A smart building energy scheduling method considering satisfaction under multi-scenario weather conditions

By constructing intelligent building models and satisfaction models in multi-scene weather and combining multi-objective functions for energy scheduling, the problem of failure to fully consider multiple weather scenarios and flexible loads in the existing technology is solved, and more comprehensive scheduling and Improved user comfort.

CN117114199BActive Publication Date: 2024-11-22SHANDONG JIANZHU UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311162783.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-09-11
Publication Date
2024-11-22
Estimated Expiration
2043-09-11

AI Technical Summary

Technical Problem

The prior art fails to fully consider the impact of multiple weather scenarios on system scheduling in intelligent building energy scheduling, ignores the dispatchable capacity of flexible loads, and the objective function is too single, and fails to comprehensively consider economics and user comfort.

Method used

Build an intelligent building model in multi-scene weather, including a comprehensive power generation cost model for normal and inclement weather, and a charging pile and lighting load satisfaction model, combine multi-objective functions and constraints to perform energy scheduling, considering the satisfaction of charging pile and lighting load The degree is converted into a single objective function using the weighting coefficient method to optimize energy scheduling.

Benefits of technology

A more comprehensive energy scheduling for weather changes has been achieved, system flexibility and user comfort has been improved, and a balance between economy and comfort has been found to meet the multiple needs of smart buildings.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117114199B_ABST
    Figure CN117114199B_ABST
Patent Text Reader

Abstract

The present invention discloses a smart building energy scheduling method considering satisfaction under multi-scenario weather, including the following steps: constructing charging pile and lighting load satisfaction models; constructing a comprehensive power generation cost model for normal weather, combining the charging pile and lighting load satisfaction models to obtain a smart building model for normal weather; constructing a comprehensive power generation cost model for severe weather, combining the charging pile and lighting load satisfaction models to obtain a smart building model for severe weather; constructing multi-objective functions and constraints of the smart building models for normal weather and severe weather respectively; and performing energy scheduling of smart buildings based on the corresponding multi-objective functions and constraints. The present invention selects two scenarios, normal weather and severe weather, to optimize the system energy scheduling, thereby obtaining the impact of weather changes on scheduling and obtaining more comprehensive scheduling results.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent building energy scheduling, and in particular relates to an intelligent building energy scheduling method taking satisfaction into consideration under multi-scenario weather conditions. Background Art

[0002] In the context of "dual carbon", the research on intelligent buildings has received more and more attention. In terms of energy configuration of intelligent buildings, new energy generation is usually used to replace traditional thermal power generation, and combined with energy storage systems for operation and scheduling, while bidirectional transmission with the large power grid is carried out according to time-of-use electricity prices. Studying intelligent building modeling methods is an effective means to achieve the economy of low-carbon building energy use.

[0003] The traditional research method is to establish a system power generation cost model, take the lowest power generation cost as the objective function, and obtain the corresponding energy scheduling results based on the constraints of each part; sometimes electric vehicles are considered as mobile energy storage, and corresponding models are established to carry out energy scheduling.

[0004] The above method has the following problems: First, it does not consider the impact of various weather scenarios on system scheduling, but only considers the energy scheduling results of various parts of the system under normal weather conditions, which is not comprehensive enough; second, it ignores the dispatchable capacity of flexible loads in electricity loads, especially lighting loads, which account for a large proportion of building energy consumption and lacks flexibility; third, the objective function considered in traditional optimization modeling is often relatively simple, and fails to comprehensively consider the economy and user comfort of smart buildings.

[0005] Therefore, it is urgent to propose an intelligent building modeling method that considers user satisfaction under multi-scenario weather conditions. Summary of the invention

[0006] The purpose of the present invention is to provide an intelligent building energy scheduling method taking satisfaction into consideration under multi-scenario weather conditions, so as to solve the problems existing in the above-mentioned prior art.

[0007] To achieve the above object, the present invention provides an intelligent building energy scheduling method considering satisfaction under multi-scenario weather conditions, comprising the following steps:

[0008] Construct charging pile and lighting load satisfaction models;

[0009] Constructing a comprehensive power generation cost model for normal weather, combining the charging pile and lighting load satisfaction models, and obtaining a smart building model for normal weather;

[0010] Constructing a comprehensive power generation cost model for severe weather, combining the charging pile and lighting load satisfaction models, and obtaining a smart building model for severe weather;

[0011] Constructing multi-objective functions and constraint conditions of the intelligent building model for normal weather and severe weather respectively;

[0012] Energy scheduling of intelligent buildings is carried out based on the corresponding multi-objective functions and constraints.

[0013] Optionally, the process of constructing the charging pile satisfaction model includes: constructing the charging pile satisfaction model based on the number of electric vehicles, the battery state of charge at the end of the electric vehicle scheduling, and the battery state of charge that is expected to be achieved at the end of the electric vehicle scheduling.

[0014] Optionally, the process of constructing a lighting load satisfaction model includes: constructing an initial lighting load satisfaction model based on the average ambient illumination at a preset moment, the expected value of the Gaussian distribution function, the variance of the Gaussian distribution function, and a threshold value of the user's satisfaction with lighting; performing linear processing on the initial lighting load satisfaction model to obtain the final lighting load satisfaction model.

[0015] Optionally,

[0016] The process of obtaining the average illumination of the environment at a preset time includes: obtaining the average illumination of lighting fixtures based on lighting power density, lighting luminous efficiency, lamp utilization efficiency and room maintenance coefficient; obtaining the average illumination of the environment at the preset time based on the average illumination of the lighting fixtures and the illumination of natural light.

[0017] Optionally, the process of constructing a comprehensive power generation cost model for normal weather includes: obtaining a comprehensive power generation cost model for normal weather based on the depreciation costs of photovoltaics, energy storage batteries and electric vehicles, the maintenance costs of photovoltaics, energy storage batteries and electric vehicles, and the purchase and sale costs of electricity in interaction with time-of-use electricity prices and the large power grid.

[0018] Optionally, the process of constructing a comprehensive power generation cost model for severe weather includes: obtaining a comprehensive power generation cost model for severe weather based on the depreciation costs of energy storage batteries and electric vehicles, the maintenance costs of energy storage batteries and electric vehicles, and the costs of purchasing and selling electricity in interaction with the large power grid.

[0019] Optionally, the multi-objective functions of the smart building models in normal weather and severe weather are consistent, both including: a function to minimize the comprehensive power generation cost, a function to maximize the charging pile satisfaction, and a function to maximize the lighting load satisfaction.

[0020] Optionally, before performing energy scheduling based on the multi-objective function, the method further includes: normalizing the multi-objective function, and then converting the multi-objective function into a single objective function using a weighted coefficient method.

[0021] Optionally, the constraints of the smart building model in normal weather include: power balance constraints in normal weather, charging and discharging power constraints of energy storage systems and electric vehicles, power constraints for interaction with the power grid, charge state continuity constraints of energy storage systems and electric vehicle batteries, and lighting load power constraints.

[0022] Optionally, the constraints of the smart building model for severe weather include: power balance constraints for severe weather, charging and discharging power constraints of energy storage systems and electric vehicles, power constraints for interaction with the power grid, charge state continuity constraints of energy storage systems and electric vehicle batteries, and lighting load power constraints.

[0023] The technical effects of the present invention are:

[0024] The present invention selects two scenarios, normal weather and severe weather, to optimize the scheduling of system energy, thereby obtaining the impact of weather changes on scheduling and obtaining more comprehensive scheduling results.

[0025] The present invention considers flexible lighting load as the backup capacity of the system, establishes a flexible lighting load satisfaction model, links it with real-time natural lighting, reflects the relationship with weather changes, schedules the lighting load on the premise of satisfying user comfort, and realizes the flexibility of the system.

[0026] The present invention adds a satisfaction model of charging piles and a satisfaction model of flexible lighting loads on the basis of the traditional model, selects multiple objective functions to perform energy scheduling for intelligent buildings, and can meet the comfort of users of intelligent buildings while achieving economy. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0028] Figure 1 A schematic flow chart of a smart building energy scheduling method considering satisfaction under multiple weather scenarios in an embodiment of the present invention;

[0029] Figure 2 Schematic diagram of the relationship between lighting load satisfaction and average illumination in the Gaussian function in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0031] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] Embodiment 1

[0033] like Figure 1 As shown, this embodiment provides an intelligent building energy scheduling method that takes satisfaction into consideration under multiple weather scenarios. First, the system is modeled under normal weather scenarios, and the constraints of each part and multiple objective function processing methods are introduced.

[0034] Step 1: Establish a comprehensive power generation cost model for the system

[0035] Under normal weather conditions, photovoltaic power generation works normally, and the comprehensive power generation cost mainly includes the maintenance and depreciation costs of photovoltaic power generation, energy storage systems, and electric vehicles, as well as the cost of purchasing and selling electricity through two-way interaction with the large power grid based on time-of-use electricity prices.

[0036] The impairment expense models for each component are as follows:

[0037]

[0038]

[0039] Among them, M dis (t) is the depreciation cost, RMB; μ is the depreciation rate; M ini is the initial investment cost per unit power, RMB / kWh; P rated is the rated charge and discharge power, kW; P(t) is the charge and discharge power at time t, kW. μ(a,b) is the depreciation rate calculation formula, where a is the depreciation rate and b is the service life of the equipment.

[0040] The maintenance cost model for each part is as follows:

[0041] M mt (t) = A mt ·P(t) (3)

[0042] Among them, M mt (t) is the maintenance cost, RMB; A mt is the maintenance cost per unit power, RMB / kWh; P(t) is the charging and discharging power at time t, kW.

[0043] Cost model for purchasing and selling electricity from the grid based on time-of-use electricity prices:

[0044] M grid (t) = P grid (t)·M price(t) (4)

[0045]

[0046] Among them, M grid (t) is the electricity purchase and sales cost at time t, P grid (t) is the power of real-time interaction between the system and the tie line, M price (t) is the unit price of electricity purchase and sale, m p is the normal electricity price, T p It is usually f is the peak electricity price, T f is the peak time, m g is the off-peak electricity price, T g It's valley time.

[0047] In summary, the comprehensive power generation cost model can be obtained:

[0048]

[0049] Where T is the number of sampling points in a day; M dis_pv (t), M dis_bat (t), M dis_ev (t) are the depreciation costs of photovoltaic, energy storage battery and electric vehicle respectively; M mt_pv (t), M mt_bat (t), M mt_ev (t) are the maintenance costs of photovoltaic, energy storage battery and electric vehicle respectively; M grid (t) is the cost of electricity purchase and sale interacting with the grid.

[0050] Step 2: Establish a satisfaction model for charging piles and lighting loads

[0051] The charging piles inside the building play an important role in the charging and discharging scheduling of electric vehicles. The satisfaction model of the charging pile needs to take into account the satisfaction level of each electric car owner. After calculating the satisfaction level of each electric car user, the average satisfaction level of all electric car owners is regarded as the satisfaction level of the charging pile.

[0052] The charging pile satisfaction model is as follows:

[0053]

[0054] Where N is the number of electric vehicles; SOC end is the battery state of charge of the i-th electric vehicle at the end of dispatch; SOC exp It is the desired state of charge of the i-th electric vehicle at the end of the dispatch. It takes values ​​between 0 and 1. If the state of charge at the end of the final dispatch is the same as the expected value, the satisfaction is the maximum value 1.

[0055] When scheduling the load capacity of the lighting load, it is necessary to satisfy the user's comfort. Therefore, when adjusting the lighting load power to respond to system frequency events, it is necessary to satisfy the user comfort of the lighting load. Here, the Gaussian distribution function is used to represent the user's satisfaction level with the average illumination of the environment.

[0056] The satisfaction model of lighting load is as follows:

[0057]

[0058] Among them, μ is the expected value of the Gaussian distribution function, σ is the variance of the Gaussian distribution function, L(t) is the average ambient illuminance at time t, and t is the threshold of user satisfaction with lighting. Here, the parameters in the Gaussian function are: μ = 350, σ = 100, t = 0.4.

[0059] from Figure 2 It can be seen that when the average illuminance is 350 lx, the satisfaction is the highest, with a value of 1. When the lighting load satisfaction is set to 0.4, the average illuminance range is [200,500] lx.

[0060] The design of the indoor lighting system must comply with the national standard lighting power density (LPD). The lighting power can be obtained based on the indoor LPD:

[0061]

[0062] Where LPD is the lighting power density, W / m 2 ; Pi is the power of the i-th lighting in the room, W; K is the number of lighting in the room; S is the area of ​​the room, m 2 .

[0063] The calculation method of average illumination generally adopts the utilization coefficient method, which is as follows:

[0064] L av =LPD·α·β·γ (10)

[0065] L(t)=L nature +L av (11)

[0066] Among them, L av is the average illumination of the lighting fixture, lx; α is the luminous efficiency of the lighting; β is the utilization efficiency of the lighting fixture; γ is the maintenance factor of the room; L(t) is the average illumination of the environment at time t, lx; L nature is the natural light illuminance at time t, lx.

[0067] Step 3: Simplify complex nonlinear models

[0068] In order to facilitate the subsequent use of the cplex solver to solve the optimization problem, the nonlinear model needs to be converted into a linear model. For convenience, the Gaussian distribution function is simplified to a triangular distribution function with a high degree of similarity, and the lighting load satisfaction model becomes:

[0069]

[0070] Where L(t) is the average illuminance of the environment at time t, lx; L best is the average illuminance when satisfaction is maximum, L max is the maximum value of the selected average illumination threshold, L min It is the minimum value of the average illumination threshold of the selected area.

[0071] Step 4: Construct multi-objective functions and corresponding constraints

[0072] (1) This embodiment selects three objective functions: minimum comprehensive power generation cost, maximum charging pile satisfaction, and maximum lighting load satisfaction. Since the three objective functions have different physical meanings and inconsistent dimensions, they need to be normalized, and then the weighted coefficient method is used to convert the multi-objective function into a single objective function:

[0073]

[0074] Among them, F max is the comprehensive power generation cost when the satisfaction of charging piles and lighting loads are both maximum, ω1, ω2, and ω3 are the weighted coefficients of the above three objective functions respectively.

[0075] (2) The constraints mainly include power balance constraints, charging and discharging power constraints of energy storage systems and electric vehicles, power constraints for interaction with the power grid, battery state of charge continuity constraints, and power constraints for flexible lighting loads.

[0076] The power balance constraints of the system are as follows:

[0077]

[0078] Among them, P load (t), P led (t) are the fixed load power and dispatchable lighting power of the system at time t, kW; P bat_c (t), P bat_d (t), P ev_c (t), P ev_d (t) are the charging power and discharging power of the energy storage system and electric vehicle at time t, kW; P grid_s , P grid_b (t) are the power sold to and purchased from the large power grid by the system at time t, kW; Ppv (t) is the photovoltaic output at time t, kw.

[0079] In the constraints of charging and discharging of each part and the constraints of interaction with the power grid, a Boolean variable U is introduced c (t), U d (t) indicates its charge and discharge state.

[0080]

[0081] Therefore, the charge and discharge power or interaction power constraint is:

[0082]

[0083] Among them, P c (t), P d (t) represents the charging and discharging power or the power interacting with the grid, kW; P cmax , P dmax Respectively represent the maximum rated charging and discharging power or the maximum grid interaction power, kW.

[0084] Energy storage system and electric vehicle battery state of charge continuity constraints:

[0085]

[0086] Among them, SOC Ini , SOC end 、SOCE xp They represent the initial value, final value and expected value of the energy storage system respectively. For the energy storage system to operate smoothly, the initial value and final value are the same, and the final value of the electric vehicle is the expected value; η C , η d They are the charge and discharge efficiency of the battery, Cap represents the capacity of the battery, SOC max , SOC min They are respectively the maximum and minimum states of charge allowed for the battery.

[0087] The power constraint of flexible lighting load is:

[0088] P led_min (t)≤P led (t)≤P led_max (t) (18)

[0089] Among them, P led (t) is the total lighting load power at time t, kW; P led_min (t), P led_max (t) are the power values ​​corresponding to the minimum and maximum acceptable average illumination at time t, kW.

[0090] Step 4: Objective Function and Constraints for Severe Weather Scenarios

[0091] In bad weather, since sunlight cannot reach the intensity required for photovoltaic power generation, the photovoltaic output is considered to be 0. The model under bad weather scenarios can be slightly modified from the model under normal weather scenarios, that is, only the comprehensive power generation cost model and power balance constraints of the system need to be changed.

[0092] (1) The comprehensive power generation cost of the system becomes:

[0093]

[0094] (2) The power balance constraint becomes:

[0095]

[0096] Other objective functions and constraints are consistent with those in normal weather scenarios, and the processing methods and optimization solutions of multi-objective functions are also consistent with those in normal weather scenarios.

[0097] This embodiment selects two scenarios, normal weather and severe weather, to optimize the scheduling of system energy, thereby obtaining the impact of weather changes on scheduling and obtaining a more comprehensive scheduling result.

[0098] This embodiment considers flexible lighting load as the backup capacity of the system, establishes a flexible lighting load satisfaction model, links it with real-time natural lighting, reflects the relationship with weather changes, schedules the lighting load on the premise of satisfying user comfort, and realizes the flexibility of the system.

[0099] This embodiment adds an electric vehicle satisfaction model and a flexible lighting load satisfaction model to the traditional model, selects multiple objective functions to perform energy scheduling for smart buildings, and can achieve economy while satisfying the comfort of smart building users.

[0100] The present embodiment is further described below with reference to the accompanying drawings and two scenarios.

[0101] Scenario 1: Normal weather

[0102] Under normal weather conditions, all units are considered to participate in energy scheduling.

[0103] Assume that there are three dispatchable charging piles in the building, with the same maximum charging and discharging power of 20kw and charging and discharging efficiency of 0.95; the charging piles can participate in the dispatching time period of [8:00,18:00], and the corresponding electric vehicle battery capacity is 20kwh. It is assumed that the SOC of each electric vehicle at the initial time of dispatch is 0.3, 0.5, and 0.7, and the expected SOC value at the end of dispatch is 0.5; the upper and lower limits of SOC are 0.2 and 0.9.

[0104] The energy storage system has a capacity of 100kwh, a maximum charge and discharge power of 15kw, and a charge and discharge efficiency of 0.95. In this scenario, its initial SOC is set to 0.3, which means that the remaining power is 30kwh.

[0105] When interacting with the power grid, electricity is purchased and sold according to the time-of-use electricity price, and a day is divided into three periods: peak, valley and flat. Peak time: 10:00-15:00, 18:00-21:00, purchase electricity 1.2 yuan / kWh; valley time: 23:00-7:00 the next day, 15:00-18:00, purchase electricity 0.3 yuan / kWh; normal time: 7:00-10:00, 21:00-23:00, purchase electricity 0.78 yuan / kWh. The electricity sales price is 0.5 yuan / kWh. The maximum interactive power with the tie line is 30kw. The parameters of photovoltaic, energy storage and electric vehicle equipment are shown in Table 1.

[0106] Table 1

[0107]

[0108] The dispatchable capacity of the flexible lighting load can be calculated based on the natural light radiation intensity and the average illuminance acceptable to users on that day. The average illuminance threshold is selected as [200, 500] lx, and the natural light radiation intensity and the calculated maximum and minimum dispatchable capacities of the lighting load are shown in Table 2.

[0109] Table 2

[0110]

[0111] The weighted coefficients of the multi-objective function are set to [0.5, 0.25, 0.25]. According to the constraints set in the model, the cplex solver is used to solve the output of each part. Among them, the energy storage system discharge, charging pile discharge, and power grid purchase are all positive values, and the energy storage system charging, charging pile charging, and power grid sales are all negative values.

[0112] In this scenario, the optimal output results of each part obtained by cplex are shown in Table 3.

[0113] Table 3

[0114]

[0115] At this time, the optimal total cost is: 115.527 yuan, the optimal average satisfaction of charging piles is 1, and the optimal average satisfaction of lighting load is 1.

[0116] Scenario 2: Bad weather

[0117] In this scenario, the photovoltaic output is 0 and the natural light radiation is also 0. At this time, the electricity mainly comes from the energy storage system, the remaining power of electric vehicles and the purchase of electricity from the large power grid. At this time, the dispatchable capacity of the lighting load obtained by calculation is shown in Table 4.

[0118] Table 4

[0119]

[0120] In scenario 2, the weight coefficients of the multi-objective function are still set to [0.5, 0.25, 0.25]. The optimal output results of each part obtained by cplex are shown in Table 5.

[0121] Table 5

[0122]

[0123]

[0124] In this scenario, the optimal total cost is: 364.3535 yuan, and the optimal average satisfaction of the charging pile is 1.

[0125] The optimal average satisfaction level of lighting load is 1.

[0126] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A smart building energy scheduling method considering satisfaction under multiple weather scenarios, It is characterized in that The following steps are involved: Construct charging pile and lighting load satisfaction models; Constructing a comprehensive power generation cost model for normal weather, combining the charging pile and lighting load satisfaction models, and obtaining a smart building model for normal weather; Constructing a comprehensive power generation cost model for severe weather, combining the charging pile and lighting load satisfaction models, and obtaining a smart building model for severe weather; Constructing multi-objective functions and constraint conditions of the intelligent building model for normal weather and severe weather respectively; Based on the corresponding multi-objective functions and constraints, the energy scheduling of intelligent buildings is carried out; The process of constructing the satisfaction model of the lighting load includes: constructing the satisfaction model of the initial lighting load based on the average illumination of the environment at a preset moment, the expected value of the Gaussian distribution function, the variance of the Gaussian distribution function and the threshold of the user's satisfaction with lighting; performing linear processing on the satisfaction model of the initial lighting load to obtain the final satisfaction model of the lighting load; The process of obtaining the average illumination of the environment at the preset time includes: obtaining the average illumination of the lighting fixtures based on the lighting power density, the luminous efficiency of the lighting, the utilization efficiency of the lighting fixtures and the maintenance factor of the room; obtaining the average illumination of the environment at the preset time based on the average illumination of the lighting fixtures and the illumination of natural light; The charging pile satisfaction model is as follows: Where N is the number of electric vehicles; SOC end_i is the battery state of charge of the i-th electric vehicle at the end of dispatch; SOC exp_i is the desired state of charge of the i-th electric vehicle at the end of dispatch; The satisfaction model of lighting load is as follows: in, L ( t ) is the average illumination of the environment at time t, L best is the average illuminance when satisfaction is maximum, L max is the maximum value of the selected average illumination, L min is the minimum value of the selected average illumination; The comprehensive electricity generation cost model for normal weather is as follows: in, T is the number of sampling points in a day; M dis_pv ( t ), M dis_bat ( t ), M dis_ev ( t ) are the depreciation costs of photovoltaic, energy storage batteries and electric vehicles respectively; M mt_pv ( t ), M mt_bat ( t ), M mt_ev ( t ) are the maintenance costs of photovoltaics, energy storage batteries, and electric vehicles respectively; M grid ( t ) is the cost of electricity purchase and sale in interaction with the power grid; The comprehensive generation cost model for severe weather is as follows: 。 2. According to the multi-scenario weather satisfaction-based smart building energy scheduling method of claim 1, It is characterized in that The multi-objective functions of the intelligent building models in normal weather and severe weather are consistent, and both include: a function to minimize the comprehensive power generation cost, a function to maximize the charging pile satisfaction, and a function to maximize the lighting load satisfaction.

3. According to the multi-scenario weather satisfaction-based smart building energy scheduling method of claim 2, It is characterized in that Before energy scheduling is performed based on the multi-objective function, the method further includes: normalizing the multi-objective function, and then converting the multi-objective function into a single objective function using a weighted coefficient method.

4. According to the multi-scenario weather satisfaction-based smart building energy scheduling method of claim 1, It is characterized in that The constraints of the smart building model in normal weather include: power balance constraints in normal weather, charging and discharging power constraints of energy storage systems and electric vehicles, power constraints for interaction with the power grid, charge state continuity constraints of energy storage systems and electric vehicle batteries, and lighting load power constraints.

5. According to the multi-scenario weather satisfaction-based smart building energy scheduling method of claim 1, It is characterized in that The constraints of the smart building model for severe weather include: power balance constraints in severe weather, charging and discharging power constraints of energy storage systems and electric vehicles, power constraints for interaction with the grid, charge state continuity constraints of energy storage systems and electric vehicle batteries, and lighting load power constraints.