Commercial building air conditioner load regulation and control method and device based on user response behaviors

Abstract

The invention relates to the field of load regulation and control, and particularly provides a commercial building air conditioner load regulation and control method and device based on user response behaviors. The method comprises the following steps: constructing a contract response cost function based on contract response cost data, and constructing a difference response cost function based on difference response cost data; performing weighted summation on the contract response cost function and the difference response cost function according to a preset weight coefficient to obtain a comprehensive response cost function; constructing an dissatisfaction degree cost function based on the deviation between the accumulated comprehensive response electric quantity and the ideal response electric quantity of each user in each sub-predetermined time period in the building; solving a target function by taking a preset range of the contract compensation cost data and the power purchase cost data as a constraint condition; and carrying out load regulation and control on the building based on the solution of the objective function. According to the technical scheme provided by the invention, the balance between the user satisfaction and the power grid regulation target is realized to a certain extent.

Description

Technical Field

[0001] This invention relates to the field of load regulation, and in particular to a method and apparatus for regulating the air conditioning load of commercial buildings based on user response behavior. Background Technology

[0002] Among the diverse types of urban load resources, the power consumption of commercial building air conditioning systems accounts for a relatively high proportion of total urban power consumption. Especially during the high-temperature summer months, the load share of air conditioning systems increases significantly, reaching over 30% of the grid's peak load. With the continuous development of smart grids and demand-side management technologies, air conditioning loads, due to their thermal inertia and adjustability, are considered a highly promising demand response resource.

[0003] In related technologies, demand response research for air conditioning loads in commercial buildings mainly focuses on centralized control of air conditioning systems or automated regulation based on preset strategies. Examples include uniformly raising the air conditioning set temperature during peak electricity consumption periods, periodically starting and stopping compressors or fans, or utilizing the thermal inertia of the building envelope and indoor objects for pre-cooling.

[0004] However, in practical applications, the individual preferences of users within commercial buildings regarding electricity consumption patterns and costs can introduce uncertainty into their electricity consumption responses, thus affecting the accuracy of aggregators' electricity consumption reporting. Existing rigid control strategies often overlook this variability, easily leading to decreased user satisfaction. Summary of the Invention

[0005] The present invention provides a method, apparatus, electronic device, storage medium, and computer program product for regulating the air conditioning load of commercial buildings based on user response behavior, so as to achieve a balance between user satisfaction and power grid regulation objectives to a certain extent.

[0006] In a first aspect, the present invention provides a method for regulating the air conditioning load of commercial buildings based on user response behavior, the method comprising:

[0007] A contract response cost function is constructed based on the contract response cost data for air conditioning load in each sub-predetermined period within the predetermined period; wherein, the contract response cost data is the product of the electricity purchase cost data and the electricity usage in the sub-predetermined period minus the product of the contract compensation cost data and the responsive power output.

[0008] A differential response cost function is constructed based on the differential response cost data for air conditioning load in each sub-predetermined period within the predetermined period; wherein, the differential response cost data is the product of the electricity consumption of the sub-predetermined period minus the differential response electricity consumption and the electricity purchase cost data of the sub-predetermined period.

[0009] The contract response cost function and the differential response cost function of each user in the commercial building are weighted and summed according to preset weighting coefficients to obtain the comprehensive response cost function.

[0010] The result of a high-order Taylor expansion of the deviation between the cumulative comprehensive response electricity and the ideal response electricity of each user in the commercial building during each sub-pre-scheduled period is multiplied by the user dissatisfaction coefficient to obtain the dissatisfaction cost function.

[0011] Using the preset range of the contract compensation cost data and the preset range of the electricity purchase cost data as constraints, an objective function is solved; and the air conditioning load corresponding to the optimal solution of the objective function is used to regulate the load of the commercial building; wherein, the objective function is the minimum sum of the comprehensive response cost function and the dissatisfaction cost function.

[0012] In one embodiment of the present invention, a contract response cost function is constructed based on the contract response cost data for air conditioning load in each sub-predetermined time period within a predetermined time period, including:

[0013] The electricity price adjustment ratio for different sub-pre-scheduled time periods is multiplied by the benchmark electricity price data to obtain the electricity purchase cost data for different sub-pre-scheduled time periods; wherein, the electricity price adjustment ratio includes the peak price adjustment ratio and the off-peak price adjustment ratio; the peak price adjustment ratio is greater than 1, and the off-peak price adjustment ratio is less than 1;

[0014] The contract response cost data for the sub-predetermined period is obtained by multiplying the electricity purchase cost data and electricity usage data for the sub-predetermined period by the product of the contract compensation cost data and the responsive power output data for the sub-predetermined period; wherein the responsive power output data and the contract compensation cost data have a linear relationship.

[0015] The contract response cost data of each sub-predetermined time period within the predetermined time period are accumulated to construct the contract response cost function.

[0016] In one embodiment of the present invention, a differential response cost function is constructed based on the differential response cost data for air conditioning load in each sub-predetermined time period within a predetermined time period, including:

[0017] The electricity price adjustment ratio for different sub-pre-scheduled time periods is multiplied by the benchmark electricity price data to obtain the electricity purchase cost data for different sub-pre-scheduled time periods; wherein, the electricity price adjustment ratio includes the peak price adjustment ratio and the off-peak price adjustment ratio; the peak price adjustment ratio is greater than 1, and the off-peak price adjustment ratio is less than 1;

[0018] The differential response electricity ratio is obtained by multiplying the electricity consumption, the price change sensitivity coefficient, and the differential response electricity ratio in sequence; wherein, the differential response electricity ratio is the ratio of the difference between the electricity purchase cost data and the benchmark electricity price data for the sub-predetermined period to the benchmark electricity price data.

[0019] The difference in response cost data is obtained by multiplying the electricity purchase cost data for the sub-predetermined period by the difference between the electricity consumption for the sub-predetermined period and the difference in response electricity consumption.

[0020] The differential response cost data of each sub-predetermined time period within the predetermined time period are accumulated to construct a differential response cost function.

[0021] In one embodiment of the present invention, the deviation between the cumulative comprehensive response electricity and the ideal response electricity of each user in a commercial building during each sub-predetermined time period is subjected to a higher-order Taylor expansion, and multiplied by the user dissatisfaction coefficient to obtain a dissatisfaction cost function, including:

[0022] Based on the base penalty coefficient Factors influencing user willingness Determine the user dissatisfaction coefficient ;in, For shape parameters, and ;

[0023] According to the preset weighting coefficient, the responsive power output and the differential responsive power within the sub-predetermined time period are weighted and summed to obtain the comprehensive responsive power.

[0024] The total response electricity of each user in the commercial building during each sub-pre-determined period within the predetermined period is added together to obtain the cumulative total response electricity.

[0025] The difference between the cumulative comprehensive response power and the ideal response power is expanded using a higher-order Taylor series, and then multiplied by the user dissatisfaction coefficient to obtain the dissatisfaction cost function.

[0026] In one embodiment of the present invention, based on the base penalty coefficient Factors influencing user willingness Determine the user dissatisfaction coefficient Prior to the step, the method includes:

[0027] Influence coefficient based on user's education level Impact coefficient of household income And the influence coefficient of the average age of users' households Determine the comprehensive subjective influence coefficient ;in, ;

[0028] When the electricity purchase cost data is less than the benchmark electricity price data, based on the objective impact coefficient Duration of air conditioner start / stop status and minimum start / stop time of air conditioner Calculate the degree of objective willingness ;in, The user willingness factor is expressed as follows: ;in, Data on the cost of purchasing electricity. For benchmark electricity price data, For the highest electricity purchase cost data, N() is the normal distribution function;

[0029] When the electricity purchase cost data is greater than the benchmark electricity price data, based on the objective impact coefficient Duration of air conditioner start / stop status and minimum start / stop time of air conditioner Calculate the degree of objective willingness ;in, The user willingness factor is expressed as follows: .

[0030] In one embodiment of the present invention, the electricity purchase cost data includes peak-hour electricity cost data and off-peak-hour electricity cost data. Using a preset range for the contract compensation fee and a preset range for the electricity purchase cost data as constraints, the objective function is solved, including:

[0031] Set the contract compensation fee data, peak electricity cost data, and off-peak electricity cost data as branch variables;

[0032] According to a preset step size, each branch variable is divided into multiple discrete values ​​according to a preset numerical range, and a multi-level decision tree is constructed; where each level represents a branch variable of one dimension.

[0033] In the decision tree, a baseline decision chain is determined; wherein the baseline decision chain includes the initial contract compensation fee, the initial peak electricity cost, and the initial off-peak electricity cost;

[0034] Using the baseline decision chain as a benchmark, the target optimal solution is searched in the decision tree; wherein, the target optimal solution is the value of the contract compensation fee data, the peak electricity cost data, and the off-peak electricity cost data when the objective function value is minimized.

[0035] In one embodiment of the present invention, searching for the optimal solution of the objective in the decision tree, using the baseline decision chain as a reference, includes:

[0036] If the objective function value corresponding to the current decision chain is less than the objective function value corresponding to the benchmark decision chain, the current decision chain is updated to the benchmark decision chain, and the benchmark decision chain before the update is pruned.

[0037] If the objective function value of the current decision chain is greater than the objective function value of the benchmark decision chain, then pruning is performed on the current decision chain.

[0038] In one embodiment of the present invention, after the step of searching for the target optimal solution in the decision tree based on the benchmark decision chain, the method further includes:

[0039] Based on the target optimal solution, determine the sub-air conditioner power of each user in each sub-pre-scheduled time period;

[0040] When the power of each sub-air conditioner is greater than or equal to the preset minimum air conditioner power, and the power of each sub-air conditioner is less than or equal to the preset maximum air conditioner power, the commercial building is subjected to segmented load control based on the cumulative air conditioner power of each user within each sub-predetermined time period.

[0041] Thirdly, the present invention provides a control device for the air conditioning load of commercial buildings based on user response behavior, the control device for the air conditioning load of commercial buildings based on user response behavior includes:

[0042] The contract cost construction module is used to construct a contract response cost function based on the contract response cost data for air conditioning load in each sub-predetermined period within a predetermined period; wherein, the contract response cost data is the product of the electricity purchase cost data and the electricity usage in the sub-predetermined period minus the product of the contract compensation cost data and the responsive power output.

[0043] The response cost construction module is used to construct a differential response cost function based on the differential response cost data for air conditioning load in each sub-predetermined period within a predetermined period; wherein, the differential response cost data is the product of the electricity consumption of the sub-predetermined period minus the differential response electricity consumption and the electricity purchase cost data of the sub-predetermined period.

[0044] The comprehensive cost construction module is used to perform a weighted summation of the contract response cost function and the differential response cost function of each user in the commercial building according to a preset weighting coefficient to obtain the comprehensive response cost function.

[0045] The Dissatisfaction Cost Construction Module is used to multiply the result of the high-order Taylor expansion of the deviation between the cumulative comprehensive response electricity and the ideal response electricity of each user in the commercial building in each sub-pre-scheduled period by the user dissatisfaction coefficient to obtain the dissatisfaction cost function.

[0046] The objective function solving module is used to solve the objective function with the preset range of the contract compensation fee and the preset range of the electricity purchase cost data as constraints; and to regulate the load of the commercial building based on the air conditioning load corresponding to the optimal solution of the objective function; wherein, the objective function is the minimum sum of the comprehensive response cost function and the dissatisfaction cost function.

[0047] Thirdly, the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method for regulating the air conditioning load of commercial buildings based on user response behavior.

[0048] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for regulating the air conditioning load of a commercial building based on user response behavior as described in any of the preceding claims.

[0049] Fifthly, the present invention provides a computer program product, including a computer program, which, when executed by a processor, causes the computer to perform the above-described method for regulating the air conditioning load of a commercial building based on user response behavior.

[0050] This invention provides a method for regulating the air conditioning load of commercial buildings based on user response behavior. It constructs a comprehensive response cost function, including a contract response cost function and a differential response cost function. A dissatisfaction cost function is generated based on the deviation between the cumulative comprehensive response power and the ideal response power. The objective function is to minimize the sum of the comprehensive response cost function and the dissatisfaction cost function, with preset ranges for contract compensation costs and electricity purchase cost data as constraints. This objective function is then solved. Finally, the air conditioning load of commercial buildings is regulated based on the optimal solution of the objective function, thereby achieving a balance between user satisfaction and grid regulation objectives to a certain extent. Attached Figure Description

[0051] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention, and those skilled in the art can obtain other embodiments based on these drawings without creative effort.

[0052] Figure 1 This is a flowchart illustrating a method for regulating the air conditioning load of commercial buildings based on user response behavior, as provided in an embodiment of the present invention.

[0053] Figure 2This is a schematic diagram of a commercial building air conditioning load control device based on user response behavior, provided in an embodiment of the present invention.

[0054] Figure 3 This is a schematic diagram of an electronic device provided according to an embodiment of the present invention. Detailed Implementation

[0055] Embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. While some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0056] Cities are major energy consumers, accounting for approximately 80% of global carbon emissions. The power grid plays a significant role in urban energy consumption, and its economical and efficient operation is crucial for achieving the goals of "carbon peaking and carbon neutrality." Among the diverse types of urban load resources, the electricity consumption of commercial building air conditioning systems accounts for a relatively high proportion of total urban electricity consumption. Especially during the high-temperature summer months, the load share of air conditioning systems increases significantly, reaching over 30% of the grid's peak load. With the continuous development of smart grids and demand-side management technologies, air conditioning loads, due to their thermal inertia and adjustability, are considered a highly promising demand response resource. By scientifically regulating the air conditioning systems of commercial buildings and participating in grid demand response projects, it is possible to effectively reduce peak grid loads, smooth load fluctuations, and improve the economic efficiency and reliability of grid operation, while also bringing considerable economic benefits to building users. Therefore, achieving accurate modeling of the demand response behavior of commercial building air conditioning loads, promoting their interaction with the grid, and supporting the optimization of power system operation are of significant practical importance.

[0057] In related technologies, demand response research for air conditioning loads in commercial buildings mainly focuses on centralized control of air conditioning systems or automated regulation based on preset strategies. Examples include uniformly raising the air conditioning set temperature during peak electricity consumption periods, periodically starting and stopping compressors or fans, or utilizing the thermal inertia of the building envelope and indoor objects for pre-cooling. These methods typically take a grid or load aggregator perspective, aiming to maximize overall energy efficiency or economic benefits, and implement rigid control strategies, either uniformly or regionally.

[0058] However, in practical applications, the individual preferences of users within commercial buildings regarding electricity consumption patterns and costs create uncertainty in their electricity consumption response, thus affecting the accuracy of aggregators' electricity consumption reporting. Existing rigid control strategies often overlook this variability, easily leading to decreased user satisfaction and consequently impacting long-term participation and actual effectiveness of demand response projects.

[0059] As the primary energy consumers, users' subjective feelings and behavioral feedback are crucial to the sustainable implementation of demand response measures. Furthermore, some optimization methods that initially consider user comfort often simplify "comfort" to a uniform threshold constraint based on physical parameters (such as temperature range) or obtain static preferences through simple questionnaires. These methods fail to deeply explore and quantify users' personalized and dynamically changing comfort preferences, and lack a mechanism for refined collaborative optimization between user preferences and grid demand and building system characteristics. Commercial building air conditioning load systems are characterized by high inertia, strong time delays, and complex thermal coupling relationships between different areas. The key to optimizing demand response for commercial building air conditioning loads lies in achieving the optimal balance between user satisfaction and grid regulation objectives—both within a unified optimization framework that fully respects and proactively adapts to diverse user preferences while efficiently responding to grid demand-side management commands.

[0060] Based on this, the present invention provides a method for regulating the air conditioning load of commercial buildings based on user response behavior. It constructs a comprehensive response cost function including a contract response cost function and a differential response cost function, and generates a dissatisfaction cost function based on the deviation between the cumulative comprehensive response power and the ideal response power. Then, it uses the minimum sum of the comprehensive response cost function and the dissatisfaction cost function as the objective function, and uses preset ranges for contract compensation fees and electricity purchase cost data as constraints to solve the objective function. Finally, it regulates the air conditioning load of commercial buildings based on the optimal solution of the objective function, thereby achieving a balance between user satisfaction and grid regulation objectives to a certain extent.

[0061] Please see Figure 1 The present invention provides a method for regulating the air conditioning load of commercial buildings based on user response behavior. This method may include the following steps.

[0062] Step S110: Construct a contract response cost function based on the contract response cost data for air conditioning load in each sub-predetermined time period within the predetermined time period; wherein, the contract response cost data is the product of the electricity purchase cost data and the electricity usage in the sub-predetermined time period minus the product of the contract compensation cost data and the responsive power output.

[0063] In this embodiment, a predetermined time period refers to a complete control cycle (e.g., 1 day, 12 hours). A sub-predetermined time period refers to a subdivided unit into which the predetermined time period is divided (e.g., 15 minutes, 30 minutes, 1 hour, etc.). Within the same sub-predetermined time period, the electricity price level and the user's electricity consumption status are considered to remain unchanged.

[0064] In this embodiment, the contract response cost data refers to the net cost incurred by a commercial building participating in contract response within a sub-predetermined time period after signing a demand response contract with an electricity service provider. The calculation logic is "total electricity purchase cost - total contract compensation revenue", i.e., (electricity purchase cost data × electricity usage - contract compensation cost data × responsive electricity output). Both the electricity purchase cost data and the contract compensation cost data are for a single unit of electricity (e.g., 1 kWh).

[0065] Step S120: Construct a differential response cost function based on the differential response cost data for air conditioning load in each sub-predetermined time period within the predetermined time period; wherein, the differential response cost data is the product of the electricity consumption of the sub-predetermined time period minus the differential response electricity consumption and the electricity purchase cost data of the sub-predetermined time period.

[0066] In this embodiment, the cost arising from the deviation between the actual electricity usage and the differential response electricity usage, i.e. (electricity usage - differential response electricity usage) × electricity purchase cost data, is used to quantify the load fluctuation cost of the non-contract response portion.

[0067] Step S130: The contract response cost function and the differential response cost function of each user in the commercial building are weighted and summed according to preset weighting coefficients to obtain the comprehensive response cost function.

[0068] In this embodiment, the preset weighting coefficient is a coefficient set according to the operational needs of commercial buildings (such as prioritizing economic efficiency or user experience), used to balance the cost weights of contract response and difference response. The value range is usually 0-1, and the sum of the two weights is 1.

[0069] Specifically, assume the contract response cost function is... The differential response cost function is Then the comprehensive response cost function It can be represented as: .in, and These are the weighting coefficients for the two user participation methods, and ; This represents the number of users within the commercial building who participated in the response.

[0070] Step S140: Multiply the result of a high-order Taylor expansion of the deviation between the cumulative comprehensive response electricity and the ideal response electricity of each user in the commercial building in each sub-pre-scheduled time period, and the user dissatisfaction coefficient, to obtain the dissatisfaction cost function.

[0071] In this embodiment, the cumulative comprehensive response power is the sum of the comprehensive response power (contract response + differential response weighted sum) of each user across all sub-predetermined time periods. The ideal response power is the optimal target value set based on electricity market demand and building energy consumption benchmarks. It represents the expected response power output / consumption of the commercial building's air conditioning load under normal power supply and distribution conditions, as determined by the power grid dispatch system. Specifically, for example, in cases of excessive green energy storage, it is desired that the commercial building increase its air conditioning load to consume the corresponding power. Conversely, in cases of power scarcity, it is desired that the commercial building reduce its air conditioning load to provide the corresponding power.

[0072] In this embodiment, the higher-order Taylor expansion is a mathematical method that transforms the power deviation function into a polynomial form (usually of order 2 or higher). Compared with linear approximation, it more accurately quantifies the impact of deviation on cost and avoids optimization errors caused by lower-order approximation.

[0073] In one specific embodiment, the power consumption of the two response methods is weighted and summed according to the preset weighting coefficients in the above embodiments to obtain the cumulative comprehensive response power consumption. :

[0074]

[0075] in, This refers to the responsive power output of a specific user within a pre-set time period. The difference in response power consumption for a user within a certain sub-preset time period.

[0076] Then, the deviation from the ideal response power can be performed using a 6th-order Taylor expansion and multiplied by a user dissatisfaction coefficient. That is, the unsatisfactory cost function can be obtained. :

[0077] .

[0078] Step S150: Solve the objective function using the preset range of the contract compensation cost data and the preset range of the electricity purchase cost data as constraints; and perform load regulation on the commercial building based on the air conditioning load corresponding to the optimal solution of the objective function; wherein, the objective function is the minimum sum of the comprehensive response cost function and the dissatisfaction cost function.

[0079] In this embodiment, the preset ranges for contract compensation fee data and electricity purchase price data can be preset. The preset range for contract compensation fee data is between the maximum compensation fee and the minimum compensation fee, i.e. .For example, , When contract compensation fees change, responsive power output also changes. Generally, the relationship between contract compensation fees and responsive power output can be considered linear. As contract compensation fees increase, the user provides more responsive power output. Understandably, responsive power output can be higher or lower than the ideal responsive power output.

[0080] In this embodiment, the electricity purchase cost data is based on a benchmark electricity purchase cost data with fluctuations. For example, during off-peak electricity usage periods, the electricity purchase cost data is less than or equal to the benchmark electricity purchase cost data. Its fluctuation range is 0.8 ≤ If the value is ≤1, then during off-peak hours, the electricity purchase cost data will range from 0.8 to 1 times the benchmark electricity purchase cost data. During peak electricity consumption periods, the electricity purchase cost data will be greater than or equal to the benchmark electricity purchase cost data. Its fluctuation range is ≤1. If the value is ≤1.2, then during peak periods, the range of electricity purchase cost data is between 1 and 1.2 times the baseline electricity purchase data.

[0081] Then, by employing a predetermined optimization method, using contract compensation cost data, off-peak electricity purchase cost data, and peak electricity purchase cost data as variables, the responsive power output and differential response power of each user in each sub-preset time period are analyzed. Therefore, the objective function can be solved by minimizing the sum of the comprehensive response cost function and the dissatisfaction cost function. Finally, load regulation of commercial buildings is implemented based on the air conditioning load corresponding to the optimal solution of the objective function.

[0082] It should be noted that the predetermined optimization method can be a particle swarm optimization algorithm, a genetic algorithm, a branch and bound algorithm, etc. This invention does not limit the specific optimization algorithm.

[0083] The above embodiments break through the limitations of traditional single-cost control, achieve a balance between the dual objectives of economic efficiency (contract / difference cost) and user experience (difference cost), and improve the accuracy of power deviation quantification through high-order Taylor expansion, ensuring that the optimization results are more in line with actual needs and constraints, guaranteeing the compliance and feasibility of the control scheme, and avoiding violations of market rules or building operation boundaries.

[0084] In some embodiments, in step S110, constructing a contract response cost function based on the contract response cost data for air conditioning load in each sub-predetermined time period within a predetermined time period may include the following steps.

[0085] Step S111: Multiply the electricity price adjustment ratio for different sub-pre-determined time periods by the benchmark electricity price data to obtain the electricity purchase cost data for different sub-pre-determined time periods; wherein, the electricity price adjustment ratio includes the peak price adjustment ratio and the off-peak price adjustment ratio; the peak price adjustment ratio is greater than 1, and the off-peak price adjustment ratio is less than 1.

[0086] In this embodiment, the benchmark electricity price data refers to the basic electricity price set by the electricity market (such as the flat-period price), which serves as the benchmark value for peak-valley electricity price adjustments. It is usually a fixed value or a long-term stable value. The peak / valley price adjustment ratio refers to the electricity price adjustment coefficient adapted to fluctuations in electricity supply and demand. The coefficient is >1 during peak hours (e.g., 9:00-17:00) (electricity price increases), and <1 during valley hours (e.g., 0:00-6:00) (electricity price decreases), which aligns with the actual time-of-use pricing mechanism.

[0087] Specifically, for example, and These are the price adjustment ratios for off-peak and peak periods, respectively. , So, what are the data on electricity purchase costs? It can be represented as .in, For benchmark electricity price data, This is a binary state indicator variable used to represent the electricity price policy orientation during time period t. When, it indicates that it is during the system's off-peak electricity price period, when "At this time" indicates that the system is in its peak electricity price period.

[0088] Step S112: Subtract the product of the electricity purchase cost data and the electricity usage data for the sub-predetermined period from the product of the contract compensation cost data and the responsive power output data for the sub-predetermined period to obtain the contract response cost data for the sub-predetermined period; wherein the responsive power output data and the contract compensation cost data are linearly related.

[0089] In this embodiment, the responsive power output is the reduction in air conditioning power consumption (i.e., load shedding) by the commercial building to fulfill the contract, and it is linearly related to the contract compensation fee. The higher the contract compensation fee, the higher the responsive power output that users in the commercial building can provide. Specifically, the responsive power output of the i-th user in time period t is defined. With contract compensation fees The functional relationship is as follows: K is the contract response sensitivity coefficient. , Let the rated maximum operating power of the air conditioning system for the i-th user be , The maximum reduction percentage is set to 0.6, meaning users can only reduce their air conditioning load by a maximum of 60%. The user's expected contract compensation price is set at the highest peak electricity price in the area where the building is located. 80%.

[0090] Step S113: Accumulate the contract response cost data of each sub-predetermined time period within the predetermined time period to construct the contract response cost function.

[0091] In this embodiment, the electricity purchase cost for each sub-period is first calculated based on the peak-valley adjustment ratio. Then, the contract response cost for a single period is calculated as "total purchase cost - total compensation revenue". Finally, the contract response cost data for each sub-predetermined period are accumulated to obtain the contract response cost function for a single user within the predetermined period. Contract Response Cost Function It can be represented as:

[0092]

[0093] Where T is the number of sub-pre ...

[0094] In the above embodiments, by incorporating the time-of-use pricing mechanism into the cost calculation, the contract response cost function is made more in line with the actual electricity market, thereby improving the accuracy of cost calculation.

[0095] In some embodiments, in step S120, constructing a differential response cost function based on the differential response cost data for air conditioning load in each sub-predetermined time period within a predetermined time period may include the following steps.

[0096] Step S121: Multiply the electricity price adjustment ratio for different sub-pre-determined time periods by the benchmark electricity price data to obtain the electricity purchase cost data for different sub-pre-determined time periods; wherein, the electricity price adjustment ratio includes the peak price adjustment ratio and the off-peak price adjustment ratio; the peak price adjustment ratio is greater than 1, and the off-peak price adjustment ratio is less than 1.

[0097] In this embodiment, the specific explanation of the electricity purchase cost data can be found in the explanation in step S111, and will not be repeated here.

[0098] Step S122: Multiply the electricity consumption, price change sensitivity coefficient, and differential response electricity ratio in sequence to obtain the differential response electricity; wherein, the differential response electricity ratio is the ratio of the difference between the electricity purchase cost data and the benchmark electricity price data for the sub-predetermined period to the benchmark electricity price data.

[0099] In this embodiment, the price change sensitivity coefficient is a coefficient that quantifies the sensitivity of air conditioning load to changes in electricity prices. A higher value indicates a more significant impact of electricity prices on the load. It is obtained by fitting historical building load data. In other words, the price change sensitivity coefficient is the user demand price elasticity coefficient. Specifically, the price change sensitivity coefficient... The calculation can statistically analyze the historical load data series Q of commercial buildings. L With the corresponding historical time-of-use electricity price data P L Sequence. Based on the definition of price elasticity of demand in economics, the following logarithmic regression model is established: ,in Let be the initial price change sensitivity coefficient to be solved. The control variables are (e.g., outdoor temperature, date type, etc.). The initial sensitivity coefficient for the user is obtained by fitting the above equation using the least squares method. .

[0100] In actual operation, to address the time-varying nature of user behavior, the system adjusts the sensitivity coefficient based on the "actual response deviation" after each control cycle. Perform correction. Let the predicted difference response charge at time t be... The actual monitored difference in response power was Define the correction factor Based on exponential smoothing, update the price change sensitivity coefficient for the next time step t+1. , This is the forgetting factor, with a value range of [0.1, 0.3]. If... A value greater than 1 indicates that the actual number of user responses is greater than the predicted number. The original coefficient underestimated the users' price sensitivity, and the system will automatically adjust it upwards. Conversely, the adjustment will be lowered.

[0101] In this embodiment, the differential response power ratio reflects the proportion of the load impacted by the degree to which the electricity price deviates from the benchmark value. The calculation logic is "(current electricity price - benchmark electricity price) / benchmark electricity price". A positive value indicates an increase in the electricity price, and a negative value indicates a decrease in the electricity price. In other words, when the differential response power ratio is positive, it indicates that the current sub-preset time period is a peak period; while when the differential response power ratio is negative, it indicates that the current sub-preset time period is a valley period.

[0102] In this embodiment, the differential response electricity is the non-contractual load adjustment amount caused by electricity price fluctuations, i.e., "electricity consumption × price change sensitivity coefficient × differential response electricity ratio," quantifying the correlation between electricity price fluctuations and load fluctuations. Specifically, the differential response electricity... It can be represented as:

[0103]

[0104] in, This indicates the electricity usage for a preset time period. This is the price change sensitivity coefficient. Data on the cost of purchasing electricity. This is the benchmark electricity price data.

[0105] Step S123: Multiply the electricity purchase cost data for the sub-predetermined time period by the difference between the electricity usage for the sub-predetermined time period and the differential response electricity to obtain the differential response cost data.

[0106] In this embodiment, the time-of-use electricity purchase cost is first calculated, and then the differential response electricity is derived through the sensitivity coefficient and electricity ratio. Finally, the time-of-use differential response cost data of a single user in a commercial building during a single sub-preset time period is calculated.

[0107] Step S124: Accumulate the differential response cost data of each sub-predetermined time period within the predetermined time period to construct the differential response cost function.

[0108] In this embodiment, the differential response cost function for a single user within a preset time period is obtained by summing the differential response cost data for each sub-preset time period within a preset time period for a single user in a commercial building. Differential Response Cost Function It can be represented as:

[0109]

[0110] Where T is the number of sub-preset time periods within the preset time period.

[0111] The above embodiments, by introducing a price change sensitivity coefficient, make the calculation of differential response electricity volume more aligned with the characteristics of air conditioning loads in different regions, thereby improving the relevance of the cost model. Furthermore, by linking electricity volume to electricity price fluctuations and load adjustments, the cost of non-contractual responses is accurately quantified, compensating for the shortcomings of traditional models that ignore the indirect costs of electricity price fluctuations.

[0112] In some embodiments, in step S140, the result of performing a high-order Taylor expansion on the deviation between the cumulative comprehensive response electricity and the ideal response electricity of each user in the commercial building in each sub-predetermined time period is multiplied by the user dissatisfaction coefficient to obtain the dissatisfaction cost function, which may include the following steps.

[0113] Step S141: Based on the base penalty coefficient Factors influencing user willingness Determine the user dissatisfaction coefficient ;in, For shape parameters, and .

[0114] In this embodiment, the base penalty coefficient The baseline coefficient for the cost of dissatisfaction is determined by building occupant surveys and historical comfort data, reflecting users' basic tolerance for load regulation. (Based penalty coefficient) The objective function can be adjusted. In other words, when the base penalty coefficient... The larger the base penalty coefficient, the higher the user dissatisfaction. Therefore, when solving the objective function, more emphasis should be placed on user satisfaction with power regulation. The larger the value, the lower the user dissatisfaction. Therefore, when solving the objective function, more emphasis is placed on the electricity output that can be provided to the user. Specifically, considering the combined cost of response and the cost of dissatisfaction, The range can be set to .when At times, the focus is on user satisfaction; when At that time, the focus was on considering the user's power output.

[0115] In this embodiment, the user willingness influence factor The factor is dynamically changing over time, quantifying users' willingness to accept the current regulatory behavior; the higher the willingness, the smaller the dissatisfaction coefficient. When α(t)≫0, it indicates that users have a strong willingness to respond. That is, the user dissatisfaction coefficient is very low; when When this occurs, it indicates that the user's willingness to respond is very weak. This means that the user dissatisfaction coefficient is close to its maximum value.

[0116] In this embodiment, shape parameters To adjust the curve shape of the influence of user willingness on dissatisfaction coefficient (β>0), the larger the β value, the more significant the impact of willingness on dissatisfaction. This parameter can be calibrated using user behavior data. A large β value results in a very steep curve, resembling a "step," indicating that users are very sensitive; a slight decrease in willingness can cause a sudden surge in dissatisfaction. A small β value results in a flatter curve, indicating that users are more tolerant; even with a significant decrease in willingness, dissatisfaction increases slowly. User behavior characteristics were analyzed based on historical response data. A β value of 2 was set for sensitive users, 0.5 for tolerant users, and 1 for other users.

[0117] Step S142: According to the preset weighting coefficient, the responsive power output and the differential responsive power within the sub-predetermined time period are weighted and summed to obtain the comprehensive responsive power.

[0118] In this embodiment, the comprehensive response power is the power that a single user can provide within a sub-predetermined time period, obtained by weighting and summing the responsive power output and the differential response power according to the weighting coefficients in the above embodiments.

[0119] Step S143: Add up the total response electricity of each user in the commercial building during each sub-predetermined time period within the predetermined time period to obtain the cumulative total response electricity.

[0120] In this embodiment, the total response power is accumulated. The result, obtained by summing the total electricity consumption of each user within a commercial building during each sub-scheduled period within a scheduled time period, can be expressed as:

[0121]

[0122] Where n is the number of users participating in the response within the commercial building, and T is the number of sub-preset time periods within the preset time period.

[0123] Step S144: Multiply the result of a higher-order Taylor expansion of the difference between the cumulative comprehensive response power and the ideal response power by the user dissatisfaction coefficient to obtain the dissatisfaction cost function.

[0124] In one specific embodiment, a 6th-order Taylor polynomial is used to describe the deviation between the actual response power and the ideal power, thus the dissatisfaction cost function is... It can be represented as:

[0125]

[0126] in, The dissatisfaction coefficient depends on factors influencing user willingness. The larger the value, the weaker the user's willingness to respond; Provides the ideal response power for users.

[0127] In the above embodiments, user willingness is quantified into mathematical factors to achieve dynamic adjustment of the cost of dissatisfaction, avoiding experience evaluation bias caused by static coefficients. Secondly, higher-order Taylor expansion improves the accuracy of power deviation quantification, ensuring that the cost of dissatisfaction matches the actual impact on comfort, balancing control effectiveness and user experience.

[0128] In some embodiments, prior to step S141, the method for regulating the air conditioning load of commercial buildings based on user response behavior may further include the following steps.

[0129] Step S1401: Based on the influence coefficient of user's education level Impact coefficient of household income And the influence coefficient of the average age of users' households Determine the comprehensive subjective influence coefficient ;in, .

[0130] In this embodiment, users with higher household incomes may be less interested in demand response compensation and relatively insensitive to changes in electricity prices. Conversely, users with higher levels of education and younger / middle-aged users are more receptive to new things and therefore more likely to participate in demand response. To quantify the impact of these factors, an influence coefficient based on user education level is introduced. Impact coefficient of household income and the influence coefficient of average age of user households .

[0131] In this embodiment, an education level mapping table is pre-established, mapping the user's highest education level information registered at the user terminal or when signing the contract to discrete values. Considering that users with higher education levels are generally more receptive to new technologies and environmental protection concepts—in other words, users with higher education levels are more willing to participate in power output response behavior—the following mapping logic can be set: if the user's education level is high school or below, set... =0.8; If the user's education level is associate's or bachelor's degree, set to 0.8. =1.0; If the user's educational background is a master's degree or above, set to 1.0. =1.2.

[0132] In this embodiment, the impact coefficient of household income The determination can be based on the median annual household income of the previous year published by the local statistics bureau. As a benchmark, the coefficient is calculated using a piecewise normalized function. Considering that lower-income households are more sensitive to electricity subsidies (stronger willingness to pay), while higher-income households are less sensitive to price changes (weaker willingness to pay), the specific calculation formula is as follows: Let the user's declared annual household income... ,when (In the lower income range) =1.1; when For the middle-income range, linear interpolation is used: = The calculation result is rounded to two decimal places; when (In the higher income range) =0.7.

[0133] In this embodiment, the influence coefficient of the average age of the user's household The determination can be based on the average age of family members. Based on the differences in the ability to operate smart devices and the willingness to participate among different age groups, a non-linear mapping relationship was constructed: Youth Group ( This group is quick to accept new things, but their lifestyles fluctuate greatly. =1.1; Middle-aged group ( This group is typically the primary decision-maker for household electricity usage, and they have relatively stable lifestyles, the strongest responsiveness and execution ability, and are the most likely to set... =1.3; elderly group ( Considering that this group is more sensitive to changes in comfort and has a lower acceptance of digital operation, the following settings are made: = Furthermore, a lower limit is set to 0.9, meaning that when the calculation result is less than 0.9, it is taken as 0.9.

[0134] It should be noted that the data on users' education level, household income, and average household age were primarily collected based on data submitted by users during registration when signing response contracts with the power grid, and this data is authorized by the users. Furthermore, the mapping relationship between education level, household income, average household age, and specific impact data may vary in different regions and can be adjusted appropriately according to local conditions.

[0135] In this embodiment, the subjective influence coefficient is used to quantify the impact of the user's own attributes on the degree of willingness, integrating education level. Family income Average age Three dimensions, through formula Normalized values, ranging from 0 to 1. Among these, the influence coefficient of education level... The distribution ranges from [0.8, 1.2]; the influence coefficient of household income. The distribution ranges from [0.7, 1.1]; the influence coefficient of average family age. It is distributed between [0.9, 1.3].

[0136] Step S1402: If the electricity purchase cost data is less than the benchmark electricity price data, based on the objective influence coefficient... Duration of air conditioner start / stop status and minimum start / stop time of air conditioner Calculate the degree of objective willingness ;in, The user willingness factor is expressed as follows: ;in, Data on the cost of purchasing electricity. For benchmark electricity price data, The data represents the highest electricity purchase cost, and N() is the normal distribution function.

[0137] In this embodiment, the objective influence coefficient is used to quantify the impact of air conditioning operation status on user willingness. It is determined by the performance of the air conditioning equipment and the building insulation conditions, reflecting the impact of the objective environment on user experience. In a specific embodiment, the objective influence coefficient... It can be set to 0.5, representing a trade-off between comfort and start-stop losses. Understandably, in some other embodiments, if the user prioritizes comfort, the value will be reduced. If the user prefers protection against start-up and shutdown losses, then increase the setting. . The interval range can be set to 0.3≤ ≤0.7.

[0138] In this embodiment, the impact of objective factors on user response willingness is considered. When the on / off state of the terminal device changes and the duration of the change is short, users are generally less willing to respond in order to protect the device's lifespan. As the duration of the device state gradually increases, users' willingness to respond gradually increases. When the device changes its on / off state again, users' willingness to respond decreases again. To reduce network load and protect user privacy, the system updates a "device state table" in real time, recording the time of the most recent state change for each user i's air conditioner. If load regulation calculations are required at the current time t, the system calculates the duration in real time using the following formula. : =t- The system only uploads a data packet containing (device ID, new status, and switching time) to the control platform when the device status changes (from on to off, or from off to on). During periods when the status remains unchanged, the control platform automatically calculates the duration using the aforementioned formula, eliminating the need for frequent data uploads from sensors. Minimum start-stop time for air conditioning. The minimum allowable start-stop interval for air conditioning equipment (e.g., 5 minutes) is used to avoid frequent start-stop damage to the equipment and serves as the benchmark for calculating objective willingness.

[0139] In this embodiment, the normal distribution function The mean is A normally distributed random term with a variance of 0.01 is used to simulate random disturbances from objective factors, such as fluctuations in ambient temperature, to improve the robustness of the model.

[0140] In this embodiment, when the cost of electricity purchase is lower than the benchmark electricity price, users prioritize the comfort of their living environment and are relatively less willing to participate in demand response. (User willingness influencing factors) This reflects the comprehensive hospital level of participation in demand response by air conditioning end-users in commercial buildings during sub-pre-scheduled periods corresponding to off-peak electricity consumption. When this indicates that the user has a positive willingness to respond; when This indicates a negative user response. Furthermore, The magnitude of the value reflects the strength of the user's willingness to respond.

[0141] Step S1403: If the electricity purchase cost data is greater than the benchmark electricity price data, based on the objective influence coefficient... Duration of air conditioner start / stop status and minimum start / stop time of air conditioner Calculate the degree of objective willingness ;in, The user willingness factor is expressed as follows: .

[0142] In this embodiment, when the cost of electricity purchase is higher than the benchmark electricity price, users are more inclined to participate in demand response activities to obtain subsidies and alleviate their electricity burden. (User willingness influencing factors) This reflects the comprehensive hospital level of air conditioning end-user participation in demand response in commercial buildings during the sub-pre-scheduled time period corresponding to peak electricity consumption.

[0143] The above embodiments, by integrating subjective user attributes (education, income, age) with objective operational status (air conditioner start / stop, electricity price), make the willingness factor more closely reflect actual user behavior. Furthermore, by introducing a normally distributed random term, the model's adaptability to interference factors is improved, avoiding bias in willingness assessment caused by a single factor, and further optimizing the accuracy of the dissatisfaction cost.

[0144] In some embodiments, the electricity purchase cost data includes peak-hour electricity cost data and off-peak-hour electricity cost data. In step S150, the objective function is solved using the preset range of the contract compensation fee and the preset range of the electricity purchase cost data as constraints, which may include the following steps.

[0145] Step S151: Set the contract compensation fee data, peak electricity cost data, and off-peak electricity cost data as branch variables.

[0146] In this embodiment, a branch and bound algorithm is used to solve the problem. The solution process starts from the root node and proceeds by relaxing all nodes. 0≤ If the value is ≤1, the original mixed integer programming problem is transformed into a linear programming problem. The solution to this relaxation problem provides a global lower bound (LB) for the original problem. Based on the relaxation solution, the algorithm employs a strong branching strategy to select branch variables. This strategy comprehensively considers the pseudo-cost of the variable and the degree of improvement in the objective function brought about by historical branches. For the selected branch variable, the algorithm generates two child nodes and adds corresponding constraints to each, thereby systematically dividing the solution space into smaller parts. During node exploration, the algorithm adopts a hybrid node selection strategy. Initially, it prioritizes searching to quickly obtain a feasible integer solution (e.g., an air conditioning start-stop plan and cost that satisfies all constraints), thus establishing a global upper bound. Later, it shifts to a best boundary priority, prioritizing the processing of nodes with the lowest relaxation objective value to effectively improve the global lower bound. Finally, the algorithm outputs the best feasible solution found so far, which is the near-globally optimal commercial building response behavior optimization scheme that satisfies all user preferences and system constraints.

[0147] In this embodiment, branch variables refer to the core variables for solving the objective function, namely, contract compensation cost data, peak-hour electricity cost data, and off-peak electricity cost data; all three are adjustable decision variables. The objective function can be expressed as:

[0148] min + )

[0149] in, For the comprehensive response cost function, Let be the cost function for dissatisfaction.

[0150] Step S152: According to the preset step size, divide each branch variable into multiple discrete values ​​according to the preset numerical range, and construct a multi-level decision tree; where each level represents a branch variable of one dimension.

[0151] In this embodiment, the preset step size refers to the interval of variable discretization (e.g., a compensation cost step size of 0.02 yuan). The numerical range is the constraint boundary of the variable (e.g., peak electricity price of 0.8-0.96 yuan / kWh), balancing the solution accuracy and efficiency.

[0152] It is understandable that the preset value ranges for each branch variable are different. Furthermore, the preset step size for each branch variable can be the same or different. For example, the preset step size for contract compensation fee data is 0.02 yuan, while the preset step size for peak-hour electricity cost data and off-peak-hour electricity cost data is 0.01 yuan.

[0153] Specifically, in this embodiment, the three branch variables can first be mapped to the spatial range of [0,1] according to a preset numerical range, and then the step size can be divided for each branch variable, with the step size of each branch variable set to 0.01. Of course, considering the influence of iteration speed, the step size of each branch variable can also maintain different rates of change, which can be set according to the actual situation.

[0154] In this embodiment, the multi-level decision tree is a decision model constructed according to the branch variable dimension. Each layer corresponds to a variable (such as the first layer contract compensation fee, the second layer peak electricity price, and the third layer valley electricity price). The nodes are discrete values ​​of the variables, and the paths are decision combinations.

[0155] Step S153: In the decision tree, determine a baseline decision chain; wherein the baseline decision chain includes the initial contract compensation fee, the initial peak electricity cost, and the initial off-peak electricity cost.

[0156] In this embodiment, the baseline decision chain is the initial decision combination (initial compensation cost, initial peak / valley electricity price), which is usually taken as the midpoint of the variable range as the baseline for searching the optimal solution.

[0157] Step S154: Using the baseline decision chain as a benchmark, search for the target optimal solution in the decision tree; wherein, the target optimal solution is the value of the contract compensation fee data, the peak electricity cost data, and the off-peak electricity cost data when the objective function value is minimized.

[0158] In this embodiment, a decision tree discretization method is used to avoid the complexity of solving continuous variables, improve solution efficiency, and adapt to the real-time control requirements of commercial buildings. Furthermore, the multi-level structure covers all variable combinations, ensuring the comprehensiveness of the optimal solution, while constraints are embedded within the variable range to guarantee the feasibility of the solution.

[0159] In some embodiments, in step S154, searching for the target optimal solution in the decision tree based on the benchmark decision chain may include the following steps.

[0160] Step S1541: If the objective function value corresponding to the current decision chain is less than the objective function value corresponding to the benchmark decision chain, update the current decision chain to the benchmark decision chain and perform pruning operation on the benchmark decision chain before the update.

[0161] Step S1542: If the objective function value corresponding to the current decision chain is greater than the objective function value corresponding to the benchmark decision chain, perform a pruning operation on the current decision chain.

[0162] In this embodiment, pruning refers to the optimization strategy in decision tree search, which deletes decision chains whose objective function values ​​are inferior to the benchmark, reduces invalid search paths, and improves the solution speed.

[0163] In this embodiment, the current decision chain refers to the decision combination being evaluated during the search process. It is compared with the objective function value of the benchmark decision chain to determine whether to retain or delete it. If the objective function value of the current decision chain is less than that of the benchmark chain, the benchmark chain is updated and the old benchmark chain is deleted; if the current value is greater than that of the benchmark chain, the current chain is directly deleted, and the solution is converged to the optimal solution through iterative pruning.

[0164] In this embodiment, the pruning strategy significantly reduces invalid search paths in the decision tree, lowers the computational load, and improves the search speed for the optimal solution, meeting the timeliness requirements of real-time control of air conditioning load in commercial buildings. Furthermore, the baseline chain is iteratively updated to ensure that the final solution is globally optimal or nearly globally optimal.

[0165] In some embodiments, after step S154, the method for regulating the air conditioning load of commercial buildings based on user response behavior may further include the following steps.

[0166] Step S1551: Based on the target optimal solution, determine the sub-air conditioning power of each user in each sub-pre-determined time period.

[0167] In this embodiment, the sub-air conditioning power is the optimal operating power of each user (or each air conditioning unit) in the corresponding sub-predetermined time period, which is derived from the target optimal solution.

[0168] Step S1552: When the power of each sub-air conditioner is greater than or equal to the preset minimum air conditioner power and the power of each sub-air conditioner is less than or equal to the preset maximum air conditioner power, the commercial building is subjected to segmented load control based on the cumulative air conditioner power of each user within each sub-predetermined time period.

[0169] In this embodiment, the preset minimum / maximum air conditioning power is the operating boundary of the air conditioning equipment. During operation, the sub-air conditioning power... for The air conditioner is The actual power consumption during the specified time period. The preset maximum air conditioning power is the maximum power of user i's air conditioner, determined by the device parameters. The preset minimum air conditioning power is the minimum power requirement set for user i's air conditioner to maintain operation when it is in the start-up state.

[0170] In this embodiment, for user i, the range of its sub-air conditioner power at time t can be expressed as: .in, For binary variables, when At that time, the user The air conditioner is The time period is open, when At that time, the user The air conditioner is The time period is in a closed state. That is, when When =0, the sub-air conditioner power of user i is adjusted to 0 within the preset time period.

[0171] In this embodiment, segmented load control is implemented by dividing the control unit into sub-predetermined time periods. Based on the cumulative air conditioning power of each time period, the load is adjusted in different time periods to adapt to the electricity price and user preference characteristics of different time periods.

[0172] In the above embodiments, the sub-air conditioning power of each user in each time period is determined based on the optimal solution, and it is verified whether the power is within the safety boundary (if it exceeds, it is adjusted to the boundary value) to avoid exceeding the power limit that users can provide. Then, segmented control is implemented according to the cumulative power of sub-time periods, so that the control scheme is more in line with the actual operation needs, and a closed-loop management of "optimal solution - equipment safety - time-sharing adaptation" is achieved.

[0173] The method for regulating air conditioning load in commercial buildings based on user response behavior provided by this invention takes into account the differences in user preferences and behavioral inertia. By constructing a user response willingness model and introducing user willingness influencing factors, it comprehensively considers the impact of subjective and objective factors on users' willingness to participate in demand response, and portrays the user's response decision-making process. In this way, it can deeply explore the regulation potential of air conditioning load and dynamically formulate differentiated air conditioning load regulation strategies while ensuring user satisfaction.

[0174] Please see Figure 2 One embodiment of the present invention provides a control device for air conditioning load in commercial buildings based on user response behavior. The control device may include: a contract cost construction module, a response cost construction module, a comprehensive cost construction module, a dissatisfaction cost construction module, and an objective function solution module.

[0175] The contract cost construction module is used to construct a contract response cost function based on the contract response cost data for air conditioning load in each sub-predetermined period within a predetermined period; wherein, the contract response cost data is the product of the electricity purchase cost data and the electricity usage in the sub-predetermined period minus the product of the contract compensation cost data and the responsive power output.

[0176] The response cost construction module is used to construct a differential response cost function based on the differential response cost data for air conditioning load in each sub-predetermined period within a predetermined period; wherein the differential response cost data is the product of the electricity consumption of the sub-predetermined period minus the differential response electricity consumption and the electricity purchase cost data of the sub-predetermined period.

[0177] The comprehensive cost construction module is used to perform a weighted summation of the contract response cost function and the differential response cost function of each user in the commercial building according to a preset weighting coefficient to obtain the comprehensive response cost function.

[0178] The Dissatisfaction Cost Construction Module is used to multiply the result of a high-order Taylor expansion of the deviation between the cumulative comprehensive response electricity and the ideal response electricity of each user in a commercial building in each sub-pre-scheduled period by the user dissatisfaction coefficient to obtain the dissatisfaction cost function.

[0179] The objective function solving module is used to solve the objective function with the preset range of the contract compensation fee and the preset range of the electricity purchase cost data as constraints; and to regulate the load of the commercial building based on the air conditioning load corresponding to the optimal solution of the objective function; wherein, the objective function is the minimum sum of the comprehensive response cost function and the dissatisfaction cost function.

[0180] The specific functions and effects of the commercial building air conditioning load control device based on user response behavior can be explained by referring to other embodiments in this specification, and will not be repeated here. Each module in the commercial building air conditioning load control device based on user response behavior can be implemented entirely or partially through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0181] Please see Figure 3 One embodiment of the present invention can provide an electronic device, the electronic device comprising:

[0182] A memory, and one or more processors communicatively connected to the memory;

[0183] The memory stores instructions that can be executed by the one or more processors, which, when executed by the one or more processors, enable the one or more processors to implement the method for regulating the air conditioning load of commercial buildings based on user response behavior as described in any of the above embodiments.

[0184] One embodiment of the present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for regulating the air conditioning load of a commercial building based on user response behavior as described in any of the above embodiments.

[0185] This specification also provides a computer program product containing instructions that, when executed by a computer, cause the computer to perform the method for regulating the air conditioning load of a commercial building based on user response behavior as described in any of the above embodiments.

[0186] It is understood that the specific examples in this document are only intended to help those skilled in the art better understand the embodiments described herein, and are not intended to limit the scope of the invention.

[0187] It is understood that in the various embodiments described in this specification, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments described in this specification.

[0188] It is understood that the various implementation methods described in this specification can be implemented individually or in combination, and the implementation methods in this specification are not limited in this respect.

[0189] Unless otherwise stated, all technical and scientific terms used in the embodiments of this specification have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of this specification. The term "and / or" as used in this specification includes any and all combinations of one or more of the associated listed items. The singular forms "a," "the," and "the" as used in the embodiments of this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0190] It is understood that the processor in this invention can be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method implementation can be completed by the integrated logic circuitry in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this specification. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this specification can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0191] It is understood that the memory in this invention can be volatile memory or non-volatile memory, or may include both. Specifically, the non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM). It should be noted that the memory in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0192] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in the embodiments of the present invention are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0193] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this specification.

[0194] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the aforementioned method implementations, and will not be repeated here.

[0195] In the several embodiments provided in this specification, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0196] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0197] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0198] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of this specification, in essence, or the parts that contribute to the prior art, or parts of the technical solutions, can be embodied in the form of software products. These computer software products are stored in a storage medium and include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this specification. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0199] The above description is merely a specific embodiment of this specification, but the scope of protection of this invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this specification should be included within the scope of protection of this specification. Therefore, the scope of protection of this invention should be determined by the scope of the claims.

Claims

1. A method for regulating the air conditioning load of commercial buildings based on user response behavior, characterized in that, The method includes: A contract response cost function is constructed based on the contract response cost data for air conditioning load in each sub-predetermined period within the predetermined period; wherein, the contract response cost data is the product of the electricity purchase cost data and the electricity usage in the sub-predetermined period minus the product of the contract compensation cost data and the responsive power output. A differential response cost function is constructed based on the differential response cost data for air conditioning load in each sub-predetermined period within the predetermined period; wherein, the differential response cost data is the product of the electricity consumption of the sub-predetermined period minus the differential response electricity consumption and the electricity purchase cost data of the sub-predetermined period. The contract response cost function and the differential response cost function of each user in the commercial building are weighted and summed according to preset weighting coefficients to obtain the comprehensive response cost function. The result of a high-order Taylor expansion of the deviation between the cumulative comprehensive response electricity and the ideal response electricity of each user in the commercial building during each sub-pre-scheduled period is multiplied by the user dissatisfaction coefficient to obtain the dissatisfaction cost function. Using the preset range of the contract compensation cost data and the preset range of the electricity purchase cost data as constraints, an objective function is solved; and the air conditioning load corresponding to the optimal solution of the objective function is used to regulate the load of the commercial building; wherein, the objective function is the minimum sum of the comprehensive response cost function and the dissatisfaction cost function.

2. The method according to claim 1, characterized in that, The contract response cost function is constructed based on the contract response cost data for air conditioning load in each sub-premise period within the pre-premise period, including: The electricity price adjustment ratio for different sub-pre-scheduled time periods is multiplied by the benchmark electricity price data to obtain the electricity purchase cost data for different sub-pre-scheduled time periods; wherein, the electricity price adjustment ratio includes the peak price adjustment ratio and the off-peak price adjustment ratio; the peak price adjustment ratio is greater than 1, and the off-peak price adjustment ratio is less than 1; The contract response cost data for the sub-predetermined period is obtained by multiplying the electricity purchase cost data and electricity usage data for the sub-predetermined period by the product of the contract compensation cost data and the responsive power output data for the sub-predetermined period; wherein the responsive power output data and the contract compensation cost data have a linear relationship. The contract response cost data of each sub-predetermined time period within the predetermined time period are accumulated to construct the contract response cost function.

3. The method according to claim 1, characterized in that, A differential response cost function is constructed based on the differential response cost data for air conditioning load in each sub-scheduled period within the predetermined time period, including: The electricity price adjustment ratio for different sub-pre-scheduled time periods is multiplied by the benchmark electricity price data to obtain the electricity purchase cost data for different sub-pre-scheduled time periods; wherein, the electricity price adjustment ratio includes the peak price adjustment ratio and the off-peak price adjustment ratio; the peak price adjustment ratio is greater than 1, and the off-peak price adjustment ratio is less than 1; The differential response electricity ratio is obtained by multiplying the electricity consumption, the price change sensitivity coefficient, and the differential response electricity ratio in sequence; wherein, the differential response electricity ratio is the ratio of the difference between the electricity purchase cost data and the benchmark electricity price data for the sub-predetermined period to the benchmark electricity price data. The difference in response cost data is obtained by multiplying the electricity purchase cost data for the sub-predetermined period by the difference between the electricity consumption for the sub-predetermined period and the difference in response electricity consumption. The differential response cost data of each sub-predetermined time period within the predetermined time period are accumulated to construct a differential response cost function.

4. The method according to claim 1, characterized in that, The deviation between the cumulative total response electricity consumption of each user in the commercial building during each sub-scheduled time period and the ideal response electricity consumption is expanded using a higher-order Taylor series. This result is then multiplied by the user dissatisfaction coefficient to obtain the dissatisfaction cost function, which includes: Based on the base penalty coefficient Factors influencing user willingness Determine the user dissatisfaction coefficient ;in, For shape parameters, and ; According to the preset weighting coefficient, the responsive power output and the differential responsive power within the sub-predetermined time period are weighted and summed to obtain the comprehensive responsive power. The total response electricity of each user in the commercial building during each sub-pre-determined period within the predetermined period is added together to obtain the cumulative total response electricity. The difference between the cumulative comprehensive response power and the ideal response power is expanded using a higher-order Taylor series, and then multiplied by the user dissatisfaction coefficient to obtain the dissatisfaction cost function.

5. The method according to claim 4, characterized in that, Based on the base penalty coefficient Factors influencing user willingness Determine the user dissatisfaction coefficient Prior to the step, the method includes: Influence coefficient based on user's education level Household income impact coefficient And the influence coefficient of the average age of users' households Determine the comprehensive subjective influence coefficient ;in, ; When the electricity purchase cost data is less than the benchmark electricity price data, based on the objective impact coefficient Duration of air conditioner start / stop status and minimum start / stop time of air conditioner Calculate the degree of objective willingness ;in, The user willingness factor is expressed as follows: ;in, Data on the cost of purchasing electricity. For benchmark electricity price data, For the highest electricity purchase cost data, N() is the normal distribution function; When the electricity purchase cost data is greater than the benchmark electricity price data, based on the objective impact coefficient Duration of air conditioner start / stop status and minimum start / stop time of air conditioner Calculate the degree of objective willingness ;in, The user willingness factor is expressed as follows: .

6. The method according to claim 1, characterized in that, The electricity purchase cost data includes peak-hour electricity cost data and off-peak electricity cost data. Using the preset range of the contract compensation fee and the preset range of the electricity purchase cost data as constraints, the objective function is solved, including: Set the contract compensation fee data, peak electricity cost data, and off-peak electricity cost data as branch variables; According to a preset step size, each branch variable is divided into multiple discrete values ​​according to a preset numerical range, and a multi-level decision tree is constructed; where each level represents a branch variable of one dimension. In the decision tree, a baseline decision chain is determined; wherein the baseline decision chain includes the initial contract compensation fee, the initial peak electricity cost, and the initial off-peak electricity cost; Using the baseline decision chain as a benchmark, the target optimal solution is searched in the decision tree; wherein, the target optimal solution is the value of the contract compensation fee data, the peak electricity cost data, and the off-peak electricity cost data when the objective function value is minimized.

7. The method according to claim 6, characterized in that, Using the baseline decision chain as a reference, searching for the optimal solution of the objective in the decision tree includes: If the objective function value corresponding to the current decision chain is less than the objective function value corresponding to the benchmark decision chain, the current decision chain is updated to the benchmark decision chain, and the benchmark decision chain before the update is pruned. If the objective function value of the current decision chain is greater than the objective function value of the benchmark decision chain, then pruning is performed on the current decision chain.

8. The method according to claim 6 or 7, characterized in that, After the step of searching for the optimal solution of the objective in the decision tree based on the baseline decision chain, the method further includes: Based on the target optimal solution, determine the sub-air conditioner power of each user in each sub-pre-scheduled time period; When the power of each sub-air conditioner is greater than or equal to the preset minimum air conditioner power, and the power of each sub-air conditioner is less than or equal to the preset maximum air conditioner power, the commercial building is subjected to segmented load control based on the cumulative air conditioner power of each user within each sub-predetermined time period.

9. A control device for air conditioning load in commercial buildings based on user response behavior, characterized in that, The commercial building air conditioning load control device based on user response behavior includes: The contract cost construction module is used to construct a contract response cost function based on the contract response cost data for air conditioning load in each sub-predetermined period within a predetermined period; wherein, the contract response cost data is the product of the electricity purchase cost data and the electricity usage in the sub-predetermined period minus the product of the contract compensation cost data and the responsive power output. The response cost construction module is used to construct a differential response cost function based on the differential response cost data for air conditioning load in each sub-predetermined period within a predetermined period; wherein, the differential response cost data is the product of the electricity consumption of the sub-predetermined period minus the differential response electricity consumption and the electricity purchase cost data of the sub-predetermined period. The comprehensive cost construction module is used to perform a weighted summation of the contract response cost function and the differential response cost function of each user in the commercial building according to a preset weighting coefficient to obtain the comprehensive response cost function. The Dissatisfaction Cost Construction Module is used to multiply the result of the high-order Taylor expansion of the deviation between the cumulative comprehensive response electricity and the ideal response electricity of each user in the commercial building in each sub-pre-scheduled period by the user dissatisfaction coefficient to obtain the dissatisfaction cost function. The objective function solving module is used to solve the objective function with the preset range of the contract compensation fee and the preset range of the electricity purchase cost data as constraints; and to regulate the load of the commercial building based on the air conditioning load corresponding to the optimal solution of the objective function; wherein, the objective function is the minimum sum of the comprehensive response cost function and the dissatisfaction cost function.

10. An electronic device, characterized in that, The device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method for regulating the air conditioning load of a commercial building based on user response behavior as described in any one of claims 1 to 8.

11. A computer storage medium, characterized in that, It stores a computer program, which, when executed by a processor, implements the method for regulating the air conditioning load of a commercial building based on user response behavior as described in any one of claims 1 to 8.

Images