Demand control method and system based on industrial and commercial energy storage

Abstract

The invention relates to the technical field of energy storage control, and discloses a demand control method and system based on industrial and commercial energy storage, and the method comprises the steps: obtaining and carrying out the standardized processing of a real-time load demand, an energy storage state and power grid dispatching data; establishing a load prediction model to generate demand baseline parameters, and constructing a dynamic adjustment rule base; the energy storage output is verified in real time, and the dynamic response trend of the power difference value is analyzed; and generating a demand control index to determine a charging and discharging strategy. The system comprises a load monitoring module, a strategy generation module, a dynamic execution module and a control judgment module which are respectively used for realizing data acquisition and processing, model construction, output verification analysis and strategy judgment functions. According to the scheme, through multi-dimensional data integration, dynamic rule base optimization and multi-constraint coordination technologies, the precision and economical efficiency of industrial and commercial energy storage demand control are improved, the demand electric charge can be effectively reduced, the electric energy utilization rate is improved, and the method is suitable for energy storage management and power grid collaborative optimization of industrial and commercial users.

Description

Technical Field

[0001] The present invention relates to the field of energy storage control technology, and in particular to a demand control method and system based on industrial and commercial energy storage. Background Art

[0002] Amidst the global energy transition, the scientific and economic management of electricity consumption in the industrial and commercial sector, a major source of energy consumption, is drawing increasing attention. Traditional industrial and commercial electricity consumption relies primarily on direct power from the grid. With the continuous growth of electricity demand and the increasing complexity of electricity pricing policies, this model has gradually exposed numerous problems. On the one hand, industrial and commercial users face the pressure of high demand charges, which are calculated based on the user's maximum electricity demand. Large fluctuations in user load can easily lead to excessive demand, further increasing electricity costs. On the other hand, the power grid's ability to regulate the load of industrial and commercial users is limited. During peak hours, the grid's load pressure increases, potentially leading to power shortages and voltage instability, impacting users' normal production and operations. During off-peak hours, energy is wasted. Furthermore, existing energy storage systems in industrial and commercial applications often lack effective coordination with user load demand and grid dispatch information, making it impossible to dynamically adjust charging and discharging strategies based on real-time data, thus undermining the full potential of energy storage systems.

[0003] At the same time, the continuous development of smart grids and energy storage technologies has placed higher demands on the intelligent control of industrial and commercial energy storage systems. Traditional demand control methods are mostly based on fixed thresholds and simple rules, and are unable to adapt to the dynamic changes in load demand and the real-time adjustments of grid scheduling. For example, when faced with time-of-use electricity pricing policies, traditional methods have difficulty adjusting the charging and discharging behavior of energy storage systems in a timely manner based on electricity price signals, making it impossible to fully utilize low-priced electricity during off-peak periods and reduce electricity costs. Moreover, existing systems lack data processing and analysis capabilities, and are unable to effectively integrate and mine large amounts of real-time load data, energy storage status data, and grid scheduling data. It is difficult to establish accurate load forecasting models and dynamic adjustment rule bases, resulting in low accuracy and effectiveness of demand control.

[0004] Furthermore, industrial and commercial users have a wide variety of electrical equipment, complex and diverse load types, and significant differences in power curves and power consumption characteristics across different devices, which increases the difficulty of demand control. Traditional control methods are unable to precisely manage different types of loads, making it difficult to achieve optimal load distribution and rational scheduling of energy storage systems. Furthermore, the operating status of the energy storage system itself, such as its SOC value, charge and discharge rate, and equipment health, can also affect the effectiveness of demand control. Traditional methods often overlook the dynamic changes in these factors, making it impossible to adjust control strategies in a timely manner to ensure the safe and stable operation of the energy storage system. Summary of the Invention

[0005] The object of the present invention is to provide a demand control method and system based on industrial and commercial energy storage to solve the problems raised in the above background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a demand control method based on industrial and commercial energy storage, the method comprising: Obtaining real-time load demand data, energy storage system operating status data, and grid dispatch information data from industrial and commercial users, and performing data standardization on the load demand data, energy storage system operating status data, and grid dispatch data; Based on the standardized data, a load forecasting model is established to generate demand baseline parameters. Feature optimization is performed based on the demand baseline parameters to form a control strategy set. A dynamic adjustment rule base is constructed in combination with the grid dispatch information. Perform real-time matching verification of energy storage system output based on a dynamic adjustment rule base, use multi-constraint coordination technology to identify the power difference between load demand and energy storage output, and perform trend analysis on the dynamic response status of the power difference; A demand control index is generated based on the verification result of the dynamic adjustment rule base, and the charge and discharge regulation strategy of the energy storage system is determined according to the demand control index.

[0007] Preferably, the real-time load demand data includes the equipment power curve and load type identification by time period; the energy storage system operating status data includes the energy storage SOC value, charging and discharging rate and equipment health parameters; the grid dispatching information data includes the time-of-use electricity price signal and the grid carrying margin parameter; the load demand data, energy storage status data and grid dispatching data are standardized, and the standardization processing includes data cleaning, timestamp alignment, abnormal data interpolation correction and dimensional unification; after the load demand data is processed, a load characteristic matrix is ​​generated, and after the energy storage status data is processed, an energy storage state vector is generated; the load characteristic matrix is ​​associated with the grid dispatching information by time period to form a multi-dimensional constraint condition set.

[0008] Preferably, establishing a load forecasting model to generate demand baseline parameters includes the following steps: Extracting statistical characteristic parameters from the standardized load characteristic matrix, the statistical characteristic parameters including the time period average value, power extreme difference value and change rate parameter, and combining each statistical characteristic parameter in a preset ratio to generate a demand baseline parameter; Set dynamic thresholds for the demand baseline parameters in the multi-dimensional constraint condition set, filter the characteristic parameters that meet the constraint boundaries to form an initial strategy set, and eliminate characteristic parameters that exceed the constraint boundaries; Perform a time series comparative analysis on each characteristic parameter in the initial strategy set, extract the difference between load demand and energy storage output in adjacent time periods, calculate the absolute value of the difference and mark it as the time period deviation parameter; The time period deviation parameters are compared with the preset fluctuation threshold, and the characteristic parameters exceeding the fluctuation threshold are screened and added to the dynamic adjustment rule base. The electricity price sensitivity characteristics are supplemented to the dynamic adjustment rule base according to the power grid dispatch information.

[0009] Preferably, performing trend analysis on the dynamic response state of the power difference includes the following steps: Obtain the instantaneous value of load demand power and energy storage output power in real time, calculate the absolute value of the power difference between the two, and mark it as a demand fluctuation event if the power difference exceeds the preset allowable range; Count the number of demand fluctuation events within a preset period, and simultaneously obtain the energy storage system SOC change rate and the real-time power price fluctuation range of the power grid; The demand deviation index is calculated based on the number of demand fluctuation events, the SOC change rate and the fluctuation range of electricity prices. If the demand deviation index exceeds the preset critical value, the energy storage output adjustment instruction is triggered.

[0010] Preferably, the verification results of the dynamic adjustment rule base in the historical operation data of the same user are extracted, and the execution effect of each adjustment rule is weightedly calculated to generate an adjustment coefficient. If the adjustment coefficient exceeds the preset triggering times continuously, it is determined to execute the energy storage charging and discharging strategy switching.

[0011] Preferably, the present invention also includes a demand control system based on industrial and commercial energy storage, which is applied to the implementation of the above-mentioned demand control method based on industrial and commercial energy storage. The system includes a load monitoring module, a strategy generation module, a dynamic execution module and a control determination module; The load monitoring module is used to obtain real-time load demand data, energy storage system operating status data and power grid dispatch information data and perform standardized processing; The strategy generation module is used to establish a load forecasting model to generate demand baseline parameters and build a dynamic adjustment rule base; The dynamic execution module is used to perform matching verification on the energy storage output according to the dynamic adjustment rule base, and analyze the power difference between the load demand and the energy storage output; The control determination module is used to generate a demand control index and determine an energy storage regulation strategy.

[0012] Preferably, the load monitoring module includes a user-side acquisition unit and a power grid information receiving unit; The user-side acquisition unit is used to collect equipment power curves and energy storage system operating parameters of industrial and commercial users; The power grid information receiving unit is used to obtain time-of-use electricity price signals and power grid carrying margin data.

[0013] Preferably, the strategy generation module includes a baseline modeling unit and a rule optimization unit; The baseline modeling unit is used to extract the time period average value, power range value and change rate parameter from the standardized data; The rule optimization unit is used to screen characteristic parameters that meet the constraint boundaries and add electricity price sensitivity characteristics to the dynamic adjustment rule base.

[0014] Preferably, the dynamic execution module includes a difference calculation unit and a trend analysis unit; The difference calculation unit is used to detect the power difference between the load demand and the energy storage output and mark the demand fluctuation event; The trend analysis unit is used to calculate the demand deviation index by combining the SOC change rate and the electricity price fluctuation range.

[0015] Preferably, the control determination module includes a coefficient generation unit and a strategy switching unit; The coefficient generation unit is used to perform weighted calculation on the execution effect of the adjustment rule; The strategy switching unit is used to determine the energy storage charging and discharging strategy switching according to the number of consecutive triggering times of the adjustment coefficient.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The demand control method and system based on industrial and commercial energy storage provided by the present invention significantly improves the demand control accuracy and economy of industrial and commercial energy storage systems through multi-dimensional data integration and intelligent analysis. Specifically, the solution achieves efficient integration of multivariate data by acquiring real-time load demand data, energy storage system operating status data, and power grid dispatch information data, and performing standardized processing, laying the foundation for subsequent precise control. By establishing a load forecasting model to generate demand baseline parameters and combining multi-dimensional constraints to build a dynamic adjustment rule base, it is possible to dynamically optimize the charging and discharging strategy of the energy storage system according to the historical laws and real-time change trends of the load, effectively reduce the risk of exceeding the demand limit, and reduce demand electricity bill expenditures. For example, by extracting statistical characteristic parameters and setting dynamic thresholds, abnormal periods of load fluctuations can be accurately identified, and the energy storage output can be adjusted in advance to avoid demand exceeding the limit due to sudden changes in load.

[0017] In terms of dynamic response mechanisms, by matching and verifying the output of the energy storage system in real time, identifying the power difference between load demand and energy storage output, and calculating the demand deviation index based on parameters such as the SOC change rate and electricity price fluctuation range, the system can quickly respond to load fluctuation events and trigger energy storage output adjustment instructions. The application of this multi-constraint coordination technology enables the energy storage system to flexibly adjust its charging and discharging strategies under different grid dispatch conditions (such as time-of-use electricity price signals) and energy storage states, achieving the optimization goals of charging and storing low-priced electricity during off-peak periods and discharging during peak periods to reduce grid dependence, significantly improving energy utilization efficiency and economic benefits. At the same time, by analyzing the execution effect of historical adjustment rules to generate adjustment coefficients, it can automatically determine whether to switch charging and discharging strategies, achieving self-optimization of the control strategy and further improving the adaptability and intelligence of the system.

[0018] From the perspective of system architecture, the layered design of the load monitoring module, strategy generation module, dynamic execution module, and control judgment module ensures efficient coordination of data collection, model building, real-time control, and strategy optimization. The independent setting of the user-side acquisition unit and the grid information receiving unit ensures the real-time and accuracy of load data and grid information; the coordination of the baseline modeling unit and the rule optimization unit realizes the organic combination of load forecasting and dynamic rule updating; the linkage of the difference calculation unit and the trend analysis unit ensures real-time monitoring and trend prediction of power differences; the collaboration of the coefficient generation unit and the strategy switching unit provides a reliable basis for the adaptive adjustment of the control strategy. This modular design not only improves the scalability and maintainability of the system, but also realizes the closed-loop management of the entire process of demand control through the deep coordination of various modules.

[0019] In addition, this solution can timely detect abnormal conditions of the energy storage system through real-time monitoring of the operating status of the energy storage system (such as SOC value, charge and discharge rate, and equipment health parameters), issue early warnings and adjust control strategies to ensure the safe and stable operation of the energy storage system and extend the service life of the equipment. At the same time, combined with the grid carrying margin parameters, the energy storage output can be actively adjusted when the grid load is tight, reducing the pressure on the grid, improving the stability and reliability of the grid operation, and realizing two-way interaction and collaborative optimization between the user side and the grid side. In summary, the present invention comprehensively improves the demand control efficiency of industrial and commercial energy storage systems through data-driven intelligent control, real-time updating of the dynamic rule base, collaborative operation of multiple modules, and two-way response to user and grid needs. It has significant technical advantages and practical value in reducing electricity costs, improving energy utilization, and ensuring grid stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a working principle diagram of the demand control method and system based on industrial and commercial energy storage according to the present invention; Figure 2Flowchart for data standardization process; Figure 3 This is a flow chart for power difference trend analysis; Figure 4 Flowchart for charge and discharge strategy switching determination. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0022] See also Figure 1-Figure 4 The present invention relates to a demand control method based on industrial and commercial energy storage, which specifically includes the following steps: The system uses the load monitoring module's user-side acquisition unit and grid information receiving unit to obtain real-time load demand data from industrial and commercial users, energy storage system operating status data, and grid dispatch information. Load demand data includes time-based equipment power curves and load type identifiers, such as power fluctuations of production equipment during different shifts and equipment types (such as motors and heating equipment). Energy storage system operating status data includes energy storage SOC values, charge and discharge rates, and equipment health parameters, such as the battery pack's remaining charge percentage, current charge and discharge power values, and trends in battery cell internal resistance. Grid dispatch information includes time-of-use electricity price signals (such as peak, valley, and flat period electricity prices) and grid carrying margin parameters (such as remaining capacity in the substation).

[0023] This data is standardized. The specific process includes: data cleaning to remove duplicate or invalid data, synchronizing data from different sources to a unified time coordinate system using timestamp alignment technology, correcting anomalous data points using cubic spline interpolation, and eliminating dimensional differences by standardizing the units (e.g., power units are standardized to kW and electricity units are standardized to kWh). After processing, the load demand data generates a three-dimensional load characteristic matrix consisting of time period, power, and type, while the energy storage status data generates a one-dimensional energy storage state vector consisting of state of charge (SOC), charge and discharge rate, and health. The load characteristic matrix is ​​then linked to grid dispatch information along the time dimension, forming a multi-dimensional constraint set encompassing time period, electricity price, and grid capacity.

[0024] Based on the standardized data, the strategy generation module establishes a load forecasting model through a baseline modeling unit. First, statistical characteristic parameters are extracted from the load characteristic matrix, including the average power value (reflecting typical load levels), the power range (reflecting load fluctuations), and the rate of change parameter (reflecting load increase or decrease rates) for each time period. These parameters are combined according to a preset ratio (e.g., 50% for the average value, 30% for the range, and 20% for the rate of change) to generate the demand baseline parameters. For example, the baseline power for a given time period is the average value ± the range × the adjustment coefficient. Dynamic thresholds are set for the demand baseline parameters within the multi-dimensional constraint set. These thresholds are dynamically adjusted based on time-of-use electricity prices and load margins from grid dispatch information (e.g., the baseline power limit can be lowered during peak periods to reduce grid stress). The characteristic parameters that meet the constraint boundaries are selected to form an initial strategy set, and parameters that exceed the constraints (e.g., outliers exceeding the baseline power limit during off-peak periods) are eliminated. A time series comparative analysis is performed on the characteristic parameters in the initial strategy set, and the absolute value of the difference between load demand and energy storage output in adjacent time periods is calculated and labeled as the time period deviation parameter. The time period deviation parameters are compared with the preset fluctuation threshold (such as ±5% of the baseline power). Parameters exceeding the threshold are added to the dynamic adjustment rule base, and the electricity price sensitivity characteristics are supplemented according to the grid time-of-use electricity price signal (such as peak periods are more sensitive to power deviations), forming a dynamic adjustment rule that includes time period, deviation threshold, and electricity price sensitivity coefficient.

[0025] The dynamic execution module uses the difference calculation unit to obtain the instantaneous load demand power and the energy storage output power in real time and calculate the absolute difference between the two. If the difference exceeds a preset allowable range (e.g., ±10% of the baseline power), it is marked as a demand fluctuation event. The module counts the number of events within a preset period (e.g., 15 minutes) and simultaneously obtains the energy storage system SOC change rate (e.g., the percentage of SOC decrease per minute) and the real-time grid electricity price fluctuation range (e.g., the rate of change of the electricity price relative to the baseline value during the current period). Based on this data, the trend analysis unit calculates the demand deviation index using a multi-constraint coordination technique. The formula is: Demand Deviation Index = Number of Events × Weight 1 + SOC Change Rate × Weight 2 + Electricity Price Fluctuation Range × Weight 3 (weights are determined based on historical data training, e.g., Weight 1 = 0.5, Weight 2 = 0.3, and Weight 3 = 0.2). If the index exceeds a preset critical value (e.g., 0.8), an energy storage output adjustment command is triggered, and the next control phase begins.

[0026] Based on the verification results of the dynamic adjustment rule base, the system generates demand control indicators, including charge and discharge power thresholds and SOC adjustment ranges. The coefficient generation unit of the control judgment module extracts the verification results of the dynamic adjustment rules from the historical operating data of the same user, performs a weighted calculation on the execution effect of each rule (for example, assigning a weight based on the proportion of power deviation reduction after adjustment) to generate an adjustment coefficient. If the adjustment coefficient exceeds a preset number of triggers (for example, three times), the strategy switching unit determines to switch the energy storage charge and discharge strategy, for example, switching from "peak shaving" to "valley filling" or adjusting the charge and discharge power slope to match the current load fluctuation characteristics.

[0027] Example 1: The system uses the load monitoring module's user-side data collection unit and grid information receiving unit to acquire real-time load demand data for industrial and commercial users, energy storage system operating status data, and grid dispatch information. Real-time load demand data includes time-based equipment power curves and load type identification. Time-based equipment power curves are collected at a minute-by-minute frequency. For example, for motors and heating equipment in a production workshop, power fluctuations during different time periods (e.g., morning, midday, and evening shifts) can be captured, down to the power value changes within each 5-minute interval. Load type identification is obtained by associating equipment numbers with a database, such as marking motors "M," heating equipment "H," and lighting equipment "L," allowing for subsequent classification and processing of different load types.

[0028] Energy storage system operating status data includes the energy storage state of charge (SOC), charge and discharge rate, and equipment health parameters. The energy storage SOC value is monitored and uploaded in real time by the battery management system (BMS), reflecting the remaining charge percentage of the battery pack with an accuracy of ±1%. The charge and discharge rate is the current power value of the energy storage system, measured in kW, and can display the energy storage system's current charging or discharging state and the corresponding power level in real time. Equipment health parameters include battery pack temperature and cell voltage consistency indicators. For example, the temperature of each cell is obtained through temperature sensors deployed in the battery module, and the temperature standard deviation is calculated to assess temperature consistency. Voltage consistency is determined by monitoring the cell voltage range. If the difference between a cell voltage and the average voltage exceeds a preset threshold, it is considered to be abnormal health.

[0029] Grid dispatch information includes time-of-use electricity price signals and grid load margin parameters. The time-of-use price signals are sent by the grid according to preset time periods (e.g., peak period 8:00-12:00, off-peak period 12:00-18:00, and off-peak period 22:00-6:00 the following day). They contain the electricity price values ​​for each period, such as 0.8 yuan / kWh during peak period and 0.3 yuan / kWh during off-peak period. The grid load margin parameter is the current remaining capacity of the substation, measured in kW, reflecting the grid's ability to handle additional load during the current period. For example, if the current remaining capacity of a substation is 100 kW, it means that the substation can still accept a total load of 100 kW without exceeding the safe operating limit.

[0030] After acquiring the aforementioned data, load demand data, energy storage status data, and grid dispatch data need to be standardized. This standardization process specifically includes data cleaning, timestamp alignment, abnormal data interpolation correction, and dimensionality unification. The data cleaning phase utilizes a sliding window filtering algorithm with a 15-minute window length to process the device power curve and remove jump data points caused by signal interference, transient equipment startup and shutdown, and so on. For example, if a spike data point significantly exceeds the normal operating range in the device power curve during a certain period of time, the point is identified as an outlier and removed by calculating the mean within the sliding window.

[0031] Timestamp alignment technology uses a timestamp-based bidirectional matching algorithm to synchronize load demand data, energy storage status data, and grid dispatch information data into a unified time coordinate system. Specifically, each type of data is sampled at a 5-minute interval, and data from different sources and different collection frequencies are aligned within this interval to ensure temporal consistency during subsequent analysis and processing. For example, device power data collected once per second is aggregated into a 5-minute average, which aligns it with energy storage SOC data and grid time-of-use electricity price data collected every 5 minutes.

[0032] Abnormal data interpolation correction uses cubic spline interpolation to address possible abnormal values ​​in energy storage health parameters. Taking battery cell voltage data as an example, if a battery cell voltage is detected at a certain moment outside the normal range (for example, the normal voltage range is 3.2V-3.8V, and the detected value at a certain moment is 2.5V), the normal voltage values ​​of the battery cell before and after the moment are used to calculate the estimated value at that moment through the cubic spline interpolation algorithm to replace the abnormal data point to ensure data continuity and reliability.

[0033] Dimensional unification involves converting data of varying physical dimensions into dimensionless or uniformly dimensional data. Power data is uniformly converted to kW; electricity data is converted to kWh; energy storage SOC is expressed as a percentage; electricity prices are expressed in yuan / kWh; and device health parameters, such as temperature in °C and voltage in V, are used for temperature and voltage. To facilitate subsequent model processing, normalization is used to convert parameters such as power, electricity prices, and SOC into dimensionless data in the [0, 1] range. The specific formula is: Normalized value = (original value - minimum value) / (maximum value - minimum value), where the minimum and maximum values ​​are statistically derived from historical data.

[0034] After normalization, load demand data is used to generate a load feature matrix. This matrix consists of rows representing the number of time periods, and columns representing characteristic dimensions such as power and load type identification codes. For example, if the rows are 288 5-minute time periods per day, and the columns include the normalized power values ​​for each time period and the one-hot encoding of the load type identification (e.g., motor equipment is coded as [1,0,0], and heating equipment is coded as [0,1,0]), then a load feature matrix of 288 × (1+N) is formed, where N is the number of load types.

[0035] After the energy storage state data is processed, an energy storage state vector is generated. This vector contains elements such as the normalized SOC value, the normalized charge and discharge rate value, and the normalized device health value, forming a one-dimensional vector of 1×M, where M is the number of energy storage state features.

[0036] Finally, the load characteristic matrix is ​​associated with the grid dispatch information by time period to form a multi-dimensional constraint set. Specifically, each time period in the load characteristic matrix is ​​associated with the corresponding time-of-use electricity price and grid load margin parameters. For example, if the power in the load characteristic matrix for a certain time period is 0.6 (normalized value) and the load type is motor, the corresponding grid dispatch information is a peak-time electricity price of 0.8 yuan / kWh and a grid load margin of 80kW. This forms a five-dimensional constraint condition that includes time period, power, load type, electricity price, and grid load margin, providing multi-dimensional data support for the subsequent establishment of load forecasting models and the generation of control strategies. Through the above standardized processing flow, the accuracy, consistency, and availability of input data are ensured, laying the foundation for the effective implementation of the entire demand control method.

[0037] Example 2: The baseline modeling unit of the strategy generation module extracts statistical characteristic parameters and generates demand baseline parameters based on the standardized load characteristic matrix. The load characteristic matrix contains information such as power data and load type identification for each time period, with each time period being 5 minutes, covering a full 24-hour period. For example, for a commercial user's weekday data, the load characteristic matrix can be obtained for 288 time periods, from 00:00-00:05 to 23:55-24:00. Each time period corresponds to a row of data, including the average power, maximum power, minimum power, and load type code for that period.

[0038] Statistical characteristic parameters are extracted from the load characteristic matrix, including the period average, power range, and rate of change parameter. The period average is the arithmetic mean of the power data within each period and reflects the typical load level during that period. For example, if the power data collected during the period from 09:00 to 09:05 is 198kW, 202kW, 200kW, 199kW, and 201kW, the period average is (198 + 202 + 200 + 199 + 201) / 5 = 200kW. The power range is the difference between the maximum and minimum power values ​​within each period and measures the load fluctuation range within that period. For example, if the maximum power value in a period is 205kW and the minimum power value is 195kW, the range is 205 - 195 = 10kW. The rate of change parameter is the ratio of the power change between adjacent periods to the time interval, reflecting the rate of increase or decrease in load demand. Assuming the average power during the period 08:55-09:00 is 170kW and the average power during the period 09:00-09:05 is 200kW, the rate of change is (200-170) / 5=6kW / minute.

[0039] Each statistical characteristic parameter is combined in a preset ratio to generate the demand baseline parameter. The preset ratios are determined based on historical data and control objectives. For example, the period average is set at 50%, the power range at 30%, and the rate of change parameter at 20%. For example, during the 09:00-09:05 period, the period average is 200 kW, the range is 10 kW, and the rate of change is 6 kW / minute. Therefore, the demand baseline parameter is: Baseline power = period average ± (range × 30% + rate of change × 20% × time interval). The time interval is measured in hours, with 5 minutes being 1 / 12 of an hour. Therefore, the baseline power is 200 ± (10 × 0.3 + 6 × 0.2 × 1 / 12) = 200 ± (3 + 0.1) = 200 ± 3.1 kW, meaning the baseline demand range for this period is 196.9 kW to 203.1 kW.

[0040] Dynamic thresholds are set for the demand baseline parameters within the multi-dimensional constraint set. The dynamic thresholds are set based on time-of-use electricity prices and grid capacity margin parameters from the grid dispatch information. For example, during peak hours (e.g., 9:00 AM to 12:00 PM), the grid capacity margin is low. To alleviate grid pressure, the upper limit of the demand baseline power is lowered by 10%. Assuming the original upper limit of the baseline power is 203.1 kW, the lower limit is 203.1 × (1-10%) = 182.79 kW, while the lower limit remains at 196.9 kW. During off-peak hours (e.g., 10:00 PM to 6:00 AM), the grid capacity margin is high, and the baseline threshold can be appropriately relaxed, for example, by raising the upper limit by 15%, to fully utilize off-peak, low-priced electricity for energy storage charging.

[0041] Based on the dynamic threshold, feature parameters that meet the constraint boundaries are selected to form the initial policy set, and feature parameters that exceed the constraint boundaries are eliminated. For example, during the peak period of 09:00-09:05, if the power value corresponding to a feature parameter is 205kW, which exceeds the lowered baseline power limit of 182.79kW, then this parameter is eliminated. However, if the power value corresponding to another feature parameter is 190kW, which is between 196.9kW and 182.79kW (note the logical relationship here: the actual upper limit should be 182.79kW, and the original lower limit of 196.9kW needs to be adjusted. In this example, it is assumed that the dynamic threshold only adjusts the upper limit, leaving the lower limit unchanged. Therefore, the parameters that meet the conditions should be ≤182.79kW and ≥196.9kW. However, in real scenarios, the baseline range may be recalculated based on the threshold adjustment, so the adjusted baseline range is used here), then this parameter is retained in the initial policy set.

[0042] Next, a time series comparative analysis is performed on each characteristic parameter in the initial strategy set to extract the difference between load demand and energy storage output within adjacent time periods. For example, for the adjacent time periods of 09:00-09:05 and 09:05-09:10, assuming the load demand during 09:00-09:05 is 200kW and the energy storage output is 190kW, the difference is 200-190 = 10kW. For the time period of 09:05-09:10, the load demand is 210kW and the energy storage output is 195kW, resulting in a difference of 210-195 = 15kW. The absolute values ​​of these differences are calculated, yielding 10kW and 15kW, respectively, and are labeled as the time period deviation parameters.

[0043] The time period deviation parameter is compared with a preset fluctuation threshold. The preset fluctuation threshold is set based on the energy storage system's regulation capabilities and grid stability requirements, for example, ±5% of the baseline power. For example, during the 09:00-09:05 period, the baseline power is 200kW, and the fluctuation threshold is 200 × 5% = 10kW. The absolute value of the time period deviation parameter for this period, 10kW, equals the threshold and is considered critical. The absolute value of the time period deviation parameter for the 09:05-09:10 period, 15kW, exceeds the threshold of 10kW. This characteristic parameter is then added to the dynamic adjustment rule base. Simultaneously, electricity price sensitivity characteristics are added to the dynamic adjustment rule base based on grid dispatch information. For example, if the current period is a peak period and the sensitivity to electricity prices is high, the deviation threshold adjustment coefficient for this period is set to 0.8 in the dynamic adjustment rule (that is, the actual allowable deviation threshold = baseline power × 5% × 0.8 = 8kW) to more strictly control load fluctuations and reduce the impact of peak periods on the power grid; if it is a valley period and the sensitivity to electricity prices is low, the deviation threshold adjustment coefficient can be set to 1.2 to allow a larger load fluctuation range to fully utilize low-priced electricity for energy storage charging.

[0044] Each rule in the dynamic adjustment rule base contains information such as time period, deviation threshold, and electricity price sensitivity characteristics. For example, a rule might be expressed as follows: During peak hours (09:00-12:00), the deviation threshold is 8kW, and the electricity price sensitivity coefficient is 1.5 (used for weight adjustment in subsequent demand deviation index calculations); during off-peak hours (22:00-6:00 the following day), the deviation threshold is 12kW, and the electricity price sensitivity coefficient is 0.7. By continuously screening and supplementing characteristic parameters, the dynamic adjustment rule base is continuously optimized, providing a more accurate basis for real-time matching and verification of energy storage system output, ensuring that demand control strategies can adapt to the grid environment and user load characteristics at different times.

[0045] Example 3: The dynamic execution module monitors and analyzes the power difference between load demand and energy storage output and its dynamic response status in real time through the difference calculation unit and trend analysis unit. The difference calculation unit obtains the instantaneous value of load demand power and energy storage output power in real time at a millisecond frequency. Both are instantaneous power data in kW, which are recorded as and ,in Indicates a time point. Calculate the absolute value of the power difference between the two, the formula is:

[0046] Where, for The absolute value of the power difference at the moment (unit: kW). The preset allowable range is the fluctuation range determined based on the demand baseline parameters, recorded as ,in The deviation threshold (unit: kW) is set by the dynamic adjustment rule base based on factors such as time period and electricity price. , it is marked as a demand fluctuation event, indicating that the difference between the current load demand and the energy storage output exceeds the normal adjustment range set by the system, and further analysis and control actions need to be triggered.

[0047] Taking the actual operation scenario of a certain industrial and commercial user as an example, assuming that during a peak period At this moment, the instantaneous value of load demand power , instantaneous value of energy storage output power , dynamically adjust the allowable deviation threshold set by the rule base for that period Calculation can be obtained ,because , does not exceed the allowed range and does not trigger the demand fluctuation event mark. At this moment, the load demand suddenly increases to , the energy storage output power is still ,but , exceeds the allowable deviation threshold, it is marked as a demand fluctuation event, and the time of the event, power difference and other information are recorded.

[0048] Count the number of demand fluctuation events within the preset period, the preset period It can be set according to the user's load characteristics and control accuracy requirements, for example During this period, the system records all the The number of events that occur is recorded as The SOC change rate of the energy storage system and the real-time power price fluctuation range of the power grid are obtained simultaneously. The SOC change rate of the energy storage system is the change of SOC per unit time, which is recorded as , the unit is , reflecting the charge and discharge intensity of the energy storage system during the cycle, for example The real-time electricity price fluctuation range of the power grid is the rate of change of the current period electricity price compared with the benchmark electricity price, which is recorded as , the unit is The base electricity price is the standard electricity price of the power grid during that period. For example, the base electricity price during peak period is If the real-time electricity price rises to ,but .

[0049] The number of events fluctuates according to demand , SOC change rate and electricity price fluctuations , the demand deviation index is calculated by multi-constraint coordination technology, and the formula is:

[0050] Where, is the demand deviation index (dimensionless); 、 、 is the weight coefficient, which corresponds to the impact weight of the number of events, SOC change rate, and electricity price fluctuation range. Its value is determined by historical data training and meets the For example, setting 、 、 , indicating that the number of demand fluctuation events has the greatest impact on the demand deviation index, followed by the SOC change rate, and the electricity price fluctuation amplitude has the smallest impact.

[0051] Taking the statistical data within the preset period as an example, assuming that The number of demand fluctuation events is counted within Second, the energy storage SOC change rate (The absolute value is ), the fluctuation range of real-time power price of power grid (The absolute value is ). Substituting into the formula, we can get:

[0052] The default threshold is , for example, , when the calculated demand deviation index When the system determines that the matching status between the current load demand and the energy storage output has exceeded the controllable range of the system, the energy storage output adjustment instruction is triggered. The adjustment instruction is sent to the converter (PCS) of the energy storage system through the collaborative interaction of the dynamic execution module and the control judgment module. For example, the instruction requires the energy storage discharge power to be increased by , in order to reduce the power difference between load demand and energy storage output, Gradually fall back to the allowable deviation threshold within the range.

[0053] Throughout the analysis process, the difference calculation unit and the trend analysis unit achieve dynamic tracking of power differences and quantitative assessment of demand deviations through real-time data interaction and algorithm processing. The difference calculation unit ensures timely capture of sudden load changes, while the trend analysis unit comprehensively judges the system's operating status through multi-dimensional parameter fusion, providing a scientific basis for real-time adjustment of energy storage output. This process does not rely on preset experimental effect data, but is based on actual collected operating parameters and algorithm logic to achieve dynamic optimization of demand control for industrial and commercial energy storage systems, ensuring that under the conditions of grid dispatch constraints and user load fluctuations, the energy storage system can efficiently and stably participate in demand management, thereby improving the economy and reliability of power system operation.

[0054] Example 4: The coefficient generation unit of the control judgment module works in conjunction with the strategy switching unit to evaluate the execution effect of the dynamic adjustment rules based on the user's historical operation data, and accordingly determine whether to trigger the energy storage charging and discharging strategy switching. The specific process is as follows: The system extracts verification results for each rule in the dynamic adjustment rule library from the same user's historical operation database. This includes information such as the rule execution time, the corresponding load period, the power difference value before and after adjustment, and the change in energy storage SOC. For example, a dynamic adjustment rule applicable to the peak period (9:00-12:00) has the following core parameters: a tolerance threshold of 10kW, a price sensitivity coefficient of 1.2, and an adjustment strategy of increasing energy storage discharge power by 5kW per time. In the past week's operating data, this rule was executed 10 times, and the change in power difference and energy storage SOC response data were recorded after each execution.

[0055] For each rule execution, the coefficient generation unit calculates the effectiveness of the rule. For example, during the first execution, the power difference before adjustment was 15 kW (load demand 215 kW, energy storage output 200 kW). After the rule execution, the energy storage discharge power was increased by 5 kW, reducing the power difference to 10 kW (energy storage output to 205 kW). The difference reduction ratio is (15 - 10) / 15 ≈ 33.3%. During the second execution, the power difference before adjustment was 18 kW (load demand 220 kW, energy storage output 202 kW). After adjustment, the difference was reduced to 13 kW, with a reduction ratio of (18 - 13) / 18 ≈ 27.8%. Similarly, the difference reduction ratios recorded for the third to tenth executions are 40%, 25%, 30%, 35%, 28%, 32%, 38%, and 31%, respectively.

[0056] To assess the overall effectiveness of rule execution, the coefficient generation unit weights the performance of each execution. Weights are assigned based on the chronological order of rule execution. For example, the first execution is weighted at 10%, and the weight increases by 5% with each subsequent execution, reflecting the more significant impact of recent executions on current policy adjustments. The specific weights are as follows: 10% for the first execution, 15% for the second, 20% for the third, 25% for the fourth, 30% for the fifth, 35% for the sixth, 40% for the seventh, 45% for the eighth, 50% for the ninth, and 55% for the tenth (Note: The actual weights must be normalized; this is for simplification).

[0057] Taking the first to third executions as an example, calculate the adjustment coefficient: First time: 33.3% × 10% = 3.33% Second time: 27.8% × 15% = 4.17% Third time: 40% × 20% = 8% The cumulative contribution values ​​for the first three executions are 3.33% + 4.17% + 8% = 15.5%. Similarly, the contribution values ​​for all 10 executions are calculated and summed, resulting in an adjustment coefficient of 32% for this rule (assuming cumulative results). The adjustment coefficient reflects the average reduction in power differences after rule execution; a higher value indicates greater rule effectiveness.

[0058] The strategy switching unit determines whether to switch strategies based on the number of consecutive triggering cycles of the adjustment coefficient. The preset trigger condition is: the adjustment coefficient exceeds a preset threshold (e.g., 30%) three times in a row. Continuing with the above rule as an example, if the adjustment coefficients are 35%, 33%, 31%, and 34% in four consecutive execution cycles, each exceeding the 30% threshold, and if this occurs four times in a row (more than the preset three times), then the current charge and discharge strategy is determined to require a switch.

[0059] The specific logic of strategy switching is based on the matching degree between user load characteristics and grid dispatch information. For example, if the current strategy is a "fixed power discharge strategy" (such as always discharging at 50kW), if the adjustment coefficient continuously exceeds the threshold, the system determines that this strategy can no longer effectively cope with load fluctuations and switches to a "dynamic slope tracking strategy." The dynamic slope tracking strategy automatically adjusts the slope of the energy storage discharge power (such as increasing or decreasing by 2kW per minute) by monitoring the rate of change of load demand in real time to more accurately track load fluctuations. The specific switching process is as follows: When the coefficient generation unit detects that the adjustment coefficient of a certain rule exceeds 30% for four consecutive times, it sends a trigger signal to the strategy switching unit; The strategy switching unit retrieves the currently executed charge and discharge strategy parameters, such as fixed discharge power value, adjustment cycle, etc. Based on the rule features with high adjustment coefficients in historical data (such as high electricity price sensitivity and high load fluctuation periods), corresponding alternative strategies are matched from the strategy library, such as selecting a dynamic adjustment strategy based on PID control; Send a strategy switching instruction to the energy storage converter (PCS) through the control interface, including the parameter settings of the new strategy (such as the proportional coefficient, integral time, and differential time of the PID controller); After the energy storage system switches to the new strategy, the coefficient generation unit reinitializes the execution effect statistics of the rule and begins to evaluate the effectiveness of the new strategy.

[0060] In another example, if a user frequently triggers the adjustment rule during off-peak hours (10:00 PM to 6:00 AM), and the adjustment coefficient continuously exceeds the threshold, the system may determine that the current "nighttime charging strategy" (e.g., charging at a fixed 30kW power) is not fully utilizing off-peak power resources and switch to an "adaptive charging strategy," dynamically adjusting the charging power based on the real-time grid capacity margin and energy storage health (e.g., the maximum chargeable power is 80% of the grid's remaining capacity). This switching maximizes the energy storage system's charging efficiency and reduces user electricity costs while ensuring grid security.

[0061] The entire process utilizes quantitative evaluation driven by historical data, avoiding control biases caused by subjective experience and ensuring that energy storage charging and discharging strategies can be dynamically optimized based on actual operational performance. The coefficient generation unit's weighted calculation method flexibly adapts to the varying importance of different time periods and rules, while the strategy switching unit implements automated decision-making through preset logic, eliminating the need for human intervention. This mechanism enables the demand control system to continuously learn user load patterns during long-term operation, improving the utilization efficiency of energy storage resources and the accuracy of demand control, thereby achieving two-way optimization for both industrial and commercial users and the power grid.

[0062] Example 5: Each module of the demand control system implements specific functions through hardware deployment and software collaboration. The following describes the system's module composition and interaction process in detail based on specific application scenarios: 1. Implementation of load monitoring module The load monitoring module serves as the system's data entry point and consists of a user-side data collection unit and a grid information receiving unit. The user-side data collection unit is deployed within the internal power distribution system of commercial and industrial users and uses industrial-grade IoT sensors for data collection. For example, a Modbus protocol power transmitter is installed in the user's power distribution cabinet. This device uses current transformers and voltage transformers to collect real-time power data from each branch circuit, including active power, reactive power, and apparent power, at a sampling rate of 1 second. The data is encoded in Modbus RTU format and transmitted to a data concentrator via the RS485 bus. For energy storage system operating parameters, the user-side data collection unit communicates with the battery management system (BMS) via the CAN bus to obtain the energy storage system's state of charge (SOC), charge and discharge rates (e.g., current discharge power of 45kW), and device health parameters (e.g., average battery pack temperature of 25°C and cell voltage range of 50mV).

[0063] The grid information receiving unit obtains grid dispatch information through a dedicated power communication network. For example, a regional power grid sends time-of-use electricity price signals and grid capacity margin parameters to the user end via the 104 protocol. Time-of-use electricity prices are divided into three periods: peak (8:00-12:00, price 0.85 yuan / kWh), flat (12:00-18:00, price 0.6 yuan / kWh), and off-peak (22:00-6:00 the following day, price 0.3 yuan / kWh). The grid capacity margin parameters update the remaining capacity of the substation in real time. For example, if it displays 95kW at a certain moment, it means that the substation can currently withstand an upper limit of 95kW of new load. Both types of data are transmitted to the system's edge computing gateway via an encrypted channel and stored synchronously with user-side data in a local database.

[0064] 2. Implementation of the Strategy Generation Module The strategy generation module includes a baseline modeling unit and a rule optimization unit, which implement data processing and strategy generation based on software algorithms. The baseline modeling unit uses Python's Pandas library to perform statistical analysis on the standardized load characteristic matrix. For example, based on a user's load data from 9:00-9:05 on weekdays, the average power value (200kW), range value (20kW), and rate of change (5kW / minute) are extracted for this period, and the demand baseline parameters are generated according to a preset ratio (e.g., the baseline power is 200±15kW). The rule optimization unit uses a decision tree algorithm to filter characteristic parameters based on multi-dimensional constraints (such as time period, electricity price, and grid capacity). During peak hours, the decision tree model prioritizes parameters with power values ​​below the baseline upper limit and embeds price sensitivity characteristics (e.g., peak hour adjustments have a high priority) into the dynamic adjustment rule library.

[0065] Taking a dynamic adjustment rule as an example, the rule optimization unit, through historical data training, discovered that when the grid's carrying capacity margin is less than 100kW during peak hours, the probability of load demand exceeding the baseline power by 10% is high. Therefore, a rule was generated: "During peak hours and when the grid's remaining capacity is less than 100kW, the deviation threshold will be tightened from ±10% of the baseline power to ±8%, and the energy storage discharge power adjustment step size will be increased from 5kW to 8kW." This rule was developed through feature engineering and algorithm training and stored in a SQL table within the dynamic adjustment rule base. Fields include time period, grid capacity threshold, deviation threshold coefficient, and adjustment step size.

[0066] 3. Implementation of Dynamic Execution Module The dynamic execution module, consisting of a difference calculation unit and a trend analysis unit, is responsible for real-time verification and trend analysis. The difference calculation unit implements high-speed data processing based on FPGA hardware, calculating the power difference between the load demand and the energy storage output with microsecond latency. For example, when the instantaneous load demand is 210kW and the energy storage output is 185kW, the difference calculation unit immediately determines the difference to be 25kW. This difference is then compared to the allowable deviation threshold in the dynamic adjustment rule base (e.g., 20kW during peak hours). If exceeded, it is marked as a demand fluctuation event, and the event timestamp and difference value are recorded.

[0067] The trend analysis unit uses the MATLAB mathematical engine to evaluate demand deviations. Within a 15-minute statistical cycle, assuming three demand fluctuation events are detected, the energy storage SOC change rate is -0.6% / minute (discharge state), and the real-time grid electricity price fluctuation range is +15% (peak price increase). The trend analysis unit comprehensively calculates the degree of demand deviation based on preset weighting logic (e.g., a weight of 0.5 for the number of events, a weight of 0.3 for the SOC change rate, and a weight of 0.2 for the electricity price fluctuation range) to determine whether to trigger an adjustment instruction. If the assessment result exceeds the critical value, an adjustment request is sent to the control decision module via the OPCUA protocol, including parameters such as the current difference, fluctuation frequency, and energy storage status.

[0068] 4. Implementation of the Control Judgment Module The coefficient generation unit and strategy switching unit of the control judgment module implement strategy optimization based on data mining and automated logic. The coefficient generation unit retrieves the execution records of a dynamic adjustment rule from the historical database. For example, the rule "allowing a deviation threshold of 15kW during off-peak hours" has been executed 20 times in the past month, and the power difference has been reduced by 20%-40% after each execution. Through weighted calculation (for example, the weight of the execution records in the past week accounts for 70%), the adjustment coefficient of the rule is 32%, indicating that its average effectiveness is 32%. If the coefficient exceeds the preset threshold (such as 30%) for five consecutive times, the strategy switching unit determines that the current charging and discharging strategy (such as a fixed charging power of 40kW) has reached an optimization bottleneck and needs to switch strategies.

[0069] A specific scenario for policy switching is as follows: A user has long adopted a "fixed power charging strategy" during off-peak hours. However, as production equipment increases, load fluctuations during off-peak hours intensify, causing the dynamic adjustment rules to be frequently triggered and the adjustment coefficient to remain high. After the system detects this trend, the policy switching unit retrieves the "load tracking charging strategy" from the policy library. This strategy monitors the user's load curve in real time and sets the energy storage charging power to 70% of the remaining grid capacity (for example, when the remaining grid capacity is 120kW, the charging power is automatically adjusted to 84kW) to avoid overload during charging. The switching command is sent to the energy storage converter (PCS) via Industrial Ethernet. Upon receiving the command, the PCS reconfigures the control parameters, adjusts the charging power slope, and sends a successful switching signal to the system.

[0070] 5. Inter-module interaction and system integration Each module interacts with data in real time through a message queue (such as RabbitMQ). Data collected by the load monitoring module is standardized and pushed to the "raw data queue" in JSON format. The strategy generation module reads data from the queue, completes baseline modeling and rule optimization, and pushes dynamic adjustment rules to the "control rule queue." The dynamic execution module subscribes to this queue, obtains rules in real time, performs power difference verification, and pushes analysis results to the "adjustment request queue." The control decision module reads requests from this queue, performs coefficient calculations and strategy switching, and pushes final instructions to the "execution instruction queue" for execution by the energy storage system.

[0071] In terms of hardware deployment, the sensors and communication equipment of the load monitoring module are distributed at the user site and on the grid side. The strategy generation module and the control judgment module run on the edge computing server (configured with an Intel i7 processor, 16GB of memory, and a 512GB SSD). The FPGA board of the dynamic execution module is integrated into the industrial control cabinet. The various components are connected through a redundant network to ensure the stability and reliability of the system in complex industrial environments.

[0072] Through the above-mentioned modular design and collaborative mechanism, the demand control system achieves full-process automation from data collection, strategy generation, dynamic execution to strategy optimization. It can accurately adapt to the load characteristics and grid dispatch requirements of industrial and commercial users, and provides a complete technical solution for the efficient operation and demand control of energy storage systems.

[0073] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0074] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A demand control method based on industrial and commercial energy storage, characterized in that: The method comprises the following steps: Obtaining real-time load demand data, energy storage system operating status data, and grid dispatch information data from industrial and commercial users, and performing data standardization on the load demand data, energy storage system operating status data, and grid dispatch data; Based on the standardized data, a load forecasting model is established to generate demand baseline parameters. Feature optimization is performed based on the demand baseline parameters to form a control strategy set. A dynamic adjustment rule base is constructed in combination with the grid dispatch information. Perform real-time matching verification of energy storage system output based on a dynamic adjustment rule base, use multi-constraint coordination technology to identify the power difference between load demand and energy storage output, and perform trend analysis on the dynamic response status of the power difference; A demand control index is generated based on the verification result of the dynamic adjustment rule base, and the charge and discharge regulation strategy of the energy storage system is determined according to the demand control index.

2. A demand control method based on industrial and commercial energy storage according to claim 1, characterized in that: The real-time load demand data includes the equipment power curve and load type identification by time period; the energy storage system operating status data includes the energy storage SOC value, charging and discharging rate and equipment health parameters; the grid dispatch information data includes time-of-use electricity price signals and grid carrying margin parameters; the load demand data, energy storage status data and grid dispatch data are standardized, and the standardization processing includes data cleaning, timestamp alignment, abnormal data interpolation correction and dimensional unification; after processing the load demand data, a load characteristic matrix is ​​generated, and after processing the energy storage status data, an energy storage state vector is generated; the load characteristic matrix and the grid dispatch information are associated with time periods to form a multi-dimensional constraint condition set.

3. A demand control method based on industrial and commercial energy storage according to claim 2, characterized in that: Establishing a load forecasting model to generate demand baseline parameters includes the following steps: Extracting statistical characteristic parameters from the standardized load characteristic matrix, the statistical characteristic parameters including the time period average value, power extreme difference value and change rate parameter, and combining each statistical characteristic parameter in a preset ratio to generate a demand baseline parameter; Set dynamic thresholds for the demand baseline parameters in the multi-dimensional constraint condition set, filter the characteristic parameters that meet the constraint boundaries to form an initial strategy set, and eliminate characteristic parameters that exceed the constraint boundaries; Perform a time series comparative analysis on each characteristic parameter in the initial strategy set, extract the difference between load demand and energy storage output in adjacent time periods, calculate the absolute value of the difference and mark it as the time period deviation parameter; The time period deviation parameters are compared with the preset fluctuation threshold, and the characteristic parameters exceeding the fluctuation threshold are screened and added to the dynamic adjustment rule base. The electricity price sensitivity characteristics are supplemented to the dynamic adjustment rule base according to the power grid dispatch information.

4. The method for demand control based on industrial and commercial energy storage according to claim 3, characterized in that: The trend analysis of the dynamic response state of the power difference includes the following steps: Obtain the instantaneous value of load demand power and energy storage output power in real time, calculate the absolute value of the power difference between the two, and mark it as a demand fluctuation event if the power difference exceeds the preset allowable range; Count the number of demand fluctuation events within a preset period, and simultaneously obtain the energy storage system SOC change rate and the real-time power price fluctuation range of the power grid; The demand deviation index is calculated based on the number of demand fluctuation events, the SOC change rate and the fluctuation range of electricity prices. If the demand deviation index exceeds the preset critical value, the energy storage output adjustment instruction is triggered.

5. A demand control method based on industrial and commercial energy storage according to claim 4, characterized in that: The verification results of the dynamic adjustment rule base in the historical operation data of the same user are extracted, and the execution effect of each adjustment rule is weightedly calculated to generate an adjustment coefficient. If the adjustment coefficient exceeds the preset trigger number continuously, it is determined to execute the energy storage charging and discharging strategy switch.

6. A demand control system based on industrial and commercial energy storage, wherein the system is applied to implement a demand control method based on industrial and commercial energy storage according to any one of claims 1 to 5, characterized in that: The system includes a load monitoring module, a strategy generation module, a dynamic execution module and a control determination module; The load monitoring module is used to obtain real-time load demand data, energy storage system operating status data and power grid dispatch information data and perform standardized processing; The strategy generation module is used to establish a load forecasting model to generate demand baseline parameters and build a dynamic adjustment rule base; The dynamic execution module is used to perform matching verification on the energy storage output according to the dynamic adjustment rule base, and analyze the power difference between the load demand and the energy storage output; The control determination module is used to generate a demand control index and determine an energy storage regulation strategy.

7. The demand control system based on industrial and commercial energy storage according to claim 6, characterized in that: The load monitoring module includes a user-side acquisition unit and a power grid information receiving unit; The user-side acquisition unit is used to collect equipment power curves and energy storage system operating parameters of industrial and commercial users; The power grid information receiving unit is used to obtain time-of-use electricity price signals and power grid carrying margin data.

8. The demand control system based on industrial and commercial energy storage according to claim 6, characterized in that: The strategy generation module includes a baseline modeling unit and a rule optimization unit; The baseline modeling unit is used to extract the time period average value, power range value and change rate parameter from the standardized data; The rule optimization unit is used to screen characteristic parameters that meet the constraint boundaries and add electricity price sensitivity characteristics to the dynamic adjustment rule base.

9. The demand control system based on industrial and commercial energy storage according to claim 6, characterized in that: The dynamic execution module includes a difference calculation unit and a trend analysis unit; The difference calculation unit is used to detect the power difference between the load demand and the energy storage output and mark the demand fluctuation event; The trend analysis unit is used to calculate the demand deviation index by combining the SOC change rate and the electricity price fluctuation range.

10. The demand control system based on industrial and commercial energy storage according to claim 6, characterized in that: The control decision module includes a coefficient generation unit and a strategy switching unit; The coefficient generation unit is used to perform weighted calculation on the execution effect of the adjustment rule; The strategy switching unit is used to determine the energy storage charging and discharging strategy switching according to the number of consecutive triggering times of the adjustment coefficient.

Images