through a multi-protocol compatible gateway and uploading the collected device data to the intelligent converged terminal; Step S2: The photovoltaic power output trend prediction step, based on the LSTM-GARCH hybrid model, uses meteorological data and historical photovoltaic power output data to generate a photovoltaic power output prediction curve with a granularity of the next 15 minutes; Step S3: The three-color operation status judgment step. Based on the real-time load data and photovoltaic output prediction curve, calculate the reverse load rate, dynamically determine and output the red light, yellow light or green light status. Step S4: The step of generating the control strategy matching, based on the determined three-color state, selects the corresponding strategy from the preset strategy library and generates control instructions; Step S5: Power execution and status indication steps, execute control commands, adjust equipment power, and drive the tri-color LED light group to display the current status of the station area with corresponding colors and brightness; Step S6: The step of effect monitoring and strategy optimization involves collecting operational data after adjustment, evaluating the effect, and feeding it back to the LSTM-GARCH hybrid model for optimization.

[0022] In step S1: After accessing the field operation data of various operating devices within the distribution area through a multi-protocol compatible gateway installed in the integrated smart energy operation cabinet at the distribution area level, the communication protocol used by the data is identified based on the structural characteristics and communication identifiers of the field operation data messages. The original data frames of the field operation data are then split and parsed according to the corresponding protocol rules. A unified time identifier is added to each type of field operation data after splitting and parsing. Using the added time identifier as a benchmark, time alignment processing is performed on data from different devices and different sampling periods to generate unified format data with consistent structure and synchronized time, which is then transmitted to the intelligent fusion terminal. Upon receiving the unified format data, the intelligent fusion terminal performs integrity verification, eliminating missing, duplicate, or abnormally fluctuating unified format data. It also classifies and stores unified format data from different sources and of different types according to pre-set data tags, forming a data set that can be directly used for subsequent distribution area operation status judgment and control calculations, improving the reliability and accuracy of data application.

[0023] The on-site operational data includes meteorological data, photovoltaic (PV) operation data, and real-time load data. Meteorological data is acquired by an environmental sensing unit and uploaded via a multi-protocol compatible gateway. The environmental sensing unit includes a temperature and humidity sensor, a smoke detector, and a current transformer. The temperature and humidity sensor collects the temperature and relative humidity values ​​inside and around the integrated smart energy operation cabinet at the distribution level. The smoke detector collects the smoke concentration status inside the integrated smart energy operation cabinet at the distribution level. The current transformer collects the effective values ​​of the incoming and outgoing circuit currents of the integrated smart energy operation cabinet at the distribution level, reflecting the cabinet's own operating conditions. PV operation data is obtained by accessing the PV inverter through the multi-protocol compatible gateway, including historical PV output data and real-time PV output data. Real-time PV output data is the instantaneous output power value of the PV inverter within the current cycle, while historical PV output data is a sequence of PV output power stored at preset time intervals, used to characterize the historical characteristics of PV output changes over time. Real-time load data is obtained by accessing the smart meters and load terminals on the distribution transformer side through the multi-protocol compatible gateway.

[0024] The intelligent fusion terminal is installed in the integrated smart energy operation cabinet at the distribution area level, and is used to collect, process, and issue control commands to various types of field devices. The intelligent fusion terminal integrates an ARM Cortex-A72 processor, possessing high computing performance and multi-task parallel processing capabilities. It supports communication protocols such as DL / T 645, Modbus, and MQTT, and interacts with devices through a multi-protocol compatible gateway to achieve data acquisition and management.

[0025] The multi-protocol compatible gateway receives data under the IEC 61850 protocol, Modbus TCP protocol, and LoRa protocol, and can connect to devices from different manufacturers, solving the problem of inconsistent protocols among multiple devices.

[0026] The integrated smart energy operation cabinet at the distribution center level is a hardware platform for integrated photovoltaic power output prediction, load regulation, three-color operating status indication, and power execution. It supports various intelligent terminal devices. The cabinet design employs a hybrid liquid and air cooling system. Heat-conducting fins are installed on both sides of the cabinet, and a centrifugal fan is integrated internally to improve heat transfer and airflow efficiency. The overall heat dissipation efficiency is approximately 40% higher than traditional solutions, meeting the temperature control requirements of equipment operating in high-power-density environments. To ensure electromagnetic compatibility, the cabinet shell is made of 0.8 mm thick galvanized steel sheet and filled with conductive foam, meeting the GB / T 17626.3 standard. This ensures that high-frequency equipment is not subject to electromagnetic interference during operation within the cabinet and prevents interference to the external environment.

[0027] By collecting data, the problem of data silos caused by scattered equipment collection is avoided, and the reliability and real-time performance of data used for status judgment and control calculation are improved, providing a stable data foundation for subsequent steps.

[0028] In step S2: historical power output data and meteorological data from the dataset are input into the LSTM-GARCH hybrid model. The LSTM model learns the temporal correlation between meteorological data and historical photovoltaic power output data to obtain the photovoltaic power output trend prediction value for future time periods. The GARCH model is used to characterize the fluctuation characteristics of the photovoltaic power output sequence and correct the uncertainty of the photovoltaic power output trend prediction value. The output result of the LSTM model is used as the input of the GARCH model to dynamically correct the prediction value and generate a photovoltaic power output prediction curve with a granularity of 15 minutes for the future, and the prediction error is controlled within a preset range.

[0029] LSTM (Long Short-Term Memory) is an improved recurrent neural network model capable of handling long-term dependencies in time series data. LSTM models selectively retain and update information through forget gates, input gates, and output gates. In photovoltaic (PV) power output forecasting, the LSTM model uses historical PV power output sequences and corresponding meteorological data as input feature vectors, arranging them chronologically to form a multi-dimensional time series matrix. The LSTM model recursively learns the patterns of sequence changes and outputs predicted PV power output trends for future time periods, capturing short- to medium-term trends in PV power and providing a basis for subsequent fluctuation corrections.

[0030] The GARCH (Generalized Autoregressive Conditional Heteroskedasticity) model characterizes the volatility of time series. By relying on the sum of squared prediction errors and conditional variances from the past, it dynamically predicts the variance changes of the series and quantifies the uncertainty of the time series. In photovoltaic power output forecasting, the GARCH model corrects the volatility of the photovoltaic power output trend forecast value output by the LSTM model, and can capture the short-term fluctuations of photovoltaic power output, generating a photovoltaic power output forecast curve that includes short-term uncertainty, photovoltaic power output trend forecast value, and confidence interval.

[0031] By using LSTM-GARCH hybrid modeling, the generated photovoltaic power output prediction curve not only reflects the overall trend of future photovoltaic power output, but also includes short-term fluctuation information, providing a confidence range for each prediction time point, and realizing photovoltaic power output prediction at the granular level of the next 15 minutes. This enables the distribution area regulation to obtain forward-looking information before photovoltaic power changes, improves the accuracy and response speed of the three-color state judgment and power regulation strategy, thereby enhancing the photovoltaic absorption capacity and the operational stability of the distribution area.

[0032] In step S3: Real-time load data and photovoltaic output prediction curves are used as inputs to calculate the reverse load rate and assess the source-grid-load matching status. After the reverse load rate calculation is completed, the intelligent integrated terminal dynamically determines the three-color operating status based on preset thresholds. When the reverse load rate is higher than the red light threshold, a red light is output; when it is between the red and green light thresholds, a yellow light is output; and when it is lower than the green light threshold, a green light is output. The determination result is output in the form of LED signals to drive the execution of subsequent strategies such as energy storage and load regulation.

[0033] The reverse load rate is used to measure the degree of matching between photovoltaic output and load within a distribution area, and to assess the energy balance of the distribution area within a specific time period; the specific time period can be selected as 9:00-17:00 on a certain day. When photovoltaic output exceeds the load, the excess electricity flows back to the distribution network, generating a reverse load; when the load is greater than the photovoltaic output, the reverse load rate is negative, indicating a power shortage. The reverse load rate provides a direct understanding of the matching relationship between the source (photovoltaic), the grid (distribution transformer capacity), and the load; the reverse load rate formula is: R = (photovoltaic output prediction curve - real-time load data) / distribution transformer rated capacity × 100%; where the distribution transformer rated capacity is the rated total power of the distribution transformer equipment at the distribution area level. The three-color operation status includes LED red, yellow, and green three-color light groups, which achieve dynamic brightness adjustment through PWM dimming.

[0034] Step S3 enables real-time dynamic assessment of photovoltaic output and load in the distribution area, and quickly outputs the three-color operating status, thereby providing a forward-looking basis for energy storage charging and discharging and load regulation, and improving the operational stability of the distribution area and the renewable energy absorption capacity.

[0035] In step S4: Based on the determined three-color operating status, a corresponding strategy is selected from a preset three-color control strategy library, and control commands are generated according to the strategy content. The control commands include energy storage charging and discharging power commands, flexible load adjustment commands, and other controllable equipment operation commands. The generated control commands are sent to energy storage, load terminals, and charging piles through the power control controller and flexible load controller to achieve energy balance control in the distribution area. The execution strategy is dynamically adjusted based on predicted data and actual feedback within short time intervals to ensure source-grid-load-storage matching.

[0036] The corresponding strategies and control instructions in the three-color control strategy library include: When the LED light is on, the distribution area is in an emergency state of either excess photovoltaic output or insufficient load. The intelligent integrated terminal generates control commands based on the red light strategy. The energy storage charges at its rated power to absorb the excess photovoltaic output, and the flexible load is reduced by about 20%, reducing the load pressure on the distribution area. The control commands are sent to the energy storage and load terminals for execution through the power regulation controller and the flexible load controller, and the LED lights indicate the red light status.

[0037] When the yellow light is on, the energy in the distribution area is close to equilibrium but still requires fine-tuning. The intelligent integrated terminal generates gradient control commands based on the yellow light strategy, and the energy storage charging and discharging power is adjusted according to the gradient. At the same time, the response delay of the flexible load is controlled within 5 seconds to reduce short-term power fluctuations. The control commands are executed through the power regulation controller, load controller, and charging pile, and the LED lights indicate the yellow light status.

[0038] In the green light state, the distribution area operates in a basically balanced manner, requiring no active control. The intelligent integrated terminal generates instructions based on the green light strategy, recording only photovoltaic output data, load data, and energy storage data for subsequent analysis and strategy optimization. LED lights indicate the green light status. Energy storage remains on standby, without charging or discharging, and flexible loads do not undergo power adjustments, ensuring stable operation of the distribution area while providing complete historical data support for subsequent control.

[0039] Step S4 achieves efficient matching and automated execution of the three-color operating status and control strategy, enabling energy storage charging and discharging and flexible load adjustment to quickly respond to energy imbalances in the distribution area, ensuring dynamic matching between photovoltaic output and load, and improving the renewable energy absorption capacity and economic benefits.

[0040] In step S5: the intelligent fusion terminal receives the three-color operating status and control commands. The intelligent fusion terminal then sends the control commands to the power regulation controller, flexible load controller, and energy storage terminal, adjusting the power of each device in real time. Based on the three-color operating status, it drives the three-color LED light groups in the distribution area to display the current distribution area status with corresponding colors and brightness, forming an early warning signal. The control power is adjusted according to actual load data and real-time photovoltaic output data, and the LED light status is updated synchronously, achieving synchronization between equipment power regulation and status indication.

[0041] The power control controller is installed in the integrated smart energy operation cabinet at the distribution area level and is used to quickly and accurately regulate the power of the energy storage system and controllable loads in both directions. This power control controller incorporates IGBT power devices and has bidirectional power regulation capabilities within the range of 0–100 kW. It can realize the charging, discharging, and smooth power regulation of energy storage according to control commands issued by the intelligent integrated terminal. During operation, the power control controller responds to power changes in real time through a high-speed control loop, with a response time of no more than 20 ms, enabling it to quickly track fluctuations in photovoltaic output and changes in load demand.

[0042] For example, in the red-light status control process, the transformer substation is operating with high real-time photovoltaic output data and near-maximum load. On-site operation data shows that the photovoltaic inverter output power is 120 kW, the energy storage system SOC is 35%, and the transformer load rate reaches 88%. After analyzing the above data, the intelligent integrated terminal calculates that the substation's reverse load rate is 82%, exceeding the red-light warning threshold, thus determining that the substation has entered the red-light operating state and driving the red LED light to illuminate. Control commands are issued according to the red-light control strategy, with the power control controller activating the energy storage to charge at 25 kW, while the flexible load controller reduces unnecessary loads, such as lowering the air conditioner set temperature to 26°C. After the control is executed, the substation load rate drops to 75% within 10 seconds, and the power difference between photovoltaic output and load is controlled within 5 kW, achieving rapid and effective recovery of the operating state.

[0043] During the dynamic optimization process for the yellow light status, the operating status of the transformer substation is pre-regulated based on the photovoltaic output prediction curve. The intelligent integrated terminal receives the photovoltaic output prediction curve and real-time load data. The peak value of the photovoltaic output prediction curve is 90kW, and the real-time load data value is 70kW. Based on the prediction results, the transformer substation is determined to be in the yellow light operating state, and the control strategy is continuously optimized using model predictive control (MPC). Specifically, MPC optimizes the energy storage charging and discharging plan in 3-minute cycles, controlling the energy storage to discharge at 15kW through the power regulation controller, while limiting the charging power of the charging piles to 50% of the rated value. Through the above dynamic control measures, the power difference between photovoltaic output and load is always kept within 8kW, ensuring the stability and energy balance of the transformer substation operation.

[0044] Step S5 enables real-time linkage between the three-color operating status and specific power control actions, achieving rapid and precise execution of energy storage, load, and charging facilities. The three-color LEDs provide intuitive feedback on the transformer substation's operating status. This step allows for timely restoration of energy balance in the substation when photovoltaic output fluctuates or load changes, improving control response speed and operational stability.

[0045] In step S6: the intelligent fusion terminal collects the operating data of the transformer area after the control is executed as input, and compares and evaluates the operating effect before and after the control. After the evaluation is completed, the evaluation results and the operating data of the corresponding time period are fed back to the LSTM-GARCH hybrid model to optimize the parameters of the LSTM-GARCH hybrid model and the control strategy, and outputs the updated LSTM-GARCH hybrid model parameters for subsequent prediction and control.

[0046] Step S6 enables closed-loop monitoring and continuous optimization of the control effect, allowing the LSTM-GARCH hybrid model and control strategy to be continuously adaptively corrected based on actual operating results, reducing prediction errors and control deviations, and enhancing the stability and reliability of the transformer area operation.

[0047] Example 2: like Figure 2 As shown, this embodiment provides a district-level smart energy control system based on the state control of red, yellow, and green LED lights, including: Data acquisition module 1 receives data from different communication protocols through a multi-protocol compatible gateway, performs protocol identification, data frame parsing, and time synchronization processing, so that data from different sampling periods and sources form structurally consistent data under the same time reference and are transmitted to the intelligent fusion terminal. The intelligent fusion terminal performs integrity verification, removes missing, duplicate, or abnormally fluctuating data, and classifies and stores data from different sources and types according to pre-set data tags, forming a data set that can be directly used for subsequent judgment of the operating status of the transformer area and control calculation. This breaks down data silos, improves data integrity and timeliness, and provides stable basic data for the generation of photovoltaic power output prediction and control strategies.

[0048] The photovoltaic (PV) output trend prediction module 2 processes meteorological data and historical PV output data in the dataset based on an LSTM-GARCH hybrid model. By learning the trend characteristics of PV output changes over time and correcting for random fluctuations in the prediction results, it outputs a PV output prediction trend with temporal continuity and foresight. This provides a basis for subsequent operational status judgment and control decisions, improves the accuracy of PV output prediction, and enables distribution areas to know the trend of PV power changes in advance, thereby optimizing energy storage scheduling and load control, and improving the capacity for renewable energy consumption.

[0049] The three-color status judgment module 3 analyzes and calculates the current and short-term operating status of the distribution area based on real-time load data and photovoltaic output forecast trends. By calculating the reverse load rate, it assesses the matching degree between photovoltaic output and load, and dynamically judges the red, yellow, or green light operating status of the distribution area in combination with preset thresholds, forming a clear status judgment signal. This enables real-time visualization and dynamic evaluation of the distribution area's operating status, providing a forward-looking reference for energy storage charging and discharging and load regulation, and improving regulation response speed and distribution area stability.

[0050] The control strategy management module 4 manages the three-color operating status in a unified manner and internally stores a control strategy library. When it receives the status judgment signal output by the three-color status judgment module 3, it selects a matching control scheme from the corresponding control strategy library and generates specific equipment control instructions. This provides a clear execution basis for subsequent power adjustment, achieving efficient matching between status and strategy. It ensures that energy storage and controllable loads can respond quickly under different operating conditions, improving the energy balance capability and economic benefits of the distribution area.

[0051] The power execution module 5 is used to execute equipment control commands, drive the power regulation controller to adjust the power of energy storage devices, controllable loads and charging facilities, and control the three-color LED light group to display the color and brightness corresponding to the current operating status, so as to realize the synchronization of power execution and status indication, quickly and accurately implement the regulation strategy, restore the energy balance of the transformer area in real time, and improve the operation monitoring and early warning capabilities through LED visualization, thereby enhancing system stability.

[0052] The monitoring feedback optimization module 6 continuously monitors the operation process after the execution of the control command, collects operating parameters including energy storage status, load changes, actual photovoltaic output and status switching, evaluates the effects before and after control, and feeds the evaluation data back to the photovoltaic output trend prediction module 2 to optimize the LSTM-GARCH hybrid model and control strategy, continuously improve the stability and control accuracy of the distribution area, realize the continuous optimization of control effect and adaptive update of the prediction model, so that the distribution area can maintain efficient operation under different photovoltaic output and load changes, improve the utilization rate of renewable energy and the overall control accuracy.

[0053] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. The methods disclosed in the embodiments are described simply because they correspond to the systems disclosed in the embodiments; relevant details can be found in the method section.

[0054] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0055] In the embodiments provided by this invention, it should be understood that the disclosed systems, methods, and approaches can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0056] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0057] In addition, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit.

[0058] Similarly, in the various embodiments of the present invention, each processing unit can be integrated into a functional module, or each processing unit can exist physically, or two or more processing units can be integrated into a functional module.

[0059] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0060] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0061] The above-disclosed embodiments are merely preferred embodiments of the present invention, but the present invention is not limited thereto. Any non-creative variations that can be conceived by those skilled in the art, as well as any improvements and modifications made without departing from the principles of the present invention, should fall within the protection scope of the present invention.

Claims

1. A transformer area level intelligent energy control method based on red, yellow and green three-color light state regulation, characterized by, The method comprises the following steps: Step S1: a data collection step, collecting device data through a multi-protocol compatible gateway, and uploading the collected device data to a smart fusion terminal; Step S2: a photovoltaic output trend prediction step, based on an LSTM-GARCH hybrid model, using meteorological data and historical photovoltaic output data to generate a 15-minute-granularity photovoltaic output prediction curve; Step S3: a three-color running state judgment step, calculating the reverse load rate according to real-time load data and the photovoltaic output prediction curve, dynamically determining and outputting a red light, yellow light or green light state; Step S4: a regulation strategy matching generation step, selecting a corresponding strategy from a preset strategy library according to the determined three-color state, and generating a control instruction; Step S5: a power execution and state indication step, executing the control instruction, adjusting the device power, and driving the three-color LED light group to display the current district state in the corresponding color and brightness; Step S6: an effect monitoring and strategy optimization step, collecting the running data after regulation, performing effect evaluation, and feeding back to the LSTM-GARCH hybrid model for optimization.

2. The method according to claim 1, wherein the method is characterized in that, In step S1, the multi-protocol compatible gateway installed in the smart energy operation integrated cabinet of the district accesses the field operation data of each running device in the district, identifies the communication protocol used by the field operation data according to the message structure characteristics and communication identifier of the field operation data, splits and analyzes the original data frame of the field operation data according to the corresponding protocol rules, adds a unified time identifier to each type of field operation data after splitting and analysis, and uses the added time identifier as a reference to align the data of different devices and different sampling periods in time, to generate unified format data with consistent structure and synchronized time, and transmit to the smart fusion terminal. After receiving the unified format data, the smart fusion terminal performs integrity check, removes missing, repeated or abnormal fluctuation unified format data, and stores different sources and different types of unified format data according to pre-set data tags, forming a data set that can be directly used for subsequent district running state judgment and regulation calculation.

3. The method according to claim 2, wherein the method is characterized in that, The field operation data includes meteorological data, photovoltaic operation data and real-time load data, wherein the meteorological data is obtained by an environment perception unit and uploaded through the multi-protocol compatible gateway. The environment perception unit includes a temperature and humidity sensor, a smoke detector and a current transformer. The temperature and humidity sensor collects the temperature and relative humidity values inside and around the smart energy operation integrated cabinet. The smoke detector collects the smoke concentration state quantity inside the smart energy operation integrated cabinet. The current transformer collects the line current effective value of the smart energy operation integrated cabinet. The photovoltaic operation data is obtained by accessing the photovoltaic inverter through the multi-protocol compatible gateway, including historical photovoltaic output data and real-time photovoltaic output data. The real-time photovoltaic output data is the instantaneous output power value in the current period of the photovoltaic inverter, and the historical photovoltaic output data is the photovoltaic output power sequence stored at a preset time interval. The real-time load data is obtained by accessing the smart meter on the side of the distribution transformer and the load terminal through the multi-protocol compatible gateway. The intelligent fusion terminal is arranged in a smart energy operation integrated cabinet at a transformer area level, and is used for realizing data collection, processing and control instruction issuing of multiple types of field devices; the intelligent fusion terminal integrates an ARM Cortex-A72 processor; The multi-protocol compatible gateway receives data under IEC 61850 protocol, Modbus TCP protocol and LoRa protocol.

4. The method according to claim 3, wherein, In step S2, the historical output data and the weather data in the data set are input into the LSTM-GARCH hybrid model, the LSTM model learns the time sequence correlation between the weather data and the historical photovoltaic output data, and a photovoltaic output trend prediction value of a future time period is obtained; The GARCH model is used for describing the volatility characteristics of the photovoltaic output sequence, correcting the uncertainty of the photovoltaic output trend prediction value, taking the output result of the LSTM model as the input of the GARCH model, dynamically correcting the prediction value, and generating a photovoltaic output prediction curve with a granularity of 15 minutes in the future.

5. The method according to claim 4, wherein the red, yellow and green light states are used to control the intelligent energy control of the transformer area. In step S3, the real-time load data and the photovoltaic output prediction curve are taken as inputs to calculate the reverse load rate, evaluate the source-grid-load matching condition, and after the reverse load rate is calculated, the intelligent fusion terminal dynamically determines the three-color operation state according to the preset threshold value, outputs a red light state when the reverse load rate is higher than a red light threshold value, outputs a yellow light state when the reverse load rate is between the red light threshold value and a green light threshold value, and outputs a green light state when the reverse load rate is lower than the green light threshold value, and the determination result is output in the form of an LED signal; ​ The reverse load rate is used to measure the matching degree of photovoltaic output and load in the transformer area, and to evaluate the energy balance state of the transformer area in a specific time period; when the photovoltaic output exceeds the load, the excess power flows reversely to the distribution network, generating reverse load; when the load is greater than the photovoltaic output, the reverse load rate is negative, indicating that there is a power shortage; the reverse load rate formula is: R=(photovoltaic output prediction curve-real-time load data) / distribution transformer rated capacity*100%; wherein the distribution transformer rated capacity is the rated total power of the transformer area level distribution transformer equipment, and the three-color operation state includes an LED red-yellow-green three-color light group, and dynamic brightness adjustment is realized through PWM dimming.

6. The method according to claim 5, wherein the red, yellow and green light states are used to control the intelligent energy control of the transformer area. In step S4, according to the determined three-color operation state, a corresponding strategy is selected from a three-color control strategy library, and a control instruction is generated according to the strategy content; the control instruction includes energy storage charging and discharging power instruction, flexible load adjustment instruction and other controllable device operation instruction; the generated control instruction is sent to the energy storage, load terminal and charging pile through the power regulation controller and the flexible load controller; ​ The corresponding strategy and control instruction in the three-color control strategy library include: In the red light state, the intelligent fusion terminal generates a control instruction according to the red light strategy, the energy storage charges at a rated power to absorb excess photovoltaic output, the flexible load is reduced by 20%, and the load pressure of the transformer area is reduced, the control instruction is issued to the energy storage and load terminal through the power regulation controller and the flexible load controller, and the LED light displays a red light state. In the yellow light state, the intelligent fusion terminal generates gradient regulation instructions according to the yellow light strategy, the energy storage charging and discharging power is adjusted according to the gradient, the flexible load response delay control is within 5 seconds, the control instructions are executed through the power regulation controller, the flexible load controller and the charging pile, and the LED lamp displays the yellow light state; In the green light state, no active regulation is needed, the intelligent fusion terminal generates instructions according to the green light strategy, only records the photovoltaic output data, load data and energy storage data, and the LED lamp displays the green light state; the energy storage remains on standby, does not charge or discharge, and the flexible load does not adjust the power.

7. The method according to claim 6, wherein the red, yellow and green light states are used to control the intelligent energy control of the transformer area. In step S5, the intelligent fusion terminal receives the three-color operation state and control instructions, the intelligent fusion terminal sends the control instructions to the power regulation controller, the flexible load controller and the energy storage terminal, adjusts the power of each device in real time, drives the three-color LED lamp group in the area according to the three-color operation state, displays the current area state with corresponding colors and brightness, forms a warning signal, adjusts the control power according to the actual load data and real-time photovoltaic output data, and synchronously updates the LED lamp state. ​ 8. The method according to claim 7, wherein the red, yellow and green light states are used to control the intelligent energy control of the transformer area. In step S6, the intelligent fusion terminal collects the area operation data after the regulation and execution as input, compares and analyzes the operation effects before and after the regulation, and evaluates the effects; after completing the evaluation, the evaluation results and the operation data of the corresponding period are fed back to the LSTM-GARCH hybrid model, the LSTM-GARCH hybrid model and the regulation strategy parameters are optimized, and the updated LSTM-GARCH hybrid model parameters are output. ​ 9. A transformer area level intelligent energy control system based on red, yellow and green three-color light state regulation, characterized in that, It comprises: a data acquisition module (1), a photovoltaic output trend prediction module (2), a three-color state judgment module (3), a regulation strategy management module (4), a power execution module (5) and a monitoring feedback optimization module (6); The data acquisition module (1) collects data through a multi-protocol compatible gateway and transmits the data to the intelligent fusion terminal; The photovoltaic output trend prediction module (2) processes the collected meteorological data and historical photovoltaic output data based on the LSTM-GARCH hybrid model, and outputs the photovoltaic output prediction trend; The three-color state judgment module (3) calculates the reverse load rate according to the real-time load data and the photovoltaic output prediction trend, and dynamically judges the state of the current area; The regulation strategy management module (4) is used for storing the regulation strategy library and generating specific device control instructions according to the input state signal; The power execution module (5) is used for receiving the device control instructions, driving the power device to adjust the load power, and controlling the three-color LED lamp group to display the corresponding state; The monitoring feedback optimization module (6) is used for monitoring the operation parameters after the execution of the regulation instructions, evaluating the regulation effect, and feeding back the data to the photovoltaic output trend prediction module (2) for optimization.

10. The area-level intelligent energy control system based on red-yellow-green three-color light state regulation according to claim 9, characterized in that, The data acquisition module (1) receives data from different communication protocols through a multi-protocol compatible gateway, performs protocol identification, data frame analysis and time synchronization processing operations, forms consistent data structure, and transmits to the intelligent fusion terminal. The intelligent fusion terminal performs integrity check, eliminates missing, repeated or abnormal fluctuation data, and classifies and stores different sources and different types of data according to pre-set data labels, forming a data set that can be directly used for subsequent substation operation state judgment and control calculation. The photovoltaic output trend prediction module (2) processes the meteorological data and historical photovoltaic output data in the data set based on the LSTM-GARCH hybrid model, learns the trend characteristics of photovoltaic output change over time, and corrects the random fluctuations in the prediction results, and outputs the photovoltaic output prediction trend. The three-color state judgment module (3) analyzes and calculates the current and short-term operation status of the substation according to real-time load data and photovoltaic output prediction trend, calculates the reverse load rate to evaluate the matching degree between photovoltaic output and load, and dynamically judges the red, yellow or green running state of the substation according to the pre-set threshold, and forms a state judgment signal. The control strategy management module (4) uniformly manages the three-color running state, internally stores the control strategy library, selects the matching control scheme from the corresponding control strategy library after receiving the state judgment signal output by the three-color state judgment module (3), and generates specific device control instructions. The power execution module (5) is used to execute the device control instructions, drive the power regulation controller to adjust the power of the energy storage device, controllable load and charging facility, and control the three-color LED lamp group to display the color and brightness corresponding to the current running state. The monitoring feedback optimization module (6) continuously monitors the running process after the control instruction is executed, collects the running parameters including the energy storage state, load change, actual photovoltaic output and state switching, evaluates the effect before and after the control, and feeds back the evaluation data to the photovoltaic output trend prediction module (2) to optimize the LSTM-GARCH hybrid model.

Images