Industrial and commercial building energy storage optimal configuration method based on flexible load

Abstract

The invention discloses an industrial and commercial building energy storage optimization configuration method based on a flexible load, and relates to the technical field of energy management and optimization, and the method comprises the steps: S1, collecting the real-time operation data and energy consumption data of various types of equipment in a building, S2, building an energy consumption model and a scheduling model of the equipment in the building based on the collected data, and carrying out the optimization of the energy consumption model and the scheduling model; s3, flexible load resources in the building and the scheduling potential of the flexible load resources are determined, and S4, configuration parameters of the energy storage system are optimized according to the flexible load resources and the scheduling potential of the flexible load resources; according to the industrial and commercial building energy storage optimal configuration method based on the flexible load, the dynamic change of the equipment can be more flexibly adapted, the adaptability of energy management is remarkably improved, the method can effectively identify and coordinate the energy requirements of different equipment in the building, and the energy management efficiency is improved. The problem of energy consumption control caused by lack of flexibility of a scheduling strategy under the conditions of multiple types of equipment and inconsistent operation modes in a building in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management and optimization, and in particular to an industrial and commercial building energy storage optimization configuration method based on flexible loads. Background Art

[0002] In existing industrial and commercial building energy management systems, with the diversification of equipment types and operation modes, the optimization management of energy consumption has become increasingly complex. At present, many energy management methods in buildings still rely on traditional fixed scheduling strategies. Although these strategies are suitable for simple equipment operation scenarios, they are obviously insufficient in flexibility and adaptability when there are many types of equipment and inconsistent operation modes.

[0003] In the above context, energy consumption control has gradually become a critical and difficult problem to solve. The energy demand of different equipment in the building is significantly dynamic and time-varying. For example, the energy demand of the air-conditioning system fluctuates with the change of the external ambient temperature, while the energy consumption of the lighting equipment is closely related to the time and area of ​​the activities of people in the building. In addition, the coupling relationship between different equipment also increases the difficulty of energy consumption optimization. Traditional fixed scheduling strategies are usually unable to effectively identify and coordinate these complex energy demand characteristics, resulting in unbalanced energy distribution and low overall system efficiency. This scheduling strategy that lacks flexibility and adaptability is not only difficult to meet actual needs, but also easily causes a series of problems. On the one hand, key equipment may face the risk of restricted operation when energy allocation is not appropriate, which in turn affects the normal operation of the building. On the other hand, non-critical equipment may cause unnecessary energy waste and increase the energy cost of the building when energy management is not appropriate. In addition, when energy prices fluctuate greatly, traditional methods are difficult to reduce electricity costs by flexibly adjusting the operating sequence of equipment, which further reduces the energy management efficiency of the building. Summary of the invention

[0004] The purpose of the present invention is to provide an industrial and commercial building energy storage optimization configuration method based on flexible loads, so as to solve the energy consumption control problem caused by the lack of flexibility of the scheduling strategy when there are many types of equipment in the building and the operation modes are inconsistent.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for optimizing energy storage configuration of industrial and commercial buildings based on flexible loads, the method comprising:

[0006] S1. Collect real-time operation data and energy consumption data of various equipment in the building;

[0007] S2. Based on the collected data, establish the energy consumption model and scheduling model of the equipment in the building, including classifying the collected data by equipment, extracting the characteristic variables of each equipment, fitting the energy consumption data of the equipment, and obtaining the model parameters. The specific formula is: y = a1x1 + a2x2 + ... + a n x n +b;

[0008] Among them, x1, x2, ... x n represents the characteristic variable of the equipment in the building, y represents the actual energy consumption of the equipment under specific conditions, a1, a2, ..., a n represents the influence weight of each characteristic variable on the energy consumption of the equipment, b represents the basic energy consumption of the equipment when the values ​​of all characteristic variables are zero, and n represents the total number of characteristic variables of the equipment operation status;

[0009] S3. Determine the flexible load resources in the building and their scheduling potential;

[0010] S4. Optimize the configuration parameters of the energy storage system based on flexible load resources and their scheduling potential.

[0011] Preferably, S1 includes collecting real-time operating data of equipment in the building, processing the data, and eliminating fluctuations and noise. The specific formula is: g t =αz t +(1-α)g t-1 ;

[0012] Among them, g t represents the data after smoothing at the current time step, t represents time, α represents the smoothing coefficient, and z t represents the real-time device data samples collected from the building at the current time step, g t-1 Represents the smoothed result data of the previous time step.

[0013] Preferably, S3 includes:

[0014] For the flexible loads in the building, we define the evaluation indicators of the regulation potential, assign weights to each indicator, calculate the comprehensive score of the flexible loads, and select the loads with the highest scheduling potential. The specific formula is:

[0015] S=w1F1+w2F2+…+w m F m ;

[0016] Among them, S represents the total dispatching potential score of flexible load, F1, F2, ..., F m Represents the scores of different evaluation indicators of flexible load, w1, w2, ..., w m It represents the weight coefficient corresponding to each evaluation indicator, and m represents the total number of evaluation indicators.

[0017] Preferably, S4 includes:

[0018] Taking the charge and discharge state of the energy storage system as a variable and the flexible load dispatch result as input, the objective function is set and recursive calculation is performed in time steps. The specific formula is:

[0019] C t =E t +γC t+1

[0020] Among them, C t represents the total operating cost of the building energy storage system at the current moment, E t represents the direct operating cost of the energy storage system and flexible load at the current moment, γ represents the discount factor, C t+1 represents the total cost of the next time step, and t represents the time.

[0021] Preferably, the real-time operating data of various types of equipment in the building collected in S1 includes the operating time, voltage, current, power and environmental parameters of the equipment.

[0022] Preferably, the value range of the smoothing coefficient α in S1 is 0.1 to 0.9.

[0023] Preferably, the calculation formula of the smoothing coefficient α in S1 is:

[0024] α=A / (A+B);

[0025] Among them, α represents the smoothing coefficient, A represents the fluctuation range, and B represents the weight of historical data.

[0026] Preferably, the real-time device data sample z in S1 t The collection period is set to 1 second to 1 minute depending on the equipment type and building operating conditions.

[0027] Preferably, the direct operating cost E in S4 is t Includes at least one of the following: the charging cost of the energy storage system, the discharging benefit of the energy storage system, and the execution cost of flexible load scheduling.

[0028] Preferably, the discount factor γ in S4 ranges from 0.8 to 1.

[0029] It can be seen from the above technical solution that the present invention has the following beneficial effects:

[0030] The flexible load-based industrial and commercial building energy storage optimization configuration method collects real-time operation data and energy consumption data of various equipment in the building, establishes an energy consumption model and a scheduling model for the equipment in the building based on the collected data, determines the flexible load resources in the building and their scheduling potential, optimizes the configuration parameters of the energy storage system according to the flexible load resources and their scheduling potential, can more flexibly adapt to the dynamic changes of the equipment, and significantly improves the adaptability of energy management. The method can effectively identify and coordinate the energy demand between different equipment in the building, reduce the risk of key equipment being restricted due to improper energy allocation, and reduce the energy waste of non-key equipment, further improve energy utilization efficiency, more efficiently respond to energy price fluctuations, and reduce overall electricity costs. It can analyze the energy consumption characteristics of equipment in the building in real time, provide high-quality data support for scheduling optimization and energy storage configuration, alleviate the impact of energy supply and demand fluctuations on building operation, effectively respond to energy management challenges of different scales and different needs, and provide a comprehensive solution for energy saving and consumption reduction and cost optimization of buildings. It solves the energy consumption control problem caused by the lack of flexibility of scheduling strategies in the existing technology when there are many types of equipment in the building and inconsistent operation modes. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0033] like Figure 1 As shown, the present invention provides a technical solution: a method for optimizing energy storage configuration of industrial and commercial buildings based on flexible loads, the method comprising:

[0034] S1. Collect real-time operation data and energy consumption data of various equipment in the building;

[0035] S2. Based on the collected data, establish the energy consumption model and scheduling model of the equipment in the building, including classifying the collected data by equipment, extracting the characteristic variables of each equipment, fitting the energy consumption data of the equipment, and obtaining the model parameters. The specific formula is: y = a1x1 + a2x2 + ... + a n x n +b;

[0036] Among them, x1, x2, ... x nrepresents the characteristic variable of the equipment in the building, y represents the actual energy consumption of the equipment under specific conditions, a1, a2, ..., a n represents the influence weight of each characteristic variable on the energy consumption of the equipment, b represents the basic energy consumption of the equipment when the values ​​of all characteristic variables are zero, and n represents the total number of characteristic variables of the equipment operation status;

[0037] S3. Determine the flexible load resources in the building and their scheduling potential;

[0038] S4. Optimize the configuration parameters of the energy storage system based on flexible load resources and their scheduling potential.

[0039] This method collects real-time operation data and energy consumption data of equipment in the building, and uses data modeling to analyze the energy consumption characteristics of the equipment under operation status. The fitting formula of characteristic variables is used in the model to describe the relationship between the change of equipment energy consumption and characteristic variables in a parameterized way, thereby reflecting the energy consumption law of the equipment. In the analysis of flexible load resources, combined with the dispatching potential assessment, the configuration of the energy storage system is optimized, and the overall energy consumption of the building is reduced while improving energy utilization efficiency to achieve economic and sustainable goals. By establishing energy consumption models and dispatching models for various types of equipment in the building, accurate analysis of energy consumption characteristics is achieved, the operating status of the equipment is optimized, thereby reducing overall energy consumption, optimizing the utilization of flexible load resources and the configuration of the energy storage system, significantly reducing energy costs, and reducing unnecessary energy waste by efficiently utilizing flexible load resources, indirectly reducing carbon emissions, and achieving sustainable development. The method is suitable for industrial and commercial buildings of different sizes, and the model parameters can be flexibly adjusted according to the actual application scenarios, with good adaptability.

[0040] S1 includes collecting real-time operating data of equipment in the building, processing the data, and eliminating fluctuations and noise. The specific formula is: g t =αz t +(1-α)g t-1 ;

[0041] Among them, g t represents the data after smoothing at the current time step, t represents time, α represents the smoothing coefficient, and z t represents the real-time device data samples collected from the building at the current time step, g t-1 Represents the smoothed result data of the previous time step.

[0042] This method collects the operating data of equipment in the building in real time, and processes the data using the exponential weighted moving average method to eliminate short-term fluctuations and random noise that may exist in the data, ensuring the stability and reliability of the data. In the formula, the smoothing coefficient α controls the weight distribution of the current data sample and the historical data, so that the sensitivity of the current data is retained during the data processing, while avoiding excessive noise influence. This smoothing process provides higher quality basic data support for subsequent modeling and optimization. Through denoising and smoothing processing, random fluctuations and noise in the data are effectively eliminated, and the stability and reliability of the data are improved. High-quality processed data provides more accurate input for the establishment of energy consumption models, improves the model fitting effect and the accuracy of the scheduling strategy, can quickly respond to data changes, and maintain the smoothness of the results. The algorithm is simple and the calculation amount is small, which is suitable for fast real-time processing in building management systems.

[0043] S3 includes defining evaluation indicators of regulation potential for flexible loads in buildings, assigning weights to each indicator, calculating the comprehensive score of flexible loads, and screening loads with the highest scheduling potential. The specific formula is:

[0044] S=w1F1+w2F2+…+w m F m ;

[0045] Among them, S represents the total dispatching potential score of flexible load, F1, F2, ..., F m Represents the scores of different evaluation indicators of flexible load, w1, w2, ..., w m It represents the weight coefficient corresponding to each evaluation indicator, and m represents the total number of evaluation indicators.

[0046] This method introduces a multi-dimensional evaluation index system to conduct a comprehensive quantitative evaluation of the dispatching potential of flexible loads in buildings. Each evaluation index (such as energy saving rate, response speed, regulation capacity, etc.) reflects the specific characteristics of flexible loads. Weights are assigned to each index according to actual needs, and the comprehensive score is calculated by combining the weighted summation formula. The load with a higher comprehensive score has a greater dispatching potential, and can be prioritized as the focus of energy storage optimization configuration. This method can not only systematically evaluate flexible loads, but also flexibly adjust evaluation indicators and weights according to different scenarios to ensure the accuracy and applicability of the analysis results. The dispatching potential of flexible loads is comprehensively evaluated based on multi-dimensional indicators to ensure the comprehensiveness and scientificity of the evaluation results. By adjusting the evaluation indicators and weights, it can adapt to the actual needs of different buildings and different application scenarios, give priority to dispatching flexible loads with high dispatching potential, and improve energy efficiency and economic benefits. The evaluation model is simple and intuitive, and the weight allocation is flexible. The weight setting can be optimized in combination with actual experience or through data analysis.

[0047] S4 includes taking the charge and discharge state of the energy storage system as a variable, the flexible load dispatch result as input, setting the objective function, and performing recursive calculation in time steps. The specific formula is:

[0048] C t =E t +γC t+1 ;

[0049] Among them, C t represents the total operating cost of the building energy storage system at the current moment, E t represents the direct operating cost of the energy storage system and flexible load at the current moment, γ represents the discount factor, C t+1 represents the total cost of the next time step, and t represents the time.

[0050] This method constructs a recursive model of the operating cost of the energy storage system, combines the charging and discharging behavior of the energy storage system with the flexible load scheduling results, and dynamically calculates the total cost of the energy storage system. t Represents the direct energy cost of energy storage and flexible load at the current time step, and the discount factor γ is used to balance the weight of current cost and future cost. By step-by-step backtracking recursive calculation, the charging and discharging state of each time step can be optimized, thereby achieving the overall minimization of the operating cost of the energy storage system. This method helps to balance short-term costs and long-term benefits and guide the optimal configuration and scheduling of building energy storage systems. Through recursive calculation, the global operating cost of the energy storage system is minimized, the overall energy cost is reduced, and the scheduling scheme is optimized in units of time steps. It can respond to energy demand and flexible load changes in real time, improve system operation efficiency, combine flexible load scheduling results with energy storage optimization, and comprehensively improve the coordination and benefits of the building energy management system. Through the introduction of discount factors, current and future costs are taken into account to achieve sustainable operation of the energy storage system.

[0051] In S1, the real-time operation data of various equipment in the building are collected, including the operation time, voltage, current, power and environmental parameters of the equipment. In this embodiment, the operation data of various equipment are collected in real time through the monitoring device arranged in the building, including the key operation parameters of the equipment such as operation time, voltage, current, power, and environmental parameters (such as temperature, humidity, etc.). These data are synchronously recorded by sensors and data acquisition modules and transmitted to the central control system. The operation time, voltage, current and power data are used to characterize the real-time working state of the equipment, while the environmental parameters can reflect the impact of the external environment on the operation of the equipment, and provide more background information for energy consumption modeling and optimization scheduling. Through the comprehensive analysis of the above data, the operation characteristics of the equipment can be more accurately described and the building energy storage configuration can be optimized. Covering a variety of key parameters of equipment operation and environmental influencing factors, ensuring the integrity and accuracy of data collection, by increasing the collection of environmental parameters, the energy consumption model and scheduling model of the equipment can be established more accurately, the model fitting effect can be improved, and the characteristic changes of the equipment can be analyzed in combination with a variety of operation parameters, providing comprehensive data support for subsequent flexible load scheduling and energy storage system optimization. This method is suitable for the monitoring and optimization needs of different types of equipment, and has strong versatility and adaptability.

[0052] The value range of the smoothing coefficient α in S1 is 0.1 to 0.9. In this embodiment, the smoothing coefficient α is used to control the weight distribution of the real-time data and the historical data in the current time step in the smoothing calculation. Specifically, when the value of α is small, more attention is paid to the trend of the historical data, and the sensitivity to the mutation data is low, which is suitable for data scenarios with large fluctuations; when the value of α is large, more attention is paid to the real-time nature of the current data, and the data changes can be responded to quickly, but it may be more sensitive to short-term fluctuations. By setting the value range of α to 0.1 to 0.9, it is ensured that the smoothing degree can be flexibly adjusted in different devices and application scenarios to optimize the data processing effect. By limiting the value range of α, it is possible to adapt to different data fluctuation characteristics and balance the relationship between data smoothing and real-time performance. When α is appropriately selected, noise and short-term fluctuations can be effectively filtered to improve the stability of the data. When it is necessary to respond quickly to real-time changes, a larger α can be selected to improve the update sensitivity of the data. It is suitable for data smoothing processing of different types of equipment in buildings. For example, a small α can be selected for high volatility equipment, and a large α can be selected for low volatility equipment.

[0053] The calculation formula of the smoothing coefficient α in S1 is: α = A / (A+B);

[0054] Among them, α represents the smoothing coefficient, A represents the fluctuation range, and B represents the weight of historical data.

[0055] The method dynamically adjusts the smoothing coefficient α through the formula α=A / (A+B), so that it can be adaptively determined according to the ratio of the data fluctuation range and the historical data weight. In this formula, the fluctuation range A reflects the fluctuation range of real-time data, and the historical data weight B reflects the degree of dependence of the system on historical data. When the real-time data fluctuates greatly, the AAA value increases, resulting in an increase in the α value, indicating that a higher weight is given to the current data; conversely, when the fluctuation is small, the B value proportion increases and the α value decreases, indicating that more attention is paid to the smoothing effect of historical data. This calculation method has strong adaptability and can dynamically optimize the smoothing effect according to the data characteristics. The dynamic adjustment of the smoothing coefficient α can adapt to the fluctuation of different devices and data characteristics, improve the flexibility of data processing, and balance the influence of the fluctuation range and historical weight. It can not only respond quickly to the changes in real-time data, but also effectively reduce the influence of noise and short-term fluctuations on data processing. The smoothing coefficient is automatically calculated through the formula, avoiding the uncertainty caused by manual adjustment of α, improving the stability and efficiency of system operation, and reasonably setting the value range of A and B can accurately control the variation of α, thereby optimizing the results of data smoothing processing.

[0056] Real-time device data sample z in S1 t The collection period is set to 1 second to 1 minute according to the equipment type and the building operating conditions. This implementation method selects the most suitable sampling frequency according to the operating characteristics of different equipment and the specific conditions of the building by flexibly adjusting the collection period of the real-time equipment data sample ztz_tzt. For equipment with a fast response speed or frequently changing operating status (such as air-conditioning systems, elevators, etc.), a shorter collection period (such as 1 second) is set to obtain higher-resolution data; for equipment with a relatively stable operating status (such as lighting systems, water heaters, etc.), a longer collection period (such as 1 minute) can be used to reduce data redundancy and collection pressure. In addition, by adjusting the collection frequency according to the operating conditions of the building (such as load fluctuation frequency and environmental change rate), the system's collection efficiency and resource utilization can be improved while ensuring data quality. The collection cycle is dynamically set according to the device type and operating conditions, and can meet the requirements of different devices for data collection frequency. By appropriately shortening the collection cycle of high-fluctuation devices, more detailed information can be captured and the data resolution and analysis accuracy can be improved. By extending the collection cycle of low-fluctuation devices, unnecessary data storage and transmission pressure can be reduced and system resource utilization can be improved. A longer collection cycle can reduce the energy consumption of the collection equipment and extend the service life of the equipment, especially in low-fluctuation scenarios.

[0057] Direct operating cost E in S4 t It includes at least one of the following: charging cost of energy storage system, discharging income of energy storage system, and execution cost of flexible load dispatch. In this implementation, direct operating cost E tComprehensively consider multiple cost and benefit factors of energy storage systems and flexible loads, including the following: Charging cost of energy storage system: refers to the cost incurred by charging energy storage equipment from the power grid or other energy sources within a specific time period, which is usually related to the real-time electricity price, charging power and time. Discharge benefit of energy storage system: refers to the economic benefit obtained by energy storage equipment from releasing electric energy to loads or power grids during peak hours, which depends on the real-time electricity price, discharge power and discharge time. Execution cost of flexible load scheduling: refers to the cost incurred to adjust the operating state of flexible loads, such as equipment start-up and shutdown costs, efficiency loss costs or potential impacts on user comfort. By incorporating the above cost and benefit factors into E t The calculation can more accurately evaluate the direct operating cost of each time step, optimize the overall dispatching strategy of the energy storage system and flexible load, and maximize economic benefits. By comprehensively considering the energy storage charging and discharging and flexible load dispatching costs, the direct operating cost of the system can be accurately calculated. By taking into account the discharge benefit factor, the discharge timing of the energy storage system can be effectively optimized to maximize economic benefits during peak electricity price periods. Combined with the flexible load dispatching cost, the economic benefits and the execution cost of flexible load regulation can be balanced to avoid unnecessary energy consumption and resource waste. The method is applicable to a variety of building energy management scenarios and can dynamically optimize cost calculation and dispatching strategies based on real-time electricity prices and load status.

[0058] The value range of the discount factor γ in S4 is 0.8 to 1. The discount factor γ is a key parameter used to balance the weights of current costs and future costs in the recursive calculation of the operating cost of the energy storage system. When the value of γ is close to 1, the system pays more attention to the cost of the future time step; when the value of γ is small, it pays more attention to the cost of the current time step. By setting the value range of γ to 0.8 to 1, the system is more inclined to optimize long-term benefits when calculating the total operating cost, while taking into account a certain degree of real-time performance to achieve the sustainability and economy of energy storage optimization. The setting of the discount factor value range guides the system to give priority to long-term cost optimization and reduce the overall operating cost. By setting γ to 0.8 to 1, a more reasonable balance can be achieved between weighing current costs and future costs. A higher discount factor value can make the system more adaptable to changes in building loads with periodic or long-term fluctuations, and improve the reliability of the optimization scheduling strategy. The value range avoids the problem that too small γ causes the system to pay too much attention to current costs and ignore long-term benefits, and at the same time reduces the decision-making lag that may be caused by excessive weighting of future costs.

[0059] Although 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 the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for optimizing energy storage configuration of industrial and commercial buildings based on flexible loads, characterized in that: The method comprises: S1. Collect real-time operation data and energy consumption data of various equipment in the building; S2. Based on the collected data, establish the energy consumption model and scheduling model of the equipment in the building, including classifying the collected data by equipment, extracting the characteristic variables of each equipment, fitting the energy consumption data of the equipment, and obtaining the model parameters. The specific formula is: y = a1x1 + a2x2 + ... + a n x n +b; Among them, x1, x2, ... x n represents the characteristic variable of the equipment in the building, y represents the actual energy consumption of the equipment under specific conditions, a1, a2, ..., a n represents the influence weight of each characteristic variable on the energy consumption of the equipment, b represents the basic energy consumption of the equipment when the values ​​of all characteristic variables are zero, and n represents the total number of characteristic variables of the equipment operation status; S3. Determine the flexible load resources in the building and their scheduling potential; S4. Optimize the configuration parameters of the energy storage system based on flexible load resources and their scheduling potential.

2. The method for optimizing the configuration of industrial and commercial building energy storage based on flexible loads according to claim 1 is characterized in that: S1 includes collecting real-time operating data of equipment in the building, processing the data, and eliminating fluctuations and noise. The specific formula is: g t =αz t +(1-α)g t-1 ; Among them, g t represents the data after smoothing at the current time step, t represents time, α represents the smoothing coefficient, and z t represents the real-time device data samples collected from the building at the current time step, g t-1 Represents the smoothed result data of the previous time step.

3. The method for optimizing the configuration of industrial and commercial building energy storage based on flexible loads according to claim 1, characterized in that: The S3 includes: For the flexible loads in the building, we define the evaluation indicators of the regulation potential, assign weights to each indicator, calculate the comprehensive score of the flexible loads, and select the loads with the highest scheduling potential. The specific formula is: S=w1F1+w2F2+…+w m F m ; Among them, S represents the total dispatching potential score of flexible load, F1, F2, ..., F m Represents the scores of different evaluation indicators of flexible load, w1, w2, ..., w m It represents the weight coefficient corresponding to each evaluation indicator, and m represents the total number of evaluation indicators.

4. The method for optimizing the configuration of industrial and commercial building energy storage based on flexible loads according to claim 1 is characterized in that: The S4 includes: Taking the charge and discharge state of the energy storage system as a variable and the flexible load dispatch result as input, the objective function is set and recursive calculation is performed in time steps. The specific formula is: C t =E t +γC t+1 ; Among them, C t represents the total operating cost of the building energy storage system at the current moment, E t represents the direct operating cost of the energy storage system and flexible load at the current moment, γ represents the discount factor, C t+1 represents the total cost of the next time step, and t represents the time.

5. The method for optimizing the configuration of industrial and commercial building energy storage based on flexible loads according to claim 1, characterized in that: The real-time operation data of various equipment in the building are collected in S1, including the operation time, voltage, current, power and environmental parameters of the equipment.

6. The method for optimizing the configuration of energy storage for industrial and commercial buildings based on flexible loads according to claim 2 is characterized in that: The value range of the smoothing coefficient α in S1 is 0.1 to 0.

9.

7. The method for optimizing the configuration of industrial and commercial building energy storage based on flexible loads according to claim 2 is characterized in that: The calculation formula of the smoothing coefficient α in S1 is: α=A / (A+B); Among them, α represents the smoothing coefficient, A represents the fluctuation range, and B represents the weight of historical data.

8. The method for optimizing the configuration of industrial and commercial building energy storage based on flexible loads according to claim 2 is characterized in that: The real-time device data sample z in S1 t The collection period is set to 1 second to 1 minute according to the equipment type and building operating conditions.

9. The method for optimizing the configuration of industrial and commercial building energy storage based on flexible loads according to claim 4 is characterized by: The direct operating cost of S4 is E t Includes at least one of the following: the charging cost of the energy storage system, the discharging benefit of the energy storage system, and the execution cost of flexible load scheduling.

10. The method for optimizing the configuration of industrial and commercial building energy storage based on flexible loads according to claim 4, characterized in that: The value range of the discount factor γ in S4 is 0.8 to 1.

Images