Cooperative control method based on optical storage and charging and micro-grid

Abstract

The invention relates to the technical field of micro-grid control, in particular to a cooperative control method based on optical storage and charging and a micro-grid, and the method comprises the steps: collecting multi-source data in real time; predicting a photovoltaic output prediction value; screening temporary units; determining an energy storage unit; determining a collaborative exception unit; dynamically correcting the power threshold; and executing power adjustment control. According to the method, a self-adaptive closed loop is constructed by organically coupling multi-dimensional real-time parameters of output power, a charge state value, a load demand and a user behavior: a power fluctuation threshold value and a charging request growth rate jointly trigger temporary unit screening, so that quick response to sudden load change is ensured; the charge state value and the queuing duration jointly determine energy storage unit scheduling, and a power generation side and a demand side are balanced; and then, a coordination index is generated through the reconnection frequency and power-load normalization weighting, coordination abnormity is accurately recognized, and the problem that the coordination control response speed is low due to model staticization and single index judgment is effectively solved.

Description

Technical Field

[0001] The present invention relates to the field of microgrid control technology, and in particular to a method for collaborative control based on photovoltaic storage and charging and a microgrid. Background Art

[0002] With the large-scale deployment of distributed photovoltaic and electric vehicle charging infrastructure, residential building-level microgrids are rapidly evolving toward integrated, coordinated control of photovoltaic, energy storage, and charging. However, the inherent volatility of photovoltaic power generation, the charging and discharging limitations of energy storage systems, and the sudden increase in charging pile loads all pose significant challenges to grid stability. Therefore, a coordinated control strategy for photovoltaic, energy storage, and charging with microgrids is urgently needed to enhance the microgrid's ability to respond quickly to fluctuating and sudden demand and improve its overall dispatch efficiency.

[0003] Patent document with publication number CN117254526A discloses an energy collaborative optimization control method for a photovoltaic, storage, charging and inspection microgrid integrated station. The method includes: S1, collecting load data in the photovoltaic, storage, charging and inspection microgrid integrated station and the power generation data of the photovoltaic system; S2, establishing load models in different time periods based on the historical load data of the transformer; S3, establishing power generation models of the photovoltaic system in different time periods based on the historical power generation data; S4, comparing the load model of the transformer with the power generation model of the corresponding time period and the preset output power of the energy storage system; S5, switching different working modes based on the comparison results, the collective electricity price time and the real-time power generation power of the photovoltaic system, and adjusting the working status of the photovoltaic system, energy storage system and power grid to meet the load value requirements.

[0004] It can be seen that the energy collaborative optimization control method of the photovoltaic storage charging and inspection integrated microgrid station has the following problems: the transformer load model is simply compared with the photovoltaic power generation model, and there is a lack of real-time response capabilities to the dynamic coupling between the two and sudden changes on the load side, resulting in the separation of the load model and the power generation model; the model is established only based on a fixed time period, which cannot adapt to sudden fluctuations in load and power generation, and it is difficult to adjust the model window in time; the preset energy storage output is directly adopted without a dynamic adjustment strategy, and the energy storage charging and discharging cannot be flexibly allocated according to photovoltaic fluctuations or sudden load increases; different working modes are only based on a few sets of comparison results and electricity price period switching, and there is a lack of support for fine-grained strategies at the unit level or feeder level, making it difficult to achieve local optimization. Summary of the Invention

[0005] To this end, the present invention provides a collaborative control method based on photovoltaic storage and microgrid, which is used to overcome the problem of low collaborative control response speed caused by model staticization and single indicator judgment in the existing technology through dynamic threshold adjustment driven by real-time multi-dimensional data.

[0006] To achieve the above objectives, the present invention provides a method for coordinated control of photovoltaic storage and charging and microgrid, comprising:

[0007] Real-time data collection is used to collect the output power of each photovoltaic unit on each feeder within the photovoltaic array in the microgrid based on the preset photovoltaic power generation power, the status of the high-current load switches in each feeder, the charge state of the energy storage system, the load demand at the building transformer end, the charging request growth rate at the target side, the average queue time, and the frequency of interruption and reconnection;

[0008] Predicting a photovoltaic output value based on all the output power, the state of charge value, the load demand, the charging request growth rate, the average queuing time, and the interruption and reconnection frequency within a preset historical period and a preset prediction model;

[0009] screening out a plurality of temporary units according to the output power, a preset total power fluctuation threshold, and the charging request growth rate;

[0010] Determine a number of energy storage units according to the average queuing time, the output power of each of the temporary units, and the state of charge value;

[0011] Determining a number of coordinated abnormal units according to the interruption and reconnection frequency, the output power of each of the energy storage units, and the load demand;

[0012] Adjusting the preset total power fluctuation threshold according to the layout position and number of the coordinated abnormal units in each feeder and the state value of the high-current load switch to obtain an adjusted power fluctuation threshold;

[0013] Correcting the photovoltaic output prediction value according to the number of the coordinated abnormal units re-determined by using the adjusted power fluctuation threshold within a preset correction period to obtain a corrected prediction value;

[0014] The control instruction of adjusting the preset photovoltaic power generation power is executed on the collaborative abnormality unit according to the corrected prediction value and the preset prediction value range.

[0015] Furthermore, the process of selecting a plurality of temporary units according to the output power, the preset total power fluctuation threshold, and the charging request growth rate includes:

[0016] Calculating the sum of all the output powers to obtain the total output power;

[0017] Calculating the standard deviation of the total output power within the preset temporary time length to obtain a total power fluctuation value;

[0018] When the total power fluctuation value is greater than the preset total power fluctuation threshold and the charging request growth rate is greater than a preset standard growth rate, a plurality of temporary units are selected according to the output power and the total power fluctuation value.

[0019] Furthermore, the temporary units selected according to the output power and the total power fluctuation value include:

[0020] Calculating the standard deviation of all the output powers of the photovoltaic units within the next preset temporary time period to obtain an output power fluctuation value;

[0021] Calculating a relative deviation between the output power fluctuation value and the total power fluctuation value to obtain a temporary determination value;

[0022] When the temporary determination value is greater than a preset temporary determination threshold, the photovoltaic unit is determined to be the temporary unit, so as to screen out a number of temporary units.

[0023] Furthermore, the process of determining a number of energy storage units according to the average queuing time, the output power of each temporary unit, and the state of charge value includes:

[0024] When the state of charge value is less than a preset state of charge threshold, calculating a difference between the preset state of charge threshold and the state of charge value to obtain a charge difference;

[0025] When the charge difference is greater than a preset charge difference threshold, the average queuing time is less than a preset time threshold, and the output power is greater than a preset standard power, determining that the temporary unit is the energy storage unit to determine a number of energy storage units;

[0026] When the charge difference is greater than a preset charge difference threshold and the average queuing time is greater than or equal to the preset time threshold, a number of energy storage units are determined according to the output power within a preset determined time.

[0027] Furthermore, the process of determining a number of energy storage units according to the output power within a preset determined time period includes:

[0028] Calculating the standard deviation of the output power within a predetermined time period to obtain a determined power fluctuation value;

[0029] When the determined power fluctuation value is greater than a preset determined fluctuation threshold, the temporary unit is determined to be the energy storage unit to determine a number of energy storage units.

[0030] Furthermore, the process of determining a plurality of coordinated abnormal units according to the interruption and reconnection frequency, the output power of each energy storage unit, and the load demand includes:

[0031] Obtaining the interruption and reconnection frequency within a preset collaboration time length to obtain a reconnection frequency set;

[0032] Obtaining the output power within the preset coordination time to obtain an output power set;

[0033] Obtaining the load demand within the preset coordination time to obtain a load demand set;

[0034] Performing maximum-minimum normalization processing on the output power at each moment within the preset coordination duration according to the output power set to obtain a power normalization value;

[0035] Performing maximum-minimum normalization processing on the load demand at each moment within the preset coordination time according to the load demand set to obtain a demand normalization value;

[0036] Calculating the product of the power normalization value and the preset power weight to obtain a first product, and calculating the product of the demand normalization value and the preset demand weight to obtain a second product;

[0037] calculating the sum of the first product and the second product to obtain a synergy index;

[0038] Acquire all the synergy indexes to obtain a synergy index set;

[0039] Calculating the correlation coefficient between the reconnection frequency set and the collaboration index set to obtain a collaboration anomaly degree;

[0040] When the coordination abnormality degree is greater than a preset standard abnormality degree, the energy storage unit is determined to be the coordination abnormality unit, so as to determine a plurality of coordination abnormality units.

[0041] Furthermore, the preset total power fluctuation threshold is adjusted according to the layout position and number of the coordinated abnormal units in each feeder and the state value of the high-current load switch, and the process of adjusting the power fluctuation threshold includes:

[0042] Obtaining the layout position of the coordinated abnormal units in each of the feeders to obtain the relative distances between the coordinated abnormal units and the starting point of the feeder;

[0043] Obtaining the feeder number to which each of the abnormal collaborative units belongs, and counting the number of abnormal collaborative units in each feeder according to the feeder number to obtain the number of units;

[0044] Performing maximum-minimum normalization processing on the relative distance at the current moment according to all the relative distances to obtain a plurality of normalized distances;

[0045] Calculate the standard deviation of all the normalized distances to obtain the distribution concentration;

[0046] calculating a concentration factor based on the distribution concentration and the number of units;

[0047] Normalizing the current distribution concentration according to all the distribution concentrations within the preset adjustment time to obtain a normalized concentration;

[0048] Normalizing the current number of units according to the total number of units within the preset adjustment time to obtain a normalized number;

[0049] Performing a weighted summation on a preset concentration weight, the normalized concentration degree, a preset quantity weight, the normalized quantity, a preset state value weight, and the state value of the high-current load switch to obtain a risk index;

[0050] When the risk index is greater than a preset risk index threshold, the preset total power fluctuation threshold is increased according to a relative deviation between the risk index and the preset risk index threshold and a preset adjustment coefficient to obtain the adjusted power fluctuation threshold.

[0051] Furthermore, the photovoltaic output prediction value is corrected according to the number of the coordinated abnormal units re-determined by using the adjusted power fluctuation threshold within a preset correction period, and the process of obtaining the corrected prediction value includes:

[0052] Calculating the standard deviation of the unit quantity within the preset correction period to obtain a corrected quantity fluctuation value;

[0053] When the corrected quantity fluctuation value is greater than a preset corrected quantity fluctuation threshold, the photovoltaic output prediction value is increased according to a relative deviation between the corrected quantity fluctuation value and the preset corrected quantity fluctuation threshold and a preset correction coefficient to obtain the corrected prediction value.

[0054] Furthermore, the process of executing the control instruction for adjusting the preset photovoltaic power generation power on the coordinated abnormal unit according to the modified predicted value and the preset predicted value range includes:

[0055] When the corrected predicted value is greater than the maximum value of the preset predicted value range, executing a control instruction to reduce the preset photovoltaic power generation power according to a relative deviation between the corrected predicted value and the maximum value of the preset predicted value range and a preset control coefficient;

[0056] When the corrected predicted value is less than the minimum value of the preset predicted value range, a control instruction to increase the photovoltaic power generation power is executed according to the relative deviation between the minimum value of the preset predicted value range and the corrected predicted value and the preset control coefficient.

[0057] Furthermore, the process of predicting the photovoltaic output prediction value based on all the output power, the state of charge value, the load demand, the charging request growth rate, the average queuing time, the interruption and reconnection frequency, and a preset prediction model within a preset historical period includes:

[0058] All the output power, state of charge value, charging pile load demand, target side charging request growth rate, average queue time and interruption reconnection frequency are time series aligned, missing value filled and normalized to construct a multi-dimensional input feature matrix;

[0059] The multi-dimensional input feature matrix is ​​input into the preset prediction model to predict the photovoltaic output prediction value.

[0060] Compared with the existing technology, the beneficial effect of the present invention lies in that by organically coupling multi-dimensional real-time parameters such as output power, state of charge value, load demand and user behavior (request growth rate, queue time, reconnection frequency), an adaptive closed loop is constructed in the six major links of "prediction, screening, identification, threshold adjustment, prediction correction, and control execution": First, the power fluctuation threshold and the charging request growth rate jointly trigger temporary unit screening to ensure a rapid response to sudden load changes; secondly, the state of charge value and the queue time jointly determine the energy storage unit scheduling to balance the power generation side and the demand side; then the reconnection frequency and power-load normalization weighting are used to generate a synergy index to accurately identify collaborative anomalies; the distribution location, number and load switch status of abnormal units at the feeder level are jointly mapped to the threshold adjustment coefficient to achieve regional risk perception; the secondary correction of the predicted value within the correction period compensates for the model deviation, and finally the photovoltaic power regulation command is executed according to the correction error range, which can significantly improve the stability, response speed and energy utilization of the system, and effectively solve the problem of low collaborative control response speed caused by model staticization and single indicator judgment.

[0061] Furthermore, through a screening mechanism based on the dual trigger logic of dynamic volatility detection and load growth signal recognition, the volatility of output power is organically combined with the load behavior on the demand side (such as the surge in electric vehicle charging). The total power fluctuation value, as an important statistical indicator reflecting the stability of the photovoltaic system, forms the basis of subjective evaluation together with the output power; while the charging request growth rate reflects the dynamic energy demand on the target (user) side. The two together determine whether temporary intervention targets need to be selected. By comprehensively judging the "supply and demand fluctuation amplitude" and "future load pressure", not only can potential power supply instability be discovered in advance, but also precise, localized, and controllable targets can be provided for subsequent energy storage scheduling, effectively improving the system's response speed and control accuracy to sudden load changes, and achieving more fine-grained photovoltaic, storage, and charging coordinated control.

[0062] Furthermore, by introducing a fluctuation determination mechanism at the photovoltaic unit level, it is possible to further identify the local sources of fluctuation that have the greatest impact on system stability in the context of large overall power fluctuations and rapidly increasing charging demand. The output power fluctuation value reflects the short-term instability of the unit itself, while the total power fluctuation value reflects the overall disturbance level of the system. The relative deviation constitutes a normalized comparison between the two, which can avoid misjudgments at different power levels. This logic not only enhances the system's sensitivity to abnormal fluctuations, but also improves the spatial resolution and strategy accuracy of the coordinated control of photovoltaic and energy storage, effectively supporting the prioritization of subsequent energy storage intervention resources.

[0063] Furthermore, by dynamically coupling the state of charge of the energy storage system, the pressure of charging demand on the resident side (reflected by the average queuing time), and the current power generation capacity of the photovoltaic unit, a "supply and demand dual-side linkage" mechanism is logically formed. On the one hand, the charge difference reflects the strength of the energy storage demand, the average queuing time reflects the urgency of the residents' immediate electricity load, and the output power measures the supply capacity of the photovoltaic unit. The linkage of the three enables dynamic sorting and flexible allocation of energy storage priorities in the context of power generation fluctuations. When user demand is controllable, the energy storage system is given priority for charging, and when demand is tight, the power supply on the resident side is maintained, thereby improving the flexibility of photovoltaic output regulation and user satisfaction, while reducing the risk of local overload and load conflict.

[0064] Furthermore, by introducing a "determined power fluctuation value" to reflect the stability of photovoltaic output over a short period of time, combined with a "pre-determined fluctuation threshold" as a screening criterion, units with severe power fluctuations can be accurately identified as priority energy storage targets. This enables the linkage between unstable power areas and the energy storage response mechanism, preventing power fluctuations from causing disturbances to the microgrid while fully utilizing the energy storage system for peak load shifting. The greater the output power fluctuation, the greater the regulatory value of the energy storage; therefore, this strategy dynamically matches system stability with the optimal scheduling of energy storage resources, improving the overall system flexibility and responsiveness.

[0065] Furthermore, the correlation between the frequency of charging interruptions and the dynamic coordination capability of power and load is integrated to make a judgment, and normalization and weighting processing are used to achieve a unified measurement of parameters of different dimensions, avoiding the one-sidedness of single indicator judgment. Among them, the output power reflects the energy supply capacity of the energy storage unit, and the load demand reflects the real-time load on the energy consumption side of the building. The ratio of the two constitutes a measure of coordination capability, while the frequency of interruption and reconnection reflects the system stability and user-side experience. When the coordination index is high but interruptions are frequent, or the coordination capability itself is strongly correlated with the interruption trend, it indicates that the energy storage response capability has hidden dangers such as fluctuations and imbalances, thereby achieving accurate identification and isolation of abnormal coordination units and improving intelligent diagnostic capabilities.

[0066] Furthermore, a risk assessment model is constructed by correlating three parameters: layout location (spatial distribution), number of units (fault scale), and switch status (load risk), to achieve dynamic adjustment of the system's power fluctuation tolerance range. The normalized concentration reflects whether the coordinated abnormal units are clustered and distributed. The smaller the standard deviation, the higher the concentration, which may cause local impact risks to a certain feeder. The normalized quantity reflects the absolute impact of the number of abnormal units. The load switch status value reflects the current system's carrying capacity and impact response capabilities. The three are weighted to generate a risk index, which can comprehensively evaluate the current system stability and then reasonably adjust the power fluctuation threshold to enhance the system's resilience and emergency response capabilities, avoid misjudgments or missed judgments due to fixed threshold settings, and improve the flexibility and security of coordinated scheduling.

[0067] Furthermore, by monitoring the fluctuation of the number of abnormally coordinated units, a dynamic correlation between abnormal behavior and PV output forecasts was established. The underlying logic is as follows: greater fluctuations in the number of abnormally coordinated units indicate potential output disturbances, necessitating an improvement in the forecast value to maintain safety margins. A preset correction quantity fluctuation threshold serves as a benchmark for determining stability. The correction quantity fluctuation value reflects the degree of system disturbance, and the relative deviation between the two reflects the actual deviation. A preset correction coefficient quantifies the correction magnitude. These parameters together establish a data-driven prediction correction mechanism, which helps improve the accuracy of PV output forecasts and the stability of system scheduling.

[0068] Furthermore, by using preset control coefficients and deviation calculations, the photovoltaic power generation power can be dynamically adjusted according to the difference between the real-time corrected predicted value and the preset value range, thereby effectively achieving optimal power distribution and accurately controlling power increase and decrease, which not only improves the stability of system operation, but also optimizes energy utilization efficiency.

[0069] Furthermore, time series alignment is used to ensure the consistency of various parameters on the same time axis; missing value filling ensures the integrity of model input; normalization processing eliminates the deviation caused by different dimensions, providing balanced features for model learning; the multi-dimensional feature matrix integrates the power generation side (output power), energy storage side (SOC), load side (transformer demand, charging growth rate, queue time) and stability indicators (reconnection frequency), enabling the prediction model to simultaneously capture the dynamic changes and mutual influence of multiple sources of supply-storage-demand at the underlying logic, thereby significantly improving the accuracy and robustness of short-term photovoltaic output forecasts. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 This is a flow chart of the method for collaborative control of photovoltaic storage and charging with microgrids in this embodiment;

[0071] Figure 2 This is a decision logic diagram for determining a temporary unit in this embodiment;

[0072] Figure 3 This is a logic diagram for determining the energy storage unit in this embodiment;

[0073] Figure 4 This is the decision logic diagram for the collaborative abnormality determination unit in this embodiment. DETAILED DESCRIPTION

[0074] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0075] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0076] See also Figure 1 As shown, it is a flow chart of the method for coordinated control of photovoltaic storage and charging and microgrid in this embodiment;

[0077] This embodiment provides a method for coordinated control of photovoltaic storage and charging with a microgrid, including:

[0078] Real-time data collection is used to collect the output power of each photovoltaic unit on each feeder within the photovoltaic array in the microgrid based on the preset photovoltaic power generation power, the status of the high-current load switches in each feeder, the charge state of the energy storage system, the load demand at the building transformer end, the charging request growth rate at the target side, the average queue time, and the frequency of interruption and reconnection;

[0079] Predicting a photovoltaic output value based on all the output power, the state of charge value, the load demand, the charging request growth rate, the average queuing time, and the interruption and reconnection frequency within a preset historical period and a preset prediction model;

[0080] screening out a plurality of temporary units according to the output power, a preset total power fluctuation threshold, and the charging request growth rate;

[0081] Determine a number of energy storage units according to the average queuing time, the output power of each of the temporary units, and the state of charge value;

[0082] Determining a number of coordinated abnormal units according to the interruption and reconnection frequency, the output power of each of the energy storage units, and the load demand;

[0083] Adjusting the preset total power fluctuation threshold according to the layout position and number of the coordinated abnormal units in each feeder and the state value of the high-current load switch to obtain an adjusted power fluctuation threshold;

[0084] Correcting the photovoltaic output prediction value according to the number of the coordinated abnormal units re-determined by using the adjusted power fluctuation threshold within a preset correction period to obtain a corrected prediction value;

[0085] The control instruction of adjusting the preset photovoltaic power generation power is executed on the collaborative abnormality unit according to the corrected prediction value and the preset prediction value range.

[0086] A microgrid is a power supply and management unit within a residential building, consisting of a photovoltaic power generation system, energy storage equipment, load requirements, and related control systems. The microgrid's function is to integrate various distributed energy resources and dispatch power based on real-time demand, ensuring a stable power supply. In this scenario, the microgrid ensures that power needs inside and outside the building are met by combining the photovoltaic, energy storage, and charging systems with other related modules.

[0087] Photovoltaic arrays in residential buildings convert solar energy into electricity, providing renewable power for the buildings. The number and layout of photovoltaic units are determined based on the building's roof area and sunlight conditions to maximize power generation efficiency. By monitoring the array's power generation in real time, the microgrid can adjust photovoltaic output based on the building's electricity needs, ensuring a stable power supply.

[0088] Feeder lines, the primary channel for power transmission in residential buildings, transmit electricity generated by photovoltaic arrays to the building's transformers, or transmit power from microgrids to charging facilities (such as electric vehicle charging stations) within the building. The health and condition of feeder lines are crucial, affecting the building's power supply and the efficiency of charging stations.

[0089] The energy storage system within the residential building is primarily responsible for monitoring the battery charge level, ensuring that power demand matches the storage system's supply. During periods of insufficient sunlight or peak power demand, the energy storage system can provide additional power to avoid power shortages. By monitoring the state of charge in real time, the microgrid can optimize power dispatch and prevent overcharging and overdischarging of the batteries, thereby extending their service life.

[0090] The load demand at the building transformer end refers to the total power demand of all electrical devices within the building, including lighting, air conditioning, elevators, and electric water heaters. By monitoring these load demands in real time through smart energy meters, the microgrid system can dispatch power based on actual electricity usage, prioritizing photovoltaic power generation and, when necessary, dispatching energy storage systems to provide power, ensuring a stable power supply within the building.

[0091] For electric vehicle charging stations installed within a building, the target-side charging request growth rate, average queue time, and interruption / reconnection frequency reflect the operating load of the charging station and the charging demand of electric vehicles. The charging request growth rate refers to the rate of increase in electric vehicle charging requests over time, reflecting the changing trend of charging demand among electric vehicle users, particularly as electric vehicle penetration continues to rise, which may show a rapid growth trend. The average queue time measures the efficiency of charging stations. When multiple electric vehicles need to charge simultaneously, the queue time at the charging station increases. Real-time monitoring of queue time allows for the optimal scheduling of photovoltaic arrays and energy storage systems, reducing waiting times and improving charging efficiency. The interruption / reconnection frequency reflects the frequency of interruptions and reconnections caused by faults or external factors (such as grid fluctuations or low battery charge). Frequent interruptions and reconnections may indicate operational issues with the charging station or unstable power supply, necessitating power scheduling to optimize the charging process and ensure continuous and stable charging.

[0092] In this embodiment, based on a preset photovoltaic power generation operation strategy, key operating parameters are collected in real time through multi-level distributed sensing and communication means: on each feeder branch of the photovoltaic array, the current transformer (DC CT) and voltage transformer (DC PT) arranged on the DC side of each photovoltaic unit, combined with the built-in power acquisition module of the micro-inverter, accurately measure its output power and upload it via the Modbus protocol; a digital load switch status collector is configured in the distribution cabinet of each feeder loop to obtain the high-current load switch status value (closed = 1, open = 0, fault = 2) in real time and transmit it via the RS-485 link; the state of charge (SOC) value of the energy storage system is uploaded to the energy management controller by the battery management system (BMS) via the CAN bus in the form of periodic messages (e.g., 10 seconds / time); the load demand at the building transformer end is measured by a three-phase smart meter connected to the DL / T1490-2015 standard, and the total active power is transmitted to the SCADA system via the Ethernet port; each smart charging pile in the target parking lot is connected to the charging station management system (CSMS), which is based on OCPP. The 1.6 protocol records the connection requests, queuing events, and communication interruption logs for each charging pile, and provides real-time statistics on the charging request growth rate, average queuing time, and interruption and reconnection frequency. All collected data is ultimately aggregated by the RTU, uploaded to the upper-level EMS system via the optical fiber link according to the Modbus or IEC 61850 protocol, and stored in the SCADA database at the second or minute level, achieving full-dimensional perception and dynamic control of the residential building microgrid system.

[0093] The preset photovoltaic power generation power refers to the target output power of the photovoltaic array that is pre-set based on historical operating efficiency, weather forecast data, and user-side load characteristics when formulating a scheduling strategy. It depends on the light intensity forecast, photovoltaic module efficiency, and power load trend. It is usually set between 40% and 90% of the rated power of the photovoltaic array. In this embodiment, it is set to 75%, which can provide a stable benchmark power target for microgrid operation.

[0094] The preset historical duration refers to the length of the historical data window used for statistical and predictive analysis. It depends on the frequency of system load fluctuations and the data sampling period, and is typically set between 5 minutes and 1 hour. In this example, it is set to 30 minutes to balance data response sensitivity and predictive stability.

[0095] The preset correction period is the interval at which the predicted value is dynamically corrected during system operation. It depends on the frequency of environmental disturbances and the response rate of the dispatch system. It is typically set between 1 and 15 minutes, but in this embodiment is set to 5 minutes. This allows for timely correction of the PV output forecast, improving control accuracy and system stability.

[0096] The preset prediction value range refers to the upper and lower limits of the photovoltaic power generation prediction value, which depends on the rated power of the photovoltaic array and the error margin of the prediction model. It is usually set between 80% and 100%. In this embodiment, it is set to 85% to 95%, which can ensure that the photovoltaic output fluctuates within a reasonable tolerance and prevent system overload or underload.

[0097] The pre-defined prediction model in this embodiment is a multivariate time series prediction model that integrates a long short-term memory (LSTM) network with a feature attention mechanism. It is specifically designed for accurate short-term prediction of photovoltaic output in residential microgrid environments. This model fully considers the nonlinear variation characteristics of photovoltaic output and multiple sources of influence, and has good robustness and generalization capabilities, making it suitable for ultra-short-term prediction scenarios of 5-60 minutes.

[0098] 1. Model structure

[0099] Input layer: Input variables include:

[0100] Output power sequence of each photovoltaic unit (P);

[0101] Energy storage system SOC sequence (S);

[0102] Building transformer load demand sequence (L);

[0103] Charge request growth rate (R);

[0104] Average queue time (Q);

[0105] Interruption and reconnection frequency (F);

[0106] Each variable forms a sliding time window according to the "preset historical length" (such as 30 minutes) at a fixed time interval (such as every minute), forming a multivariate time series tensor.

[0107] Feature Attention Layer: This layer assigns different weights to multiple input variables, automatically learning the impact of each parameter on PV output, forming a weighted feature embedding representation, and improving modeling accuracy. For example, in rainy weather, the model may automatically increase the weights of load demand and energy storage SOC.

[0108] LSTM encoding layer: A two-layer LSTM unit extracts long-term temporal dependencies to capture the changing trends of PV output. This network features a memory gating mechanism that effectively retains highly relevant temporal information and suppresses noise interference.

[0109] Fully connected output layer (Dense Layer): The LSTM output feature vector is input into the fully connected layer to regress and predict the photovoltaic output value (unit: kW) at a certain moment in the future.

[0110] 2. Training Methods

[0111] Loss function: Use mean square error (MSE) as the loss function;

[0112] Optimizer: Adam optimizer is used for gradient update;

[0113] Training data set: Select the second-level operation data of the past 30 days and group and enhance it according to sunshine changes and load curves;

[0114] Training cycle: set to 100 rounds or until the validation set error converges.

[0115] 3. Model Deployment

[0116] Operating environment: Deployed on building-level EMS edge computing nodes (supporting Python+TensorFlow or PyTorch);

[0117] Update frequency: daily offline training, hourly hot update;

[0118] Output frequency: Outputs the predicted PV output value for the next 5 minutes every 1 minute.

[0119] 4. Model Advantages

[0120] Improve the dynamic expression ability of different influencing factors through the attention mechanism;

[0121] The LSTM structure enhances the ability to model complex time changes;

[0122] Supports multi-source heterogeneous data input to meet the actual needs of photovoltaic storage and charging coordinated scheduling in microgrids;

[0123] It can provide high-precision prediction support for downstream strategy modules and improve the reliability and economy of predictive drive control response.

[0124] First, the system collects real-time data on the output power of each PV unit on each feeder of the PV array, the status of high-current load switches, the state of charge of the energy storage system, the load demand on the building transformer, and the target-side charging request growth rate, average queue time, and interruption and reconnection frequency. These real-time parameters are then aligned and normalized according to a preset historical time period and input into the prediction model to obtain a preliminary PV output forecast. Temporary units with significant fluctuations are then screened based on their output power, a preset total power fluctuation threshold, and the charging request growth rate. Available energy storage units are then identified based on the average queue time, the output power of these temporary units, and their state of charge. Collaborative abnormal units are then identified based on the output power, load demand, and reconnection frequency of these energy storage units. The total power fluctuation threshold is dynamically adjusted based on the distribution, number, and load switch status of abnormal units on each feeder. Within a preset correction period, the updated threshold is used to reassess the number of abnormal units and revise the PV output forecast, generating a revised forecast that is more accurate to reality. Finally, when the revised forecast exceeds the preset range, control commands are issued to the abnormal units to increase or decrease PV power generation, achieving closed-loop adaptive control of the PV-storage-charging system.

[0125] By organically coupling multi-dimensional real-time parameters such as output power, state of charge, load demand, and user behavior (request growth rate, queue length, and reconnection frequency), an adaptive closed loop is constructed in the six major links of "prediction, screening, identification, threshold adjustment, prediction correction, and control execution": First, the power fluctuation threshold and the charging request growth rate jointly trigger temporary unit screening to ensure a rapid response to sudden load changes; second, the state of charge value and the queue length jointly determine the energy storage unit scheduling to balance the power generation side and the demand side; the reconnection frequency and the power-load normalization weight are then used to generate a synergy index to accurately identify collaborative anomalies; the distribution location and number of abnormal units at the feeder level and the load switch status are jointly mapped to the threshold adjustment coefficient to achieve regional risk perception; the secondary correction of the predicted value within the correction period compensates for the model deviation, and finally the photovoltaic power regulation command is executed according to the correction error range, which can significantly improve the system stability, response speed, and energy utilization, and effectively solve the problem of low collaborative control response speed caused by model staticization and single indicator judgment.

[0126] Specifically, the process of selecting a plurality of temporary units according to the output power, the preset total power fluctuation threshold, and the charging request growth rate includes:

[0127] Calculating the sum of all the output powers to obtain the total output power;

[0128] Calculating the standard deviation of the total output power within the preset temporary time length to obtain a total power fluctuation value;

[0129] When the total power fluctuation value is greater than the preset total power fluctuation threshold and the charging request growth rate is greater than a preset standard growth rate, a plurality of temporary units are selected according to the output power and the total power fluctuation value.

[0130] The preset standard growth rate refers to the baseline growth threshold for the number of charging requests per unit time on the target side. It depends on the changes in the average charging requests over the same period in history and the system load responsiveness. It is usually set between 5% and 20%. In this embodiment, it is set to 12%. This allows for timely identification of rapid growth trends in the charging load and provides a basis for determining energy storage intervention in PV fluctuations.

[0131] By calculating the sum of the output power of each photovoltaic unit, the total output power in the current microgrid is obtained, and the standard deviation of the total power is calculated within a preset temporary period (for example, 15 minutes) as a total power fluctuation value to measure the degree of fluctuation of photovoltaic output. If this value is greater than the preset total power fluctuation threshold, and the growth rate of charging requests from the target side (such as residential building charging piles) exceeds the set standard growth rate at this time, the system believes that there is a risk of "photovoltaic fluctuations superimposed on load surges". In this case, the system will give priority to photovoltaic units that have a greater impact on system stability based on the degree of deviation between the real-time output power of each photovoltaic unit and the total power fluctuation value, mark them as temporary units, and enter the next stage of energy storage regulation or control intervention process.

[0132] Through a screening mechanism based on the dual trigger logic of dynamic volatility detection and load growth signal recognition, the volatility of output power is organically combined with the load behavior on the demand side (such as the surge in electric vehicle charging). The total power fluctuation value, as an important statistical indicator reflecting the stability of the photovoltaic system, forms the basis of subjective evaluation together with the output power; while the growth rate of charging requests reflects the dynamic energy demand on the target (user) side. These two factors together determine whether temporary intervention targets are needed. By comprehensively judging the "supply and demand fluctuation amplitude" and "future load pressure", not only can potential power supply instability be detected in advance, but also precise, localized, and controllable targets can be provided for subsequent energy storage scheduling, effectively improving the system's response speed and control accuracy to sudden load changes, and achieving more fine-grained photovoltaic, storage, and charging coordinated control.

[0133] Please continue reading Figure 2 As shown, it is a decision logic diagram for determining a temporary unit in this embodiment;

[0134] The temporary units selected according to the output power and the total power fluctuation value include:

[0135] Calculating the standard deviation of all the output powers of the photovoltaic units within the next preset temporary time period to obtain an output power fluctuation value;

[0136] Calculating a relative deviation between the output power fluctuation value and the total power fluctuation value to obtain a temporary determination value;

[0137] When the temporary determination value is greater than a preset temporary determination threshold, the photovoltaic unit is determined to be the temporary unit, so as to screen out a number of temporary units.

[0138] The preset temporary judgment threshold is a standard benchmark for judging whether the output power fluctuation of a single photovoltaic unit is abnormal. It depends on the local power fluctuation tolerance allowed by the system and the historical operating stability data. It is usually set between 0.1 and 0.3. In this embodiment, it is set to 0.2. That is, when the fluctuation of the output power of a photovoltaic unit deviates from the overall fluctuation by more than 20%, it is regarded as a temporary abnormal unit. It can effectively filter normal fluctuations and accurately identify units that contribute more to system disturbances, providing a basis for subsequent optimization of control strategies.

[0139] By analyzing the output power fluctuation behavior of individual PV units, accurate identification of temporary units is achieved. Specifically, the standard deviation of the output power of each PV unit within the next preset temporary duration is calculated to obtain its output power fluctuation value. This value is then compared with the total power fluctuation value of the entire system to calculate the relative deviation, resulting in a temporary judgment value for each PV unit. If this judgment value exceeds the set temporary judgment threshold, the PV unit is marked as a temporary unit and is subsequently monitored and intervened in energy storage and load scheduling.

[0140] By introducing a fluctuation determination mechanism at the photovoltaic unit level, it is possible to further identify the local sources of fluctuation that have the greatest impact on system stability, even in the context of large overall power fluctuations and rapidly increasing charging demand. The output power fluctuation value reflects the short-term instability of the unit itself, while the total power fluctuation value reflects the overall disturbance level of the system. The relative deviation constitutes a normalized comparison between the two, which can avoid misjudgments at different power levels. This logic not only enhances the system's sensitivity to abnormal fluctuations, but also improves the spatial resolution and strategy accuracy of the coordinated control of photovoltaic and energy storage, effectively supporting the prioritization of subsequent energy storage intervention resources.

[0141] Specifically, the process of determining a number of energy storage units according to the average queuing time, the output power of each temporary unit, and the state of charge value includes:

[0142] When the state of charge value is less than a preset state of charge threshold, calculating a difference between the preset state of charge threshold and the state of charge value to obtain a charge difference;

[0143] When the charge difference is greater than a preset charge difference threshold, the average queuing time is less than a preset time threshold, and the output power is greater than a preset standard power, determining that the temporary unit is the energy storage unit to determine a number of energy storage units;

[0144] When the charge difference is greater than a preset charge difference threshold and the average queuing time is greater than or equal to the preset time threshold, a number of energy storage units are determined according to the output power within a preset determined time.

[0145] The preset charge difference threshold depends on the operating characteristics of the energy storage system and the output power fluctuation of the photovoltaic unit. It is usually set between 10% and 20%. In this embodiment, it is set to 15%. It can ensure that the charging process is started in time when the energy storage system power is lower than the threshold to avoid system instability due to low power.

[0146] The preset time threshold depends on the user's tolerance for power demand and the system response time, and is usually set between 3 minutes and 10 minutes. In this embodiment, it is set to 5 minutes. While ensuring system stability, it can reduce the user's waiting time in queues and improve charging efficiency.

[0147] The preset standard power depends on the power generation capacity of the photovoltaic unit and the requirements of the energy storage system. It is usually set between 30% and 50% of the maximum output power. In this embodiment, it is set to 40%, which can effectively balance the output power of the photovoltaic unit and the charging requirements of the energy storage unit, avoiding unnecessary fluctuations caused by excessive or low power.

[0148] The preset determination time duration refers to the time window used to calculate the fluctuation of the output power of the photovoltaic unit. It depends on the sensitivity of the system to the power fluctuation response and the energy storage response cycle. It is usually set between 5 minutes and 30 minutes. In this embodiment, it is set to 10 minutes. It can fully capture the power change trend while ensuring the real-time response, which is used to accurately identify the energy storage regulation demand.

[0149] The photovoltaic units that can be used as energy storage regulation objects are further determined from the screened temporary units. The system first determines the state of charge (SOC) of the energy storage device corresponding to each temporary unit. When the SOC is lower than the preset state of charge threshold, the difference between it and the threshold (charge difference) is calculated; if the difference exceeds the set charge difference threshold, it means that the energy storage system is in a low-power state and needs to be charged. At this time, if the average queuing time in the area where the unit is located is less than the preset queuing time threshold (that is, the user's waiting pressure for charging service is relatively small), and the output power of the unit is higher than the standard power value, then the unit is determined to have priority in supplying energy to the energy storage system and is marked as an energy storage unit; on the contrary, if the queuing time is long (indicating that the residents' charging needs are more urgent), the unit will not be immediately arranged as an energy storage unit, but will be further combined with its output power level over a period of time to comprehensively judge whether it is suitable as an energy storage regulation participating unit.

[0150] By dynamically coupling the state of charge of the energy storage system, the pressure of charging demand on the resident side (reflected by the average queuing time), and the current power generation capacity of the photovoltaic unit, a "supply and demand dual-side linkage" mechanism is logically formed. On the one hand, the charge difference reflects the strength of the energy storage demand, the average queuing time reflects the urgency of the residents' immediate electricity load, and the output power measures the supply capacity of the photovoltaic unit. The linkage of the three enables dynamic sorting and flexible allocation of energy storage priorities in the context of power generation fluctuations. When user demand is controllable, the energy storage system is charged first, and when demand is tight, the power supply on the resident side is maintained, thereby improving the flexibility of photovoltaic output regulation and user satisfaction, while reducing the risk of local overload and load conflict.

[0151] Please continue reading Figure 3 As shown, it is a determination logic diagram for determining the energy storage unit in this embodiment;

[0152] The process of determining a number of energy storage units according to the output power within a preset determined time period includes:

[0153] Calculating the standard deviation of the output power within a predetermined time period to obtain a determined power fluctuation value;

[0154] When the determined power fluctuation value is greater than a preset determined fluctuation threshold, the temporary unit is determined to be the energy storage unit to determine a number of energy storage units.

[0155] The preset fluctuation threshold refers to the standard deviation threshold used to determine whether the power fluctuation of the photovoltaic unit is significant. It depends on the system's tolerance for power fluctuations and the energy storage intervention strategy. It is usually set between 50W and 300W. In this embodiment, it is set to 150W. It can effectively identify photovoltaic units with significant power fluctuations and accurately trigger the energy storage unit to participate in regulation.

[0156] When determining an energy storage unit based on output power within a preset duration, the system first performs a statistical analysis of the output power data of all temporary units within that time period, calculates its standard deviation, and determines the power fluctuation value for that period. The system then compares this fluctuation value with a preset fluctuation threshold. If the fluctuation value exceeds the threshold, it indicates that the corresponding PV unit's power output is unstable or exhibits sudden changes during that period. In this case, the PV unit is identified as an energy storage unit, enabling energy storage regulation intervention.

[0157] By introducing a "determined power fluctuation value" to reflect the stability of PV output over a short period of time, combined with a "pre-determined fluctuation threshold" as a screening criterion, units with significant power fluctuations can be accurately identified as priority energy storage targets. This enables the linkage between unstable power areas and the energy storage response mechanism, preventing power fluctuations from disrupting the microgrid while fully utilizing the energy storage system for peak load shifting. The greater the output power fluctuation, the higher the regulatory value of the energy storage; therefore, this strategy dynamically matches system stability with the optimal scheduling of energy storage resources, improving the overall system's flexibility and responsiveness.

[0158] Please continue reading Figure 4 As shown, it is a decision logic diagram of the collaborative abnormality determination unit in this embodiment;

[0159] The process of determining a plurality of coordinated abnormal units according to the interruption and reconnection frequency, the output power of each energy storage unit, and the load demand includes:

[0160] Obtaining the interruption and reconnection frequency within a preset collaboration time length to obtain a reconnection frequency set;

[0161] Obtaining the output power within the preset coordination time to obtain an output power set;

[0162] Obtaining the load demand within the preset coordination time to obtain a load demand set;

[0163] Performing maximum-minimum normalization processing on the output power at each moment within the preset coordination duration according to the output power set to obtain a power normalization value;

[0164] Performing maximum-minimum normalization processing on the load demand at each moment within the preset coordination time according to the load demand set to obtain a demand normalization value;

[0165] Calculating the product of the power normalization value and the preset power weight to obtain a first product, and calculating the product of the demand normalization value and the preset demand weight to obtain a second product;

[0166] calculating the sum of the first product and the second product to obtain a synergy index;

[0167] Acquire all the synergy indexes to obtain a synergy index set;

[0168] Calculating the correlation coefficient between the reconnection frequency set and the collaboration index set to obtain a collaboration anomaly degree;

[0169] When the coordination abnormality degree is greater than a preset standard abnormality degree, the energy storage unit is determined to be the coordination abnormality unit, so as to determine a plurality of coordination abnormality units.

[0170] The maximum-minimum value normalization is a prior art and will not be described in detail here;

[0171] The preset coordination duration refers to the time window used to evaluate the coordinated operation status of the energy storage unit. It depends on the response cycle of photovoltaic output and load demand and is usually set between 10 minutes and 1 hour. In this embodiment, it is set to 30 minutes, which can accurately capture the dynamic changes in the coordinated response of the energy storage unit and the load.

[0172] The preset power weight is a coefficient used to measure the importance of the energy storage unit output power in the calculation of the synergy index. It depends on the degree to which the energy storage response capability in the system depends on load regulation. It is usually set between 0.4 and 0.7. In this embodiment, it is set to 0.5, which can reasonably reflect the impact of the energy storage output on the overall synergy capability.

[0173] The preset demand weight is a coefficient used to measure the importance of load demand in the calculation of the collaborative index. It depends on the load-side regulation priority and the real-time supply and demand balance pressure. It is usually set between 0.3 and 0.6. In this embodiment, it is set to 0.5, which can reflect the reference value of load changes in collaborative anomaly judgment.

[0174] The preset standard abnormality is a correlation coefficient threshold used to identify whether an energy storage unit has a coordinated abnormality. It depends on the typical correlation characteristics between the interruption frequency and the coordinated index in the historical operation data. It is usually set between 0.6 and 0.9. In this embodiment, it is set to 0.75, which can effectively screen out energy storage units with potential unstable operation or mismatch.

[0175] Energy storage units with abnormal operating status are identified through a multi-dimensional data fusion method. First, the interruption and reconnection frequency, output power and load demand of the energy storage unit are obtained respectively within the preset coordination time, and a frequency set, an output power set and a load demand set are formed respectively. Subsequently, the output power set and the load demand set are normalized to the maximum and minimum values ​​to obtain the corresponding normalized value sequences, and then multiplied by the set power weight and load demand weight respectively. The sum of the weighted results is calculated to form a coordination index, which is used to reflect the degree of coordination contribution of the energy storage unit to the supply and demand matching during the period. Finally, the Pearson correlation coefficient is calculated for the coordination index set and the interruption and reconnection frequency set to obtain the coordination anomaly degree. If the coordination anomaly degree is greater than the preset standard anomaly threshold, it is considered that the energy storage unit has abnormal performance during operation and is determined to be a coordination abnormality unit.

[0176] The judgment is made by integrating the correlation between the frequency of charging interruptions and the dynamic power-load coordination capability, and using normalization and weighting processing to achieve a unified measurement of parameters of different dimensions, avoiding the one-sidedness of single indicator judgment. Among them, the output power reflects the energy supply capacity of the energy storage unit, and the load demand reflects the real-time load on the energy consumption side of the building. The ratio of the two constitutes a measure of coordination capability, while the frequency of interruption and reconnection reflects system stability and user-side experience. When the coordination index is high but interruptions are frequent, or the coordination capability itself is strongly correlated with the interruption trend, it indicates that the energy storage response capability has hidden dangers such as fluctuations and imbalances, thereby achieving accurate identification and isolation of abnormal coordination units and improving intelligent diagnostic capabilities.

[0177] Specifically, the preset total power fluctuation threshold is adjusted according to the layout position and number of the coordinated abnormal units in each feeder and the state value of the high-current load switch, and the process of adjusting the power fluctuation threshold includes:

[0178] Obtaining the layout position of the coordinated abnormal units in each of the feeders to obtain the relative distances between the coordinated abnormal units and the starting point of the feeder;

[0179] Obtaining the feeder number to which each of the abnormal collaborative units belongs, and counting the number of abnormal collaborative units in each feeder according to the feeder number to obtain the number of units;

[0180] Performing maximum-minimum normalization processing on the relative distance at the current moment according to all the relative distances to obtain a plurality of normalized distances;

[0181] Calculate the standard deviation of all the normalized distances to obtain the distribution concentration;

[0182] calculating a concentration factor based on the distribution concentration and the number of units;

[0183] Normalizing the current distribution concentration according to all the distribution concentrations within the preset adjustment time to obtain a normalized concentration;

[0184] Normalizing the current number of units according to the total number of units within the preset adjustment time to obtain a normalized number;

[0185] Performing a weighted summation on the preset concentration weight, the normalized concentration, the preset quantity weight, the normalized quantity, the preset state value weight, and the state value of the high-current load switch to obtain a risk index, wherein Q=w1×J+w2×S+w3×K, Q is the risk index, w1 is the preset concentration weight, J is the normalized concentration, w2 is the preset quantity weight, S is the normalized quantity, w3 is the preset state value weight, and K is the state value of the high-current load switch;

[0186] When the risk index is greater than the preset risk index threshold, the preset total power fluctuation threshold is increased according to the relative deviation between the risk index and the preset risk index threshold and the preset adjustment coefficient to obtain the adjusted power fluctuation threshold, wherein T'=T×[1+e×(Q-Q0) / Q], T' is the adjusted power fluctuation threshold, T is the preset total power fluctuation threshold, e is the preset adjustment coefficient, and Q0 is the preset risk index threshold.

[0187] Feeder numbers are unique identifiers for each feeder in the distribution system. These numbers are determined by the topology of the distribution network and its operational and maintenance requirements, and are typically coded by region, voltage level, or substation outgoing line sequence. In this embodiment, numbering by substation outgoing line sequence clarifies the physical feeder path to which each collaborative abnormal unit belongs, facilitating statistics and analysis of the distribution of abnormal units across different feeders, thereby supporting subsequent distribution concentration calculations and risk assessments.

[0188] The preset concentration weight is a weight factor used to measure the degree of influence of the distribution concentration of collaborative abnormal units in the feeder on the risk index. It depends on the sensitivity of the system to the influence of the distribution of the layout location and is usually set between 0.2 and 0.5. In this embodiment, it is set to 0.35, which can reasonably reflect the importance of the layout location in risk assessment.

[0189] The preset quantity weight is a weight factor used to measure the contribution of the number of collaborative abnormal units to the overall risk index. It depends on the degree of influence of the number of abnormal units on the local fluctuation stability. It is usually set between 0.3 and 0.6. In this embodiment, it is set to 0.45, which can accurately express the driving effect of unit density on system instability.

[0190] The preset state value weight is used to characterize the importance of the impact of the high-current load switch state value on the system risk index. It depends on the contribution of load state fluctuations to power instability and is usually set between 0.1 and 0.4. In this embodiment, it is set to 0.2, which can moderately reflect the impact of the actual load state on the risk level.

[0191] The preset risk index threshold is a limit value used to determine whether the current system has entered a high-risk state. It depends on the system's tolerance to power fluctuations and reliability requirements. It is usually set between 0.5 and 0.8. In this embodiment, it is set to 0.65, which can achieve timely identification and response to the degree of abnormal aggregation.

[0192] The preset adjustment coefficient is a proportional parameter used to adjust the power fluctuation threshold according to the relative deviation of the risk index. It depends on the system's response sensitivity to the threshold change and the adjustment amplitude requirements. It is usually set between 1.1 and 1.5. In this embodiment, it is set to 1.2, which can dynamically enhance the power fluctuation threshold to adapt to the system disturbance caused by the density of abnormal units.

[0193] By obtaining the relative distance between the layout position of the collaborative abnormal unit in each feeder and the starting point of the feeder, and combining the corresponding feeder number to count the number of units, the standard deviation of the normalized distance is calculated to obtain the distribution concentration. The distribution concentration and the number of units are then normalized within the preset adjustment time (existing technology, no longer repeated), and the normalized concentration and normalized quantity are obtained. Finally, the risk index is calculated by weighted summation based on the normalized concentration, normalized quantity, high-current load switch state value and their respective preset weights. When the risk index exceeds the preset risk index threshold, the preset total power fluctuation threshold is dynamically adjusted according to its relative deviation and the preset adjustment coefficient to generate a new adjusted power fluctuation threshold.

[0194] By building a risk assessment model based on the correlation between three parameters: layout location (spatial distribution), number of units (fault scale), and switch status (load risk), the system's tolerance for power fluctuations can be dynamically adjusted. The normalized concentration reflects whether the coordinated abnormal units are clustered. The smaller the standard deviation, the higher the concentration, which may cause local impact risks to a certain feeder. The normalized quantity reflects the absolute impact of the number of abnormal units. The load switch status value reflects the current system's carrying capacity and impact response capabilities. The three are weighted to generate a risk index, which can comprehensively assess the current system stability and then reasonably adjust the power fluctuation threshold to enhance the system's resilience and emergency response capabilities, avoid misjudgments or missed judgments due to fixed threshold settings, and improve the flexibility and safety of coordinated scheduling.

[0195] Specifically, the photovoltaic output prediction value is corrected according to the number of the coordinated abnormal units re-determined by using the adjusted power fluctuation threshold within a preset correction period, and the process of obtaining the corrected prediction value includes:

[0196] Calculating the standard deviation of the unit quantity within the preset correction period to obtain a corrected quantity fluctuation value;

[0197] When the corrected quantity fluctuation value is greater than the preset corrected quantity fluctuation threshold, the photovoltaic output prediction value is increased according to the relative deviation between the corrected quantity fluctuation value and the preset corrected quantity fluctuation threshold and the preset correction coefficient to obtain the corrected prediction value, wherein Y'=Y×[1+i×(L-L0) / L0], Y' is the corrected prediction value, Y is the photovoltaic output prediction value, i is the preset correction coefficient, L is the corrected quantity fluctuation value, and L0 is the preset corrected quantity fluctuation threshold.

[0198] The preset correction quantity fluctuation threshold is the benchmark value for judging whether the degree of fluctuation in the number of collaborative abnormal units is abnormal. It depends on the system's sensitivity requirements for quantity changes and is usually set between 1 and 5. In this embodiment, it is set to 3, which can effectively identify the time periods when the number of collaborative abnormal units in the system fluctuates greatly, providing a basis for predictive correction.

[0199] The preset correction coefficient is a multiplication factor used to adjust the photovoltaic output forecast value according to the fluctuation deviation. It depends on the system's tolerance for risk redundancy and the prediction accuracy requirements. It is usually set between 0.1 and 1.0. In this embodiment, it is set to 0.5. It can moderately increase the forecast value when the fluctuation is significant, thereby enhancing the robustness of system scheduling.

[0200] The revised power fluctuation value is obtained by counting the number of coordinated abnormal units re-determined using the adjusted power fluctuation threshold within a preset correction period and calculating the standard deviation of the unit number within this period. When the revised power fluctuation value exceeds the preset revised power fluctuation threshold, it indicates that the number of coordinated abnormal units is fluctuating significantly and the system is becoming more unstable. Based on the relative deviation between this fluctuation value and the threshold and the preset correction coefficient, the PV output forecast is adjusted upward to obtain a revised forecast value, thereby enhancing the robustness and adaptability of the forecast.

[0201] By monitoring the fluctuations in the number of abnormally coordinated units, a dynamic correlation between abnormal behavior and PV output forecasts was established. The underlying logic is as follows: greater fluctuations in the number of abnormally coordinated units indicate potential output disturbances, necessitating an improvement in the forecast value to maintain safety margins. A preset correction threshold for fluctuations in the number of units serves as a benchmark for determining stability. The correction value reflects the degree of system disturbance, and the relative deviation between the two reflects the actual deviation. A preset correction coefficient quantifies the correction magnitude. These parameters together form a data-driven forecast correction mechanism, which helps improve the accuracy of PV output forecasts and the stability of system scheduling.

[0202] Specifically, the process of executing the control instruction for adjusting the preset photovoltaic power generation power on the coordinated abnormal unit according to the modified predicted value and the preset predicted value range includes:

[0203] When the corrected predicted value is greater than the maximum value of the preset predicted value range, a control instruction for reducing the preset photovoltaic power generation power is executed according to the relative deviation between the corrected predicted value and the maximum value of the preset predicted value range and the preset control coefficient, wherein F'=F×[1-p×(U-Umax) / Umax], F' is the preset photovoltaic power generation power after execution of the control instruction, F is the preset photovoltaic power generation power, p is the preset control coefficient, Umax is the maximum value of the preset predicted value range, and U is the corrected predicted value;

[0204] When the corrected predicted value is less than the minimum value of the preset predicted value range, a control instruction to increase the preset photovoltaic power generation power is executed based on the relative deviation between the minimum value of the preset predicted value range and the corrected predicted value and the preset control coefficient, wherein F'=F×[1+p×(Umin-U) / U], F' is the preset photovoltaic power generation power after executing the control instruction, and Umin is the minimum value of the preset predicted value range.

[0205] The preset control coefficient refers to the scaling factor used to adjust the photovoltaic power generation power based on the power deviation. It depends on the system's response sensitivity to output fluctuations and the safety redundancy requirements. It is usually set between 0.1 and 1.0. In this embodiment, it is set to 0.3, which can provide a moderate adjustment range when the power deviation is significant, balancing the response speed and system stability.

[0206] First, the revised PV output forecast is compared with a preset forecast range. If the revised forecast exceeds the maximum value of the preset forecast range, a control instruction to reduce the PV power generation is executed by calculating the relative deviation and combining it with a preset control coefficient. If the revised forecast is less than the minimum value of the preset forecast range, a similar calculation method is used to increase the PV power generation. This process ensures that the PV power generation is controlled within a reasonable range by adjusting the deviation between the revised forecast value and the preset range, avoiding excessive system load or waste of resources.

[0207] By using preset control coefficients and deviation calculations, the photovoltaic power generation power can be dynamically adjusted according to the difference between the real-time corrected predicted value and the preset value range, thereby effectively achieving optimal power distribution and accurately controlling power increase and decrease, which not only improves the stability of system operation, but also optimizes energy utilization efficiency.

[0208] Specifically, the process of predicting the photovoltaic output prediction value based on all the output power, the state of charge value, the load demand, the charging request growth rate, the average queue time, and the interruption and reconnection frequency within a preset historical period and a preset prediction model includes:

[0209] All the output power, state of charge value, charging pile load demand, target side charging request growth rate, average queue time and interruption reconnection frequency are time series aligned, missing value filled and normalized to construct a multi-dimensional input feature matrix;

[0210] The multi-dimensional input feature matrix is ​​input into the preset prediction model to predict the photovoltaic output prediction value.

[0211] First, the photovoltaic unit output power, energy storage SOC, building transformer load demand, charging request growth rate, average queue time, and interruption and reconnection frequency collected within a preset historical period are aligned according to timestamps, and missing values ​​in the data are interpolated or forward-filled. Finally, each variable is normalized to generate a multi-dimensional time series feature matrix with a unified scale. Subsequently, this feature matrix is ​​input into a preset multivariate time series prediction model to output the predicted photovoltaic output value for the future time period.

[0212] Time series alignment ensures the consistency of various parameters on the same time axis; missing value filling ensures the integrity of model input; normalization eliminates the deviation caused by different dimensions and provides balanced features for model learning; the multi-dimensional feature matrix integrates the power generation side (output power), energy storage side (SOC), load side (transformer demand, charging growth rate, queue time) and stability indicators (reconnection frequency), enabling the prediction model to simultaneously capture the dynamic changes and mutual influence of multiple sources of supply-storage-demand at the underlying logic, thereby significantly improving the accuracy and robustness of short-term photovoltaic output forecasts.

[0213] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A method for coordinated control of photovoltaic storage and microgrid, characterized in that: include: Real-time data collection is used to collect the output power of each photovoltaic unit on each feeder within the photovoltaic array in the microgrid based on the preset photovoltaic power generation power, the status of the high-current load switches in each feeder, the charge state of the energy storage system, the load demand at the building transformer end, the charging request growth rate at the target side, the average queue time, and the frequency of interruption and reconnection; Predicting a photovoltaic output value based on all the output power, the state of charge value, the load demand, the charging request growth rate, the average queuing time, and the interruption and reconnection frequency within a preset historical period and a preset prediction model; Selecting a plurality of temporary units based on the output power, a preset total power fluctuation threshold, and the charging request growth rate; Determine a number of energy storage units according to the average queuing time, the output power of each of the temporary units, and the state of charge value; Determining a number of coordinated abnormal units according to the interruption and reconnection frequency, the output power of each of the energy storage units, and the load demand; Adjusting the preset total power fluctuation threshold according to the layout position and number of the coordinated abnormal units in each feeder and the state value of the high-current load switch to obtain an adjusted power fluctuation threshold; Correcting the photovoltaic output prediction value according to the number of the coordinated abnormal units re-determined by using the adjusted power fluctuation threshold within a preset correction period to obtain a corrected prediction value; The control instruction of adjusting the preset photovoltaic power generation power is executed on the collaborative abnormality unit according to the corrected prediction value and the preset prediction value range.

2. The method for coordinated control of photovoltaic storage and microgrid according to claim 1 is characterized in that: The process of selecting a plurality of temporary units according to the output power, the preset total power fluctuation threshold, and the charging request growth rate includes: Calculating the sum of all the output powers to obtain the total output power; Calculating the standard deviation of the total output power within the preset temporary time length to obtain a total power fluctuation value; When the total power fluctuation value is greater than the preset total power fluctuation threshold and the charging request growth rate is greater than a preset standard growth rate, a plurality of temporary units are selected according to the output power and the total power fluctuation value.

3. The method for coordinated control of photovoltaic storage and microgrid according to claim 2 is characterized in that: The temporary units selected according to the output power and the total power fluctuation value include: Calculating the standard deviation of all the output powers of the photovoltaic units within the next preset temporary time period to obtain an output power fluctuation value; Calculating a relative deviation between the output power fluctuation value and the total power fluctuation value to obtain a temporary determination value; When the temporary determination value is greater than a preset temporary determination threshold, the photovoltaic unit is determined to be the temporary unit, so as to screen out a number of temporary units.

4. The method for coordinated control of photovoltaic storage and microgrid according to claim 3 is characterized in that: The process of determining a number of energy storage units according to the average queuing time, the output power of each temporary unit, and the state of charge value includes: When the state of charge value is less than a preset state of charge threshold, calculating a difference between the preset state of charge threshold and the state of charge value to obtain a charge difference; When the charge difference is greater than a preset charge difference threshold, the average queuing time is less than a preset time threshold, and the output power is greater than a preset standard power, determining that the temporary unit is the energy storage unit to determine a number of energy storage units; When the charge difference is greater than a preset charge difference threshold and the average queuing time is greater than or equal to the preset time threshold, a number of energy storage units are determined according to the output power within a preset determined time.

5. The method for coordinated control of photovoltaic storage and microgrid according to claim 4 is characterized in that: The process of determining a number of energy storage units according to the output power within a preset determined time period includes: Calculating the standard deviation of the output power within a predetermined time period to obtain a determined power fluctuation value; When the determined power fluctuation value is greater than a preset determined fluctuation threshold, the temporary unit is determined to be the energy storage unit to determine a number of energy storage units.

6. The method for coordinated control of photovoltaic storage and microgrid according to claim 5 is characterized in that: The process of determining a plurality of coordinated abnormal units according to the interruption and reconnection frequency, the output power of each energy storage unit, and the load demand includes: Obtaining the interruption and reconnection frequency within a preset collaboration time length to obtain a reconnection frequency set; Obtaining the output power within the preset coordination time to obtain an output power set; Obtaining the load demand within the preset coordination time to obtain a load demand set; Performing maximum-minimum normalization processing on the output power at each moment within the preset coordination time according to the output power set to obtain a power normalization value; Performing maximum-minimum normalization processing on the load demand at each moment within the preset coordination time according to the load demand set to obtain a demand normalization value; Calculating the product of the power normalization value and the preset power weight to obtain a first product, and calculating the product of the demand normalization value and the preset demand weight to obtain a second product; calculating the sum of the first product and the second product to obtain a synergy index; Acquire all the synergy indexes to obtain a synergy index set; Calculating the correlation coefficient between the reconnection frequency set and the collaboration index set to obtain a collaboration anomaly degree; When the coordination abnormality degree is greater than a preset standard abnormality degree, the energy storage unit is determined to be the coordination abnormality unit, so as to determine a plurality of coordination abnormality units.

7. The method for coordinated control of photovoltaic storage and microgrid according to claim 6 is characterized in that: The process of adjusting the preset total power fluctuation threshold according to the layout position and number of the coordinated abnormal units in each feeder and the state value of the high-current load switch to obtain the adjusted power fluctuation threshold includes: Obtaining the layout position of the coordinated abnormal units in each of the feeders to obtain the relative distances between the coordinated abnormal units and the starting point of the feeder; Obtaining the feeder number to which each of the abnormal collaborative units belongs, and counting the number of abnormal collaborative units in each feeder according to the feeder number to obtain the number of units; Performing maximum-minimum normalization processing on the relative distance at the current moment according to all the relative distances to obtain a plurality of normalized distances; Calculate the standard deviation of all the normalized distances to obtain the distribution concentration; calculating a concentration factor based on the distribution concentration and the number of units; Normalizing the current distribution concentration according to all the distribution concentrations within the preset adjustment time to obtain a normalized concentration; Normalizing the current number of units according to the total number of units within the preset adjustment time to obtain a normalized number; Performing a weighted summation on a preset concentration weight, the normalized concentration degree, a preset quantity weight, the normalized quantity, a preset state value weight, and the state value of the high-current load switch to obtain a risk index; When the risk index is greater than a preset risk index threshold, the preset total power fluctuation threshold is increased according to a relative deviation between the risk index and the preset risk index threshold and a preset adjustment coefficient to obtain the adjusted power fluctuation threshold.

8. The method for coordinated control of photovoltaic storage and microgrid according to claim 7 is characterized in that: The process of correcting the photovoltaic output prediction value according to the number of the coordinated abnormal units re-determined by using the adjusted power fluctuation threshold within a preset correction period to obtain the corrected prediction value includes: Calculating the standard deviation of the unit quantity within the preset correction period to obtain a corrected quantity fluctuation value; When the corrected quantity fluctuation value is greater than a preset corrected quantity fluctuation threshold, the photovoltaic output prediction value is increased according to a relative deviation between the corrected quantity fluctuation value and the preset corrected quantity fluctuation threshold and a preset correction coefficient to obtain the corrected prediction value.

9. The method for coordinated control of photovoltaic storage and microgrid according to claim 8 is characterized in that: The process of executing the control instruction of adjusting the preset photovoltaic power generation power on the coordinated abnormal unit according to the modified predicted value and the preset predicted value range includes: When the corrected predicted value is greater than the maximum value of the preset predicted value range, executing a control instruction to reduce the preset photovoltaic power generation power according to a relative deviation between the corrected predicted value and the maximum value of the preset predicted value range and a preset control coefficient; When the corrected predicted value is less than the minimum value of the preset predicted value range, a control instruction to increase the photovoltaic power generation power is executed according to the relative deviation between the minimum value of the preset predicted value range and the corrected predicted value and the preset control coefficient.

10. The method for coordinated control of photovoltaic storage and microgrid according to claim 9 is characterized in that: The process of predicting the photovoltaic output prediction value according to all the output powers, the state of charge values, the load demands, the charging request growth rate, the average queuing time, the interruption and reconnection frequency, and a preset prediction model within a preset historical period includes: All the output power, state of charge value, charging pile load demand, target side charging request growth rate, average queue time and interruption reconnection frequency are time series aligned, missing value filled and normalized to construct a multi-dimensional input feature matrix; The multi-dimensional input feature matrix is ​​input into the preset prediction model to predict the photovoltaic output prediction value.

Images