Optimized scheduling method and device for comprehensive smart energy system, and storage medium

Abstract

The invention relates to the field of new energy, and provides an optimal scheduling method of a comprehensive smart energy system based on fuzzy logic, which comprises the following steps: S1, constructing a scalar function of the cost of the comprehensive energy system, S2, determining an operation target of the comprehensive energy system, and determining an operation boundary condition of the comprehensive energy system according to the operation boundary condition, the boundary condition reflects the operation limitation of the integrated energy system under a specific target; s3, fuzzy logic is adopted to process fluctuation factors in the integrated energy system, the fluctuation factors comprise fluctuation of energy demands, unstable output of renewable energy sources and fluctuation of market prices, and an attribution normal form of the fluctuation factors is established through a fuzzy set method; and S4, calculating an optimal scheduling strategy by using a linear programming optimization algorithm according to the affiliation normal form and the cost scalar function so as to minimize the operation cost of the integrated energy system under the condition of meeting the boundary condition.

Description

Technical Field

[0001] The present invention relates to the field of new energy, and particularly focuses on how to improve the operating efficiency and economic benefits of energy systems through intelligent scheduling means. Background Art

[0002] With the development of economy and the growth of population, the demand for energy is rising. The traditional energy supply mode mainly relies on a single energy system, which can no longer meet the diversified needs of modern energy systems. Therefore, the use of multi-energy complementary methods to aggregate distributed energy has become an effective way to improve energy efficiency and reduce energy consumption costs.

[0003] The Integrated Energy System (IES) optimizes the energy supply structure and improves the reliability and flexibility of energy supply by integrating multiple energy forms such as electricity, heat, and gas. However, when faced with a high proportion of renewable energy such as wind power and solar energy, the volatility and uncertainty of the output of the existing integrated energy system poses a challenge to the stable operation of the system.

[0004] In recent years, although the production of renewable energy has shown rapid growth, the uncertainty brought about by its grid connection has put forward new technical requirements for the demand response scheduling of integrated energy systems. Existing scheduling methods are often unable to fully cope with these uncertainties, resulting in increased system operation risks and reduced economic benefits.

[0005] In order to solve the above problems, various strategies have been proposed in the prior art, such as prediction-based scheduling methods, stochastic optimization, etc. However, these methods often require a large amount of historical data support or have limitations in dealing with uncertainty.

[0006] Based on an in-depth analysis of the prior art, the present invention clearly points out the main problems faced by existing integrated energy demand response scheduling methods: how to achieve integrated energy scheduling with maximum cost-effectiveness and minimum risk under uncertain conditions. Summary of the invention

[0007] In response to these problems, the present invention proposes an optimization scheduling method and device for an integrated smart energy system based on fuzzy logic to achieve optimal scheduling under an uncertain environment.

[0008] In one embodiment of the present application, a method for optimizing the scheduling of an integrated smart energy system based on fuzzy logic is proposed, comprising:

[0009] S1. The cost function of building an integrated energy system.

[0010] Optionally, the target amount function is:

[0011]

[0012] TC(t) represents the total energy cost at time t;

[0013] C e (t) represents the energy consumption cost at time t;

[0014] C s (t) represents the energy storage system cost at time t;

[0015] C d (t) represents the demand response cost at time t;

[0016] C c (t) represents the carbon emission cost at time t;

[0017] p(t) represents the electricity price at time t;

[0018] P e (t) represents the power consumption of the power grid at time t;

[0019] p w (t) represents the wind power price at time t;

[0020] P w (t) represents the wind power generation at time t;

[0021] p g (t) represents the gas price at time t;

[0022] G(t) represents the gas consumption at time t;

[0023] p b (t) represents the electricity storage price;

[0024] P ch P(t) and Pdis(t) represent the storage power and discharge power at time t, respectively;

[0025] p h (t) represents the heat storage price;

[0026] H ch (t) and H dis (t) represents the heat storage power and heat release power at time t respectively;

[0027] α represents the demand response compensation coefficient;

[0028] Pd _out (t) and Pd _in (t) represents the cut-out power and cut-in power at time t respectively;

[0029] η e , ηh and η g P e (t), H ch (t) and carbon emission factors of G(t);

[0030] P chp (t) represents the CHP gas power consumption at time t;

[0031] P boiler (t) represents the gas power consumed by the gas boiler at time t;

[0032] λ is the penalty coefficient;

[0033] N s is the number of energy storage systems;

[0034] N f is the number of emission sources;

[0035] η i is the carbon emission coefficient of the ith emission source;

[0036] F i (t) is the emission of the ith emission source at time t;

[0037] F i ref (t) is the reference emission of the ith emission source at time t;

[0038] δ is half the length of the time window and represents the width of the time smoothing window;

[0039] τ is the time lag parameter, representing the time delay of cost calculation;

[0040] η s (t) and η d (t) are the cost weight functions of energy storage system and demand response, respectively, reflecting how the weight of cost calculation changes over time;

[0041] S2. setting the operation target of the integrated energy system, and determining the operation boundary conditions of the integrated energy system accordingly, wherein the boundary conditions reflect the operation limitations of the integrated energy system under specific targets;

[0042] S3. Using fuzzy logic to process the volatility factors in the integrated energy system, the volatility factors include fluctuations in energy demand, unstable output of renewable energy, and market price fluctuations, and establishing an attribution paradigm for the volatility factors through a fuzzy set method;

[0043] S4. Using a linear programming optimization algorithm, the optimal scheduling strategy is calculated according to the attribution paradigm and the cost quota function to minimize the operating cost of the integrated energy system while satisfying the boundary conditions.

[0044] 1. Energy consumption cost Ce(t): In the calculation of energy consumption cost, this application uses the logarithmic function ln(1+P e (t″)-α·P d_out (t″)-β·P d_in (t″)) 2 ), which can smooth the difference between actual electricity consumption and demand response reduction and prevent instability caused by extreme values ​​in the calculation process.

[0045] 2. Energy storage system cost Cs(t): Similarly, in the calculation of energy storage system cost, this application also uses the logarithmic function ln(1+(P ch，i (t″)-P dis，i (t″)) 2 ), which can smooth the difference between the charge and discharge of the energy storage system and help optimize the scheduling strategy of the energy storage system.

[0046] 3. Demand response cost Cd(t): The logarithmic function ln(1+(P d_put (t″)-P d_in (t″)) 2 ), which can smooth the difference between demand response reduction and demand response increase, helping to improve the flexibility of the dispatch strategy.

[0047] 4. Carbon emission cost Cc(t): In the calculation of carbon emission cost, this application also uses a logarithmic function This smooths the difference between actual and reference emissions, helping to optimize the calculation of carbon emission costs.

[0048] In some alternative embodiments, the target amount function may also be defined as:

[0049] in,

[0050]

[0051] Alternatively, the energy requirement is assigned to the form μE demand Defined as:

[0052]

[0053] Where E actual is the actual energy requirement, Elow and E high The preset low and high energy demand thresholds are

[0054] The wind power attribution paradigm μP wind Defined as:

[0055]

[0056] Where P wind is the wind power output, P rated is the rated output of the wind turbine, σP wind is the standard deviation of wind power output;

[0057] The electricity price attribution paradigm μC price Defined as:

[0058]

[0059] Among them C price is the electricity price, C base is the basic electricity price, α is the electricity price adjustment coefficient, and

[0060] The operating cost attribution paradigm μC operation Defined as:

[0061]

[0062] Among them C operation is the operating cost, C max and C min are the maximum and minimum values ​​of operating costs, respectively; and,

[0063] The attribution paradigm also includes a demand response attribution paradigm μR response , defined as:

[0064]

[0065] Where R is the demand response amount, R threshold is the threshold of demand response;

[0066] The attribution paradigm also includes the energy storage cost attribution paradigm μC storage , defined as:

[0067]

[0068] Among them, C storage is the energy storage cost, β is the regulation slope, C threshold is the threshold of energy storage cost.

[0069] Optionally, the step S1 further includes: S1-1. establishing a target amount function of a comprehensive energy demand response scheduling energy cost, the target amount function is a multi-target amount function, consisting of energy consumption cost, energy storage cost, demand response cost and carbon emission cost;

[0070] The step S2 further includes: S2-1. determining the target boundary conditions according to the preset target quantity and the integrated energy system demand response scheduling value;

[0071] The step S3 also includes: S3-1. Using fuzzy set method to model the uncertainties of the input parameters of the integrated energy system, including energy demand, wind power, electricity price and operating cost, to obtain the target attribution paradigm.

[0072] Optionally, in some embodiments, the optimization scheduling method of the integrated smart energy system based on fuzzy logic, wherein the fuzzy set method includes:

[0073] Define fuzzy sets and attribution paradigms to quantify the uncertainty of input parameters;

[0074] Modeling the uncertainty of energy demand, wind power output, electricity price fluctuations, and operating cost changes using the attribution paradigm; and,

[0075] The target amount function is defined by the following formula:

[0076] TC=∑ t (C energy (t)·P grid (t)C storage (t)·(P charge (t)+P discharge (t))+C response (t)·(P cut (t)+P regain (t))+C emission (t)·E total (t))

[0077] Where E total (t) Total energy consumption including electricity, wind power and gas;

[0078] Target boundary conditions include, but are not limited to, energy balance, grid operation constraints, gas grid constraints, and wind power constraints;

[0079] The energy demand attribution paradigm is defined based on the following formula

[0080]

[0081] Where E is the actual demand, E 0 is the baseline demand;

[0082] The wind power attribution paradigm is defined based on the following formula:

[0083]

[0084] Where P is the wind power output, P min and P max are the minimum and maximum power output respectively.

[0085] The electricity price attribution paradigm is defined based on the following formula:

[0086]

[0087] Where C is the electricity price, C avg is the average electricity price, σ C is the standard deviation of electricity prices

[0088] The operating cost attribution paradigm is defined based on the following formula:

[0089]

[0090] Where C is the operating cost, C min and C max are the minimum and maximum costs respectively.

[0091] Optionally, in some embodiments,

[0092] The target attribution paradigm includes:

[0093] The energy demand attribution paradigm Jdemand is defined as:

[0094] J demand (D elec , D heat , D gas )=w elec ·μ elec (D elec )+w heat ·μ heat (D heat )+w gas ·μ gas (D gas )

[0095] Among them, D elec , D heat and D gas Represent the demand for electricity, heat and gas respectively, μ represents the attribution paradigm, and w represents the weight coefficient of the corresponding energy type;

[0096] Wind power ownership paradigm J wind , defined as:

[0097]

[0098] Among them, G represents the actual wind power, G rated Indicates the rated power generation of the wind turbine, k wind is the shape parameter, controlling the sensitivity of the attribution paradigm;

[0099] Electricity price attribution paradigm price , defined as:

[0100]

[0101] Among them, P represents the electricity price, P avg represents the average value of electricity price, σ price represents the standard deviation of electricity prices;

[0102] Operating cost attribution paradigm J cost , defined as:

[0103]

[0104] Where C represents the total operating cost, C min and C max denote the minimum and maximum thresholds of the cost, respectively, and n is a shape parameter used to adjust the shape of the attribution paradigm.

[0105] Optionally, in some embodiments, step S3 further comprises:

[0106] In the demand response dispatch of integrated energy systems, the fuzzy set method is used to model the uncertainty of input parameters in order to capture and express the fuzziness and uncertainty of these parameters.

[0107] Optionally, in some embodiments, the step S4 further includes: S4-1. solving the target amount function based on i) a nonlinear programming solver or a linear programming solver and ii) a target attribution paradigm to determine an optimal scheduling method for the integrated energy system;

[0108] Among them, the minimum membership decision variable z is defined as the minimum value of all belonging paradigms;

[0109] The boundary conditions of the minimum membership degree z include that the values ​​of all belonging paradigms are greater than or equal to z;

[0110] The linear programming solver takes into account all parameters including but not limited to the target amount function, boundary conditions and attribution paradigm;

[0111] The boundary condition of the minimum membership decision variable z is the minimum value of all belonging paradigms:

[0112]

[0113] Optionally, in some embodiments, the energy demand is assigned in the form of μE demand Defined as:

[0114]

[0115] Where E actual is the actual energy requirement, El ow and E high are the preset low and high energy demand thresholds, respectively;

[0116] The wind power attribution paradigm μP wind Defined as:

[0117]

[0118] Where P wind is the wind power output, P rated is the rated output of the wind turbine, σP wind is the standard deviation of wind power output;

[0119] The electricity price attribution paradigm μC price Defined as:

[0120]

[0121] Among them C price is the electricity price, C base is the basic electricity price, α is the electricity price adjustment coefficient, and

[0122] The operating cost attribution paradigm μC operation Defined as:

[0123]

[0124] Among them C operation is the operating cost, C max and C min are the maximum and minimum values ​​of operating costs, respectively; and,

[0125] The attribution paradigm also includes a demand response attribution paradigm μR response , defined as:

[0126]

[0127] Where R is the demand response amount, R threshold is the threshold of demand response;

[0128] The attribution paradigm also includes the energy storage cost attribution paradigm μC storage , defined as:

[0129]

[0130] Among them, C storage is the energy storage cost, β is the regulation slope, C threshold is the threshold of energy storage cost.

[0131] Optionally, in some embodiments,

[0132] 7.

[0134] p(t) represents the electricity price at time t;

[0135] P e (t) represents the power consumption of the power grid at time t;

[0136] p w (t) represents the wind power price at time t;

[0137] P w (t) represents the wind power generation at time t;

[0138] p g (t) represents the gas price at time t;

[0139] G(t) represents the gas consumption at time t;

[0140] p b (t) represents the electricity storage price;

[0141] P ch P(t) and Pdis(t) represent the storage power and discharge power at time t, respectively;

[0142] p h (t) represents the heat storage price;

[0143] H ch (t) and H dis (t) represents the heat storage power and heat release power at time t respectively;

[0144] α represents the demand response compensation coefficient;

[0145] Pd _out (t) and Pd _in (t) represents the cut-out power and cut-in power at time t respectively;

[0146] η e , η h and η g P e (t), H ch (t) and carbon emission factors of G(t);

[0147] P chp(t) represents the CHP gas power consumption at time t;

[0148] P boiler (t) represents the gas power consumed by the gas boiler at time t;

[0149] λ is the penalty coefficient;

[0150] N s is the number of energy storage systems;

[0151] N f is the number of emission sources;

[0152] η i is the carbon emission coefficient of the ith emission source;

[0153] F i (t) is the emission of the ith emission source at time t;

[0154] F i ref (t) is the reference emission of the ith emission source at time t;

[0155] δ is half the length of the time window and represents the width of the time smoothing window;

[0156] τ is the time lag parameter, representing the time delay of cost calculation;

[0157] η s (t) and η d (t) are the cost weight functions of energy storage system and demand response, respectively, reflecting the changes in the weight of cost calculation over time.

[0158] In addition, some embodiments of the present application also provide an electronic device, including a processor, which is operable to execute the optimization scheduling method of the integrated smart energy system based on fuzzy logic of any other embodiment.

[0159] In addition, some embodiments of the present application also provide an electronic device, including a processor and a non-volatile storage medium, storing a program that can be activated to execute the optimization scheduling method of the integrated smart energy system based on fuzzy logic of any other embodiment.

[0160] Technical Effects

[0161] By using logarithmic functions, we can better handle the uncertainty in actual operation and improve the robustness and flexibility of scheduling strategies. By using logarithmic functions to smooth the differences in various cost calculations, we can more accurately optimize costs and improve resource utilization. By using logarithmic functions to smooth various uncertain factors, we can enhance the adaptability and stability of the system. By using logarithmic functions to smooth the differences in various cost calculations, we can improve the reliability of decision-making and ensure the stability and reliability of the system under uncertain environments. By using logarithmic functions to smooth the differences in various cost calculations, we can support more refined energy management and scheduling strategies.

[0162] The optimization scheduling method with these mathematical expressions in this application helps to more deeply understand the cost calculation method in the integrated energy demand response scheduling method, and can more finely adjust various parameters in the cost calculation to achieve a better scheduling strategy. It should be noted that the parameters and functions in these formulas need to be appropriately selected and adjusted according to actual conditions.

[0163] Furthermore, in some preferred embodiments, the energy cost Ce(t): In the calculation of the energy cost, the present application uses the logarithmic function ln(1+(P e (t″)-α·P d_out (t″)-β·P d_in (t″)) 2 ), which can smooth the difference between actual electricity consumption and demand response reduction and prevent instability caused by extreme values ​​in the calculation process.

[0164] Furthermore, in some preferred embodiments, in calculating the cost of the energy storage system, the present application also uses the logarithmic function ln(1+(P ch，i (t″)-P dis，i (t″)) 2 ), which can smooth the difference between the charge and discharge of the energy storage system and help optimize the scheduling strategy of the energy storage system.

[0165] Furthermore, in some preferred embodiments, the logarithmic function ln(1+(P d_out (t″)-P d_in (t″)) 2 ), which can smooth the difference between demand response reduction and demand response increase, helping to improve the flexibility of the dispatch strategy.

[0166] Furthermore, in some preferred embodiments, in the calculation of carbon emission costs, the present application also uses a logarithmic function This smooths the difference between actual and reference emissions, helping to optimize the calculation of carbon emission costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0167] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0168] Figure 1 A flowchart showing an optimization scheduling method for an integrated smart energy system based on fuzzy logic according to an embodiment of the present application is shown;

[0169] Figure 2 A schematic diagram of the structure of an optimization scheduling device for an integrated smart energy system based on fuzzy logic according to an embodiment of the present application is shown;

[0170] Figure 3 A schematic diagram showing the structure of a computing device according to an embodiment of the present application is shown;

[0171] Figure 4 A functional block diagram of an optimization scheduling device for an integrated smart energy system based on fuzzy logic according to an embodiment is shown.

[0172] In the description of the drawings, the same, similar or corresponding reference numerals represent the same, similar or corresponding units, elements or functions. DETAILED DESCRIPTION

[0173] Reference will now be made in detail to the embodiments, examples of which are illustrated in the accompanying drawings. In the detailed description that follows, many specific details are set forth in order to provide a full understanding of the various described embodiments. However, it will be apparent to one of ordinary skill in the art that the various described embodiments may be practiced without these specific details. In other cases, well-known methods, processes, components, circuits, and networks are not described in detail, thereby not unnecessarily obscuring various aspects of the embodiments.

[0174] The terms used in the description of the various embodiments described herein are only for the purpose of describing specific embodiments, and are not intended to be limiting. As used in the description of the various embodiments described and in the appended claims, the singular forms "a", "an" and "the" are intended to also include plural forms, unless the context clearly indicates otherwise. It will also be understood that the term "and / or" used herein refers to and encompasses any and all possible combinations of one or more items in the items listed in association. It will also be understood that the term "includes", "including", "comprises" and / or "comprising" when used in this specification specifies the presence of stated features, integers, steps, operations, elements and / or parts, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or their groupings.

[0175] Depending on the context, the word "through" as used in this application may be interpreted as "by", "by virtue of" or "by means of". Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determination" or "in response to detection". Similarly, depending on the context, "when..." or "when..." in some embodiments may also be interpreted as conditional assumptions such as "if", "such as". Similarly, depending on the context, the phrases "if (stated condition or event)", "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when determined" or "in response to determination" or "when detecting (stated condition or event)". Similarly, depending on the context, the phrases "in response to (stated condition or event)" in some embodiments may be interpreted as "in response to detecting (stated condition or event)" or "in response to detecting (stated condition or event)".

[0176] It should be understood that although the terms first, second, third, etc. may be used in the present disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, the first may also be referred to as the second, and vice versa, without departing from the scope of the present disclosure. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0177] The integrated energy system uses combined heat and power (CHP) technology to achieve efficient conversion of electricity and gas into thermal energy. The advantage of CHP technology is that it can generate electricity and thermal energy simultaneously, greatly improving energy utilization efficiency. This technology effectively meets the needs of energy diversification, provides thermal energy for industry, buildings and residential areas, and enhances the flexibility and efficiency of energy use.

[0178] To ensure the efficient operation of the integrated energy system, energy storage technology is integrated into the system design, which includes both electrical energy storage and thermal energy storage. During periods of low electricity demand, the system stores electrical energy and releases it during peak periods to adjust the fluctuations between electricity supply and demand. Similarly, through thermal energy storage technology, the system can store surplus thermal energy and use it during peak demand to meet peak thermal energy demand.

[0179] The energy demand faced by the integrated energy system is multi-dimensional, covering multiple aspects such as electricity, heat and gas. Among them, electricity demand occupies a dominant position and is mainly used to meet daily electricity consumption. Heat demand involves building heating and industrial heating. As for gas, its main use is as a fuel supply for the CHP system. Through this comprehensive management, the system can achieve optimal configuration and efficient use of energy.

[0180] The present application is further described below by way of examples, but the present application is not limited to the scope of the examples.

[0181] The definition of the electricity price attribution paradigm μCprice can be refined according to a specific application scenario. Figure 1 Some embodiments of the present application and their effects are described in detail, including specific numerical calculations:

[0182] Embodiment 1:

[0183] Description of Application Scenario A: Assume that an integrated energy system operator needs to adjust its energy purchasing and allocation strategy based on real-time electricity prices. The operator faces electricity price fluctuations, especially between peak and off-peak hours. The electricity price attribution paradigm is used to evaluate the impact of different electricity price levels on operating costs and help make purchasing decisions.

[0184] Specific values:

[0185] Basic electricity price C base : Set at 100 yuan / MWh as a reference point for the average market electricity price.

[0186] Electricity price adjustment coefficient α: set to 20, used to adjust the sensitivity of the attribution paradigm.

[0187] Real-time electricity price Cprice : It may reach 150 yuan / MWh during peak hours and as low as 70 yuan / MWh during off-peak hours.

[0188] Attribution paradigm calculation: During peak hours, the electricity price is 150 yuan / MWh:

[0189]

[0190] The value of the electricity price attribution paradigm is 0.0385, which indicates that the electricity price is high during peak hours and it may not be appropriate to purchase large amounts of electricity.

[0191] During off-peak hours, the electricity price is 70 yuan / MWh:

[0192]

[0193] The value of the electricity price attribution paradigm is also 0.0385, but here it represents a lower electricity price, at which the operator may choose to increase electricity purchases.

[0194] Decision Making:

[0195] When μC price <0.5μ Cprice When <0.5, it indicates that the electricity price is too high or too low, and the operator may need to adjust its energy purchasing strategy, such as reducing the purchase amount or looking for alternative energy sources.

[0196] When 0.5≤μCprice≤1, the electricity price is in a reasonable range, and operators may choose to purchase normally or increase the purchase volume.

[0197] Technical effects:

[0198] Through this refined attribution paradigm calculation, integrated energy system operators can more accurately evaluate the impact of different electricity price levels on operating costs, thereby making more reasonable energy purchasing and scheduling decisions, effectively reducing operating costs and improving energy utilization efficiency.

[0199] It should be understood that this is only an exemplary embodiment, and in actual applications, the parameters and thresholds of the electricity price attribution paradigm may need to be adjusted according to specific market conditions and operation strategies.

[0200] Description of application scenario B:

[0201] Suppose an integrated energy system (such as a smart building or industrial park) needs to optimize its energy demand response based on real-time data and forecast models. The system operator wants to minimize operating costs while ensuring the stability of energy supply and taking into account the uncertainty of renewable energy.

[0202] Embodiment 2:

[0203] Minimum membership decision variable z:

[0204] · Set the target attribution paradigm as the attribution paradigm of energy demand, wind power, electricity price and operating cost.

[0205] Suppose at a certain point in time, the values ​​of these attribution paradigms are: μE demand =0.8,μP wind =0.7,μC price =0.9,μC operation =0.6.

[0206] Calculate the minimum membership z: z = min (0.8, 0.7, 0.9, 0.6) = 0.6

[0207] -Energy demand attribution paradigm μE demand :

[0208] Set the actual energy requirement E actual =500MWh, low threshold E low =400MWh, high threshold E high =600MWh.

[0209] Calculate membership:

[0210] - Wind power ownership paradigm μP wind :

[0211] Set wind power output P wind =300kW, rated output P rated =500kW, standard deviation σP wind =50kW.

[0212] Calculate membership:

[0213] Electricity price attribution paradigm μC price :

[0214] Set real-time electricity prices C price =120 yuan / MWh, basic electricity price C base =100 yuan / MWh, adjustment coefficient α=10 yuan / MWh.

[0215] Calculate membership:

[0216]

[0217] Operation cost attribution paradigm μC operation :

[0218] Set operating costs C operation =20000, the maximum cost Cmax =30,000 yuan, minimum value C min =10,000 yuan.

[0219] Calculate membership:

[0220] Technical effects:

[0221] Through these specific attribution paradigm calculations, integrated energy system operators can dynamically adjust energy purchase, distribution and storage strategies based on real-time data and affiliation evaluation. This helps to minimize operating costs while ensuring energy supply stability, taking into account the uncertainty of renewable energy, and improving the economic benefits and environmental friendliness of the entire system.

[0222] It should be understood that these embodiments and numerical calculations are only examples and may need to be adjusted according to specific system parameters and market conditions in actual applications.

[0223] Application scenario description:

[0224] Assume that an integrated energy system operator is responsible for managing the energy consumption of a large commercial building. The operator needs to evaluate the degree of subordination under different operating costs in order to optimize energy use and reduce costs while maintaining service quality. Specific embodiment 3:

[0226] Operation cost attribution paradigm μC operation is defined as:

[0227]

[0228] C operation is the current operating cost.

[0229] ·C min It is the minimum value of operating cost, which is set at 20,000 yuan.

[0230] ·C max It is the maximum value of operating cost, which is set at 50,000 yuan.

[0231] Specific numerical calculation:

[0232] 1. Assume the current operating cost C operation For 30,000 yuan, calculate the membership degree:

[0233]

[0234] This means that at the current cost, the degree of membership is 0.25, indicating that the operating cost is at a medium level.

[0235] 2. If the operating cost is reduced to 25,000 yuan, recalculate the membership:

[0236]

[0237] This shows that after the operating cost is reduced, the membership does not change and remains at 0.25.

[0238] 3. If the operating cost is further reduced to C operation 10,000 yuan (close to C min ), calculate the membership:

[0239]

[0240] This indicates that the operating cost has reached its minimum value, and the degree of membership is 0, indicating that the operating cost is very low.

[0241] Technical effects:

[0242] Through this attribution paradigm calculation, operators can quantify the position of operating costs relative to the optimal cost range. The membership value can help operators identify potential opportunities for cost reduction and take measures to optimize operating strategies to maximize cost effectiveness.

[0243] It should be understood that this embodiment is intended to illustrate how to apply the attribution paradigm to practical problems, and specific values ​​and parameters may need to be adjusted according to actual conditions.

[0244] This application envisions a specific application scenario, which involves the energy storage cost attribution paradigm μC storage The following is an example, including specific numerical calculations:

[0245] Application scenario description:

[0246] Assume that an integrated energy system operator is responsible for managing a smart grid equipped with a battery energy storage system. The operator needs to adjust the charging and discharging strategy of the energy storage system according to the energy storage cost to optimize the overall energy cost and improve the system operation efficiency. Specific embodiment 4:

[0248] Energy storage cost attribution paradigm μC storage is defined as:

[0249]

[0250] in:

[0251] ·C storage is the current energy storage cost.

[0252] ·C thresholdis the threshold for energy storage costs, set at the average cost plus a safety margin.

[0253] β is the modulation slope, which controls the sensitivity of the attribution paradigm.

[0254] Specific numerical calculation:

[0255] 1. Assume the current energy storage cost C storage The threshold is C120 / MWh. threshold It is set to 100 yuan / MWh, and the adjustment slope β is set to 0.1 / MWh. This means that at current costs, the membership is 0.135, indicating that the cost of energy storage is slightly above the threshold and operators may need to consider reducing energy storage use or looking for lower-cost energy storage solutions.

[0256] 2. If the energy storage cost is reduced to C storage It is 80 yuan / MWh, and the membership is recalculated:

[0257]

[0258] This indicates that after the storage cost decreases, the membership increases to 0.864, and operators can increase storage usage to take advantage of the lower storage cost.

[0259] 3. If the energy storage cost changes further, for example, increases to C storage The price is 140 yuan / MWh, and the membership is calculated as follows:

[0260]

[0261] This indicates that the energy storage cost is significantly higher than the threshold, with the membership reduced to 0.018, and operators may need to avoid using energy storage systems to reduce costs.

[0262] Technical effects:

[0263] Through the calculation of this attribution paradigm, operators can flexibly adjust energy storage strategies according to real-time changes in energy storage costs, optimize energy costs, and improve the economy and efficiency of the energy system.

[0264] It should be understood that this embodiment is intended to illustrate how to apply the attribution paradigm to practical problems, and specific values ​​and parameters may need to be adjusted according to actual conditions.

[0265] This application constructs another specific application scenario, which involves the demand response attribution paradigm μ Rresponse The following is an example, including specific numerical calculations:

[0266] Application scenario description:

[0267] Assume that an electricity market operator needs to adjust its energy allocation strategy based on demand response events on the grid. Demand response events allow electricity consumers to reduce electricity consumption when electricity prices are high in exchange for certain compensation. The operator needs to evaluate the membership under different demand response amounts to determine their contribution to grid stability and economy. Specific embodiment 5:

[0269] Demand Response Attribution Paradigm μR response is defined as:

[0270]

[0271] in:

[0272] R is the demand response amount, which is the amount of electricity consumption reduced by consumers during a demand response event.

[0273] ·R threshold It is the threshold of demand response. Consumers can only receive compensation when the demand response amount reaches or exceeds this threshold.

[0274] Specific numerical calculation:

[0275] 1. Assume that in a demand response event, the actual demand response amount R of the consumer is 500MWh and the threshold R threshold Set to 300MWh. μR response (500)=1 This means that the consumer's demand response volume exceeds the threshold, and therefore compensation can be obtained.

[0276] 2. If another consumer’s DR is 200MWh, and the threshold remains the same: μR response (200) = 0 This indicates that the consumer's demand response volume does not reach the threshold and therefore cannot be compensated.

[0277] 3. If the threshold is raised to R threshold 600MWh, while the consumer's demand response is still 500MWh: μR response (500)=0 This indicates that under the new threshold, the consumer's demand response volume no longer meets the conditions for compensation.

[0278] Technical effects:

[0279] Through this attribution paradigm calculation, electricity market operators can clearly identify which demand response volumes are effective and provide consumers with corresponding compensation accordingly. This approach helps incentivize consumers to participate in demand response programs, thereby improving the flexibility and stability of the grid while reducing the load pressure on the grid during peak hours.

[0280] It should be understood that this embodiment is intended to illustrate how to apply the attribution paradigm to practical problems, and specific values ​​and parameters may need to be adjusted according to actual conditions.

[0281] This application constructs another specific application scenario, which involves defining a new decision variable z as the calculation of the minimum membership of the target attribution paradigm. The following is an embodiment, including specific numerical calculations:

[0282] Application scenario description:

[0283] Assume that a smart grid operator needs to optimize dispatch among multiple energy inputs (such as wind, solar, gas, and electricity market purchases) to minimize total cost and meet demand response. The operator uses fuzzy logic to handle the uncertainty of these inputs and defines a minimum membership decision variable z to ensure that the worst performance of the dispatch scheme among all membership paradigms is still acceptable. Specific embodiment 6:

[0285] The goal attribution paradigm includes:

[0286] Energy demand attribution paradigm μE demand

[0287] Wind power ownership paradigm μP wind

[0288] ·Electricity price attribution paradigm μC price

[0289] ·Operation cost attribution paradigm μC operation

[0290] Specific numerical calculation:

[0291] 1. Energy demand attribution paradigm μEdemandμE demand :Assume the predicted energy demand is E demand = 1000 kWh, the attribution paradigm is based on the deviation of demand from the historical average demand. If the historical average demand is E avg =800kWh, then:

[0292]

[0293] Assumption E scale =200kWh, then:

[0294]

[0295] 2. Wind power ownership paradigm μP wind :

[0296] Assume that wind power forecast is P wind=500kWh, the attribution paradigm is based on the ratio of wind power to the maximum generating capacity. If the maximum capacity is P mas =600kWh, then:

[0297] 3. Electricity price attribution paradigm μC price :

[0298] Assume that the current electricity price is C price =0.15$ / kWh, the attribution paradigm is based on the comparison of the electricity price with the average electricity price. If the average electricity price is C avg =0.10$ / kWh, then:

[0299] 4. Operation cost attribution paradigm μC operation :Assuming the estimated operating cost is

[0300] C operation = 5000$, the attribution paradigm is based on the comparison of cost with budget. If the budget is B budget =6000$, then:

[0301]

[0302] 5. Minimum membership decision variable z: According to the calculation results of the above attribution paradigm, z is defined as the minimum membership:

[0303]

[0304] z=min(0,0.8333,0.6667,0.1667)=0

[0305] Technical effects:

[0306] By calculating the minimum membership z, the operator identifies that under the current circumstances, the energy demand has the lowest membership, indicating that there may be a risk of insufficient supply. This prompts the operator to take measures, such as increasing energy storage release, adjusting demand-side management strategies, or purchasing additional power resources to ensure that demand is met and the system remains stable.

[0307] It should be understood that this embodiment is intended to illustrate how to apply the attribution paradigm to practical problems, and specific values ​​and parameters may need to be adjusted according to actual conditions.

[0308] The following is an example of a specific application scenario, including detailed numerical calculations:

[0309] Application scenario description:

[0310] Consider an energy management system for a smart city, which needs to optimize energy distribution based on real-time energy demand and supply. The uncertainty of energy demand is a key factor in system optimization. System operators use fuzzy set methods to evaluate energy demand in different time periods and adjust energy supply strategies accordingly. Specific embodiment 7:

[0312] Energy demand attribution paradigm μE demand is defined as:

[0313]

[0314] in:

[0315] E is the predicted energy demand.

[0316] ·E low This is the lowest energy demand in historical data.

[0317] ·E high This is the highest energy demand in historical data.

[0318] Specific numerical calculation:

[0319] 1. Assume that historical data shows the minimum energy demand E low The maximum energy demand is 50MW. high It is 150MW.

[0320] 2. During a specific peak period, the predicted energy demand E is 100MW.

[0321] 3. According to the above attribution paradigm, calculate the energy demand attribution degree during the peak period:

[0322]

[0323] 4. This membership value indicates that the current predicted energy demand is in the middle of the historical minimum and maximum demand.

[0324] 5. If in another off-peak period, the predicted energy demand EE drops to 70MW, recalculate the membership:

[0325]

[0326] 6. This membership value is higher, indicating that the predicted energy demand is closer to the historical maximum demand, but still within the acceptable range.

[0327] Technical effects:

[0328] By calculating the energy demand membership in different time periods, the energy management system of a smart city can more accurately assess the security and reliability of energy supply. This helps system operators make more reasonable energy dispatch decisions, such as increasing energy supply or launching demand response programs during periods of high energy demand to ensure that energy supply meets demand and optimizes costs.

[0329] It should be understood that this embodiment is intended to illustrate how to apply the attribution paradigm to practical problems, and specific values ​​and parameters may need to be adjusted according to actual conditions.

[0330] This application assumes a specific application scenario, such as an integrated energy management system of a smart grid, which needs to optimize its energy distribution and cost-effectiveness. The following is an example, including specific numerical calculations:

[0331] Application scenario description:

[0332] A smart grid operator manages an integrated energy system consisting of wind power, solar power, energy storage, and grid purchases. The operator needs to develop a dispatch plan to minimize the total operating cost within a day while meeting energy demand and considering carbon emission costs. Specific embodiment 8:

[0334] The target amount function includes the following formula:

[0335] TC=∑ t＝1 T (C energy (t)·P grid (t)+C storage (t)·(P charge (t)+P discharge (t))+C response (t)·(P cut (t)+P regain (t))+C emission (t)·E total (t))

[0336] in:

[0337] T is the total number of time periods considered, such as 24 hours in a day.

[0338] ·C energy (t) is the electricity price at time t.

[0339] ·P grid (t) is the amount of electricity purchased from the grid at time t.

[0340] ·C storage (t) is the energy storage cost at time t.

[0341] ·P charge (t) and P discharge (t) are the energy storage charging and discharging powers at time t, respectively.

[0342] ·C response (t) is the demand response cost at time t.

[0343] ·P cut (t) and P regain (t) are the demand response cut-out and cut-in powers at time t, respectively.

[0344] ·C emission (t) is the carbon emission cost at time t.

[0345] ·E total (t) is the total energy consumption at time t.

[0346] Specific numerical calculation:

[0347] 1. Assume that at time t = 1 (i.e. the first hour), the electricity price C energy (1) = $0.10 / kWh, the amount of electricity purchased from the grid P grid (1) = 1000 kWh.

[0348] 2. Energy storage cost C storage (1) = 0.05 USD / kWh, energy storage charging power P charge (1) = 200 kWh, discharge power P discharge (1) = 150 kWh.

[0349] 3. Demand response cost C response (1) = $20 / MW, demand response cut-out power P cut (1) = 50MW, cut-in power P regain (1) = 25MW.

[0350] 4. Carbon emission cost C emission (1) = 5 USD / ton, total energy consumption E total (1) = 1500 kWh (assuming that each kWh corresponds to 0.9 kg of carbon dioxide emissions).

[0351] 5. Calculate the total cost TC1 of the first hour: TC1 = 0.10 × 1000 + 0.05 × (200 + 150) + 20 × (50 + 25) + 5 × (1500 × 0.9)

[0352] TC1=100+25+1500+3375

[0353] TC1 = $5,000

[0354] Technical effects:

[0355] With this detailed cost calculation, smart grid operators can identify the most cost-effective energy dispatch strategies and optimize the scheduling of energy purchases, storage usage, and demand response events to minimize costs and maximize efficiency.

[0356] It should be understood that this embodiment is intended to illustrate how to apply the target amount function to practical problems, and the specific values ​​and parameters may need to be adjusted according to actual conditions.

[0357] This application assumes a specific application scenario, such as an operator of an integrated energy system who wants to optimize its daily operations to minimize energy costs and take into account environmental impact. The following is an example, including specific numerical calculations:

[0358] Application scenario description:

[0359] An integrated energy system operator manages a system that includes wind power, solar power, gas power and grid-purchased power. The system is also equipped with energy storage equipment and participates in demand response.

[0360] The following is an example of a specific application scenario involving an energy management system for a smart building that needs to optimize its energy consumption in response to demand response signals from the grid and consider the use of energy storage devices. This example includes specific numerical calculations:

[0361] Application scenario description:

[0362] A smart building is equipped with rooftop solar power generation, wind power generation, energy storage battery systems, and controllable loads (such as HVAC systems and lighting). Building managers hope to participate in the grid's demand response program to reduce energy costs by adjusting energy use and the charging and discharging strategies of energy storage equipment, and obtain compensation for demand response. Specific embodiment 9:

[0364] The target amount function includes the following formula:

[0365] TC=∑ t＝1 T (C grid (t)·P grid (t)+C storage (t)·(P charge (t)+P discharge (t))+C response (t)·(P cut (t)+P regain (t))+C emission (t)·E emission (t))

[0366] The new decision variable z is introduced as the minimum membership of the target attribution paradigm:

[0367] z=min(μE demand (t),μP wind (t),μC price (t),μC operation (t))

[0368] The boundary conditions for minimum membership include:

[0369] z≤μE demand (t)

[0370] z≤μP wind (t)

[0371] z≤μC price (t)

[0372] z≤μC operation (t)

[0373] Specific numerical calculation:

[0374] 1. At time t = 1 (i.e. a certain hour), the grid electricity price C grid (1) = $0.08 / kWh, the amount of electricity purchased by the building from the grid P grid (1) = 500 kWh.

[0375] 2. Energy storage cost C storage (1) = 0.02 = 0.02 USD / kWh, energy storage charging power P charge (1) = 100 kWh, discharge power P discharge (1) = 80 kWh.

[0376] 3. Demand response cost C response (1) = $5 / kW, the power P reduced by the building during a demand response event cut (1) = 50kW, the recovered power P regain (1) = 25kW.

[0377] 4. Carbon emission cost C emission (1) = $10 / ton, carbon emissions from building gas-fired power generation E emission (1) = 200 kg.

[0378] 5. Assume that the value of the attribution paradigm is:

[0379] ομE demand (1) = 0.9

[0380] ομP wind (1) = 0.85

[0381] ομC price (1) = 0.75

[0382] ομC operation (1) = 0.65

[0383] 6. Calculate the minimum membership z:

[0384] z=min(0.9,0.85,0.75,0.65)=0.65

[0385] 7. Calculate the total cost for that hour based on the membership and cost

[0386] TC1=0.08×500+0.02×(100+80)+5×(50+25)+10×200

[0387] TC1=40+4+375+2000

[0388] TC1 = $2409

[0389] Technical effects:

[0390] Through this optimized scheduling method, smart buildings can reduce energy costs and improve economic benefits while ensuring the stability of energy supply, and ensure the feasibility of scheduling plans under uncertain conditions through the constraint of minimum membership.

[0391] It should be understood that this embodiment is intended to illustrate how to apply the target amount function and the minimum membership decision variable to actual problems, and the specific values ​​and parameters may need to be adjusted according to actual conditions.

[0392] This application may assume a specific application scenario, such as an integrated energy management system for an industrial park, which needs to optimize energy costs and reduce carbon footprint while ensuring production stability. The following is an example, including specific numerical calculations:

[0393] Application scenario description:

[0394] An integrated energy management system for an industrial park that combines wind power, solar power, energy storage equipment, and grid power to meet the park's energy needs. The system operator hopes to optimize energy procurement and use based on changes in energy prices and demand at different times of the day. Specific embodiment 10:

[0396] The target amount function includes the following formula:

[0397] TC=∑ t＝1 T (C grid(t)·P grid (t)+C storage (t)·(P charge (t)+P discharge( t))+C response (t)·(P cut (t)+P regain (t))+C emission (t)·E emission (t))

[0398] Among them, a new decision variable z is introduced as the minimum membership of the target attribution paradigm:

[0399] z=min(μE demand (t),μP wind (t),μC price (t),μC operation (t))

[0400] The boundary conditions for minimum membership include:

[0401] z≤μE demand (t)

[0402] z≤μP wind (t)

[0403] z≤μC price (t)

[0404] z≤μC operation (t)

[0405] Specific numerical calculation:

[0406] 1. At time t = 1 (i.e. a certain hour), the grid electricity price C grid (1) = 0.12 USD / kWh, the amount of electricity purchased by the park from the grid P grid (1) = 1500 kWh.

[0407] 2. Energy storage cost C storage (1) = 0.05 USD / kWh, energy storage charging power P charge (1) = 300 kWh, discharge power P discharge (1) = 200 kWh.

[0408] 3. Demand response cost C response (1) = $20 / MW, the power P reduced by the park during the demand response event cut (1) = 75MW, the recovered power P regain (1) = 25MW.

[0409] 4. Carbon emission cost C emission(1) = 15 USD / ton, carbon emissions from gas-fired power generation in the park E emission (1) = 1.2 tons.

[0410] 5. Assume that the value of the attribution paradigm is:

[0411] ομE demand (1) = 0.8

[0412] ομP wind (1) = 0.9

[0413] ομC price (1) = 0.7

[0414] ομC operation (1) = 0.6

[0415] 6. Calculate the minimum membership z:

[0416] z=min(0.8,0.9,0.7,0.6)=0.6

[0417] 7. Calculate the total cost TC1 for that hour based on the membership and cost:

[0418] TC1=0.12×1500+0.05×(300+200)+20×(75+25)+15×1.2TC1

[0419] =0.12×1500+0.05×(300+200)+20×(75+25)+15×1.2TC1=180+25+2000+18TC1=180+25+2000+18

[0420] TC1 = 2223TC1 = 2223 USD

[0421] Technical effects:

[0422] Through this optimized scheduling method, industrial parks can reduce energy costs and improve economic benefits while ensuring production stability, and ensure the feasibility of scheduling plans under uncertain conditions through the constraint of minimum membership.

[0423] It should be understood that this embodiment is intended to illustrate how to apply the target amount function and the minimum membership decision variable to actual problems, and the specific values ​​and parameters may need to be adjusted according to actual conditions.

[0424] This application may assume a specific application scenario, such as a city traffic management department needs to optimize the energy consumption of traffic lights and reduce energy use during peak hours through a demand response program. The following is an example, including specific numerical calculations:

[0425] Application scenario description:

[0426] A city traffic management department is responsible for monitoring and controlling all traffic lights in the city. In order to reduce energy consumption and participate in demand response programs, the management department decided to use an intelligent energy management system to optimize the operation of traffic lights. The system can adjust the brightness and operation mode of the lights based on real-time traffic flow and grid demand signals. Specific embodiment 11:

[0428] The target amount function includes the following formula:

[0429] TC=∑ t＝1 T (C grid (t)·P grid (t)+C storage (t)·(P charge (t)+P discharge (t))+C response (t)·(P cut (t)+P regain (t))+C emission (t)·E emission (t)) In which, a new decision variable z is introduced as the minimum membership of the target attribution paradigm:

[0430] z=min(μE demand (t),μP wind (t),μC price (t),μC operation (t))

[0431] The boundary conditions for minimum membership include:

[0432] z≤μE demand (t)

[0433] z≤μP wind (t)

[0434] z≤μC price (t)

[0435] z≤μC operation (t)

[0436] Specific numerical calculation:

[0437] 1. At time t = 1 (i.e. a certain hour), the grid electricity price C grid (1) = 0.06 USD / kWh, the amount of electricity purchased by the traffic light from the grid P grid (1) = 2000 kWh.

[0438] 2. Energy storage cost C storage(1) = 0.03 USD / kWh, energy storage charging power P charge (1) = 500 kWh, discharge power P discharge (1) = 300 kWh.

[0439] 3. Demand response cost C response (1) = $30 / MW, the power P reduced by the traffic light during a demand response event cut( 1) = 100kW, the recovered power P regain (1) = 50kW.

[0440] 4. Carbon emission cost C emission (1) = $40 / ton, carbon emissions from gas-fired power generation of traffic lights E emission (1) = 0.8 tons.

[0441] 5. Assume that the value of the attribution paradigm is:

[0442] ομE demand (1) = 0.75

[0443] ομP wind (1) = 0.85

[0444] ομC price (1) = 0.65

[0445] ομC operation (1) = 0.55

[0446] 6. Calculate the minimum membership z:

[0447] z=min(0.75,0.85,0.65,0.55)=0.55

[0448] 7. Calculate the total cost TC1 for that hour based on the membership and cost:

[0449] TC1=0.06×2000+0.03×(500+300)+30×(100+50)+40×0.8

[0450] TC1=120+24+2100+32

[0451] TC1 = $2,276

[0452] Technical effects:

[0453] Through this optimized scheduling method, traffic management departments can reduce energy costs and improve economic benefits while ensuring the normal operation of traffic lights, and ensure the feasibility of scheduling plans under uncertain conditions through the constraint of minimum membership.

[0454] It should be understood that this embodiment is intended to illustrate how to apply the target amount function and the minimum membership decision variable to practical problems, and the specific values ​​and parameters may need to be adjusted according to the actual situation.

[0455] In one possible design, Figure 3 The data annotation apparatus of the illustrated embodiment may be implemented as a computing device, which may include a storage component 71 and a processing component 72 as shown in the figure;

[0456] The storage component 71 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 72 .

[0457] The processing component 72 is used to: obtain a query object provided by a user; based on the query object, query multiple data to be labeled that match the query object in a pre-established data set to be labeled, and generate multiple initial segmentation results corresponding to the data to be labeled; perform fine segmentation on the initial segmentation results corresponding to the multiple data to be labeled to generate multiple target segmentation results of the data to be labeled; use a pre-created labeling tool to perform labeling operations on the target segmentation results of the selected data to be labeled, and apply the labeling operations in batches to the remaining multiple target segmentation results of the data to be labeled.

[0458] The processing component 72 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0459] The storage component 71 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0460] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0461] The display component 73 can be an electroluminescent (EL) element, a liquid crystal display or a micro display with a similar structure, or a retinal direct display or a similar laser scanning display.

[0462] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0463] The communication components are configured to facilitate wired or wireless communications between the computing device and other devices.

[0464] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0465] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The data labeling method of the illustrated embodiment.

[0466] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0467] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0468] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0469] like Figure 2As shown, a schematic diagram of an optimization scheduling device A8 of an integrated intelligent energy system based on fuzzy logic of an embodiment of the present application is disclosed, and the device A8 includes: a cost target function construction module A90, an operation target and boundary condition setting device A91, a fuzzy set establishment device A92, and an operation cost minimization device A93.

[0470] The cost quota function construction module A90 is used to construct the cost quota function of the integrated energy system, and the quota function is:

[0471] in,

[0472]

[0473] TC(t) represents the total energy cost at time t;

[0474] C e (t) represents the energy consumption cost at time t;

[0475] C s (t) represents the energy storage system cost at time t;

[0476] C d (t) represents the demand response cost at time t;

[0477] C c (t) represents the carbon emission cost at time t;

[0478] p(t) represents the electricity price at time t;

[0479] P e (t) represents the power consumption of the power grid at time t;

[0480] p w (t) represents the wind power price at time t;

[0481] P w (t) represents the wind power generation at time t;

[0482] p g (t) represents the gas price at time t;

[0483] G(t) represents the gas consumption at time t;

[0484] p b (t) represents the electricity storage price;

[0485] P ch P(t) and Pdis(t) represent the storage power and discharge power at time t, respectively;

[0486] p h (t) represents the heat storage price;

[0487] H ch (t) and H dis (t) represents the heat storage power and heat release power at time t respectively;

[0488] α represents the demand response compensation coefficient;

[0489] Pd _out (t) and Pd _in (t) represents the cut-out power and cut-in power at time t respectively;

[0490] η e , η h and η g P e (t), H ch (t) and carbon emission factors of G(t);

[0491] P chp (t) represents the CHP gas power consumption at time t;

[0492] P boiler (t) represents the gas power consumed by the gas boiler at time t;

[0493] λ is the penalty coefficient;

[0494] N s is the number of energy storage systems;

[0495] N f is the number of emission sources;

[0496] η i is the carbon emission coefficient of the ith emission source;

[0497] F i (t) is the emission of the ith emission source at time t;

[0498] F i ref (t) is the reference emission of the ith emission source at time t;

[0499] δ is half the length of the time window and represents the width of the time smoothing window;

[0500] τ is the time lag parameter, representing the time delay of cost calculation;

[0501] η s (t) and η d (t) are the cost weight functions of energy storage system and demand response, respectively, reflecting how the weight of cost calculation changes over time;

[0502] The operation target and boundary condition setting device A91 is used to set the operation target of the integrated energy system and determine the operation boundary conditions of the integrated energy system accordingly, wherein the boundary conditions reflect the operation restrictions of the integrated energy system under specific targets;

[0503] A fuzzy set building device A92, used to process the volatility factors in the integrated energy system using fuzzy logic, the volatility factors include fluctuations in energy demand, unstable output of renewable energy, and market price fluctuations, and to establish an attribution paradigm of the volatility factors using a fuzzy set method;

[0504] The operating cost minimization device A93 uses a linear programming optimization algorithm to calculate the optimal scheduling strategy based on the attribution paradigm and the cost target function to minimize the operating cost of the integrated energy system while satisfying the boundary conditions.

[0505] Energy input: In some embodiments of the present application, multiple energy input methods are involved, including power grid, wind turbine generator set and gas grid. These input sources provide a variety of energy supply for the system, as follows:

[0506] Power grid: As the main energy source, the power grid provides a stable supply of electricity to meet base load demand.

[0507] Wind turbines: Use wind power converters to convert wind energy into electrical energy, contributing renewable power resources to the system.

[0508] Gas grid: Provides gas as fuel for use in the combined heat and power (CHP) system within the system.

[0509] CHP system: Using combined heat and power technology, the CHP system can generate electricity and heat energy at the same time, improving the comprehensive utilization efficiency of energy.

[0510] Energy storage equipment: Including electricity and heat storage technologies, energy storage equipment can store energy when energy demand is low and release energy during peak hours to balance the difference between supply and demand.

[0511] Demand side: The integrated energy system serves multiple needs, including electricity demand, heat demand and gas demand. Electricity demand is mainly used for electricity consumption, heat demand includes building heating and industrial heating, and gas demand is mainly used for fuel in the CHP system.

[0512] Intelligent scheduling: The system optimizes the distribution and use of energy through intelligent scheduling algorithms to ensure the stability and reliability of energy supply.

[0513] The connection relationship between the above-mentioned scheduled subsystems, as well as the conversion and distribution process of energy in the system, are as follows:

[0514] In some embodiments of the present application, the integrated energy system integrates different energy forms and realizes efficient utilization and management of energy through intelligent scheduling. The system not only improves the efficiency of energy utilization, but also enhances the adaptability to renewable energy, providing strong support for the realization of a low-carbon, clean, diversified and intelligent energy structure system.

[0515] Grid connection: As the main source of electricity supply, the grid is connected to the input end of the integrated energy system through high-voltage transmission lines, ensuring the basic power supply of the system.

[0516] Access to wind power generation system: Wind turbines convert wind energy into electrical energy through wind power converters, and after being collected through collection lines, they are connected to the power input terminal of the integrated energy system.

[0517] Gas supply: The gas grid transports gas to the CHP system in the integrated energy system through pipelines as a fuel source for the cogeneration of heat and electricity.

[0518] Connection between CHP system and power grid: The electric energy and thermal energy generated by the CHP system are connected to the power grid and thermal demand side through transmission lines and thermal pipelines respectively, realizing on-site conversion and supply of energy.

[0519] Energy storage system access: Energy storage devices, including battery energy storage systems and thermal energy storage devices, are connected to the grid and can store energy when electricity demand is low and release energy during peak hours to regulate grid load.

[0520] Demand-side connection: The demand side of the integrated energy system, including industrial, commercial and residential users, is connected to the output end of the integrated energy system through their respective power distribution networks and thermal pipelines to meet different forms of energy demand.

[0521] Intelligent dispatching system: As the control center of the system, the intelligent dispatching system is connected to each component through a communication network to monitor the energy supply and demand status in real time and optimize energy distribution.

[0522] Energy flow direction: from energy input to conversion, storage and final distribution to the demand side of the above modules and subsystems.

[0523] Internal connections within the system: The various components within the system, such as the CHP system, energy storage equipment, and intelligent dispatching system, are interconnected through internal networks and control lines, working together to achieve efficient energy management and optimized dispatching.

[0524] like Figure 4 As shown, in another embodiment of the present application, an optimization scheduling device (10) of a comprehensive intelligent energy source system based on fuzzy logic is also proposed, which is characterized by comprising:

[0525] An energy source demand component (1) is configured to manage energy source demand, the energy source demand component (1) is connected to a plurality of energy source components (12), and the energy source demand component (1) comprises a data storage area (11) for recording the energy source demand of the plurality of energy source components (12);

[0526] A demand monitoring component (2) is used to monitor energy source demand, the demand monitoring component (2) is connected to the energy source demand component (1), and the demand monitoring component (2) is used to monitor the state of the power grid, consumer demand and available energy resources in real time, and monitor energy source output and energy source demand;

[0527] A control component (3) for determining the priority order of energy source supply, and for arranging the priority order of energy source supply according to the preset priority order of the multiple energy source components (12);

[0528] and a control component (4) configured to regulate and manage the energy source demand component (1), the demand monitoring component (2) and the energy source supply priority control component (3), and,

[0529] The control component (4) includes a machine learning module (41) configured to predict energy demand patterns, grid outages and energy production fluctuations by storing characteristics and data of multiple energy source components (12), and integrate demand response functions to adaptively adjust power consumption based on grid conditions and peak demand periods.

[0530] Optionally, the energy source demand component (1) is a computing device that receives a demand request from a communication unit of an energy source component (12) connected thereto; and

[0531] The sequence is preset according to user needs and matches the sequence of the various energy source components (12).

[0532] Optionally, the optimization scheduling device (10) also includes an optimization algorithm unit for effectively allocating energy resources, minimizing energy waste, and maintaining grid stability.

[0533] Optionally, the control component (4) is operable to enable the optimization scheduling device (10) to seamlessly switch between normal operation and demand-side management periods; or to smoothly transition between regular operation and demand regulation periods; and the control component (4) is a control device controlled by a microprocessor drive.

[0534] like Figure 4As shown, another embodiment of the present application also proposes an optimization scheduling device (100) for an integrated smart energy source system based on fuzzy logic, with demand side management and energy storage unit integration, which includes:

[0535] A real-time monitoring and data collection module (101) for grid conditions, consumer demand and available energy resources;

[0536] A forecasting module (102) that uses algorithms to predict energy demand patterns, grid outages, and energy production fluctuations;

[0537] An integrated module (103) for integrating a demand response function to adjust power consumption according to grid conditions and peak demand periods;

[0538] and an energy storage unit integrated module (104) for storing excess energy when demand is low and releasing it when demand is high to balance supply and demand.

[0539] Optionally, the optimization dispatching device (100) of the integrated intelligent energy source system based on fuzzy logic also includes an optimization algorithm for effectively allocating energy resources, minimizing energy waste, and maintaining grid stability.

[0540] Optionally, the optimization scheduling device (100) of the integrated intelligent energy source system based on fuzzy logic can seamlessly switch between normal operation and demand side management periods, thereby ensuring the comfort and convenience of users.

[0541] Optionally, in the optimization dispatching device (100) of the integrated intelligent energy source system based on fuzzy logic, the real-time monitoring includes using advanced sensors and communication networks to collect and analyze power grid data.

[0542] Optionally, the energy storage unit of the optimization scheduling device (100) of the integrated intelligent energy source system based on fuzzy logic is integrated and designed for high energy density and extended cycle life.

[0543] Optionally, the optimization dispatching device (100) of the integrated smart energy source system based on fuzzy logic further includes a control unit and a software interface to facilitate communication between power supply enterprises, power grid operators and consumers.

[0544] In another embodiment of the present application, an optimization scheduling device (100) for an integrated smart energy source system based on fuzzy logic is also proposed.

[0545] It has the functions of demand-side regulation and energy storage equipment integration, and its components include:

[0546] Dynamic monitoring and data collection unit (101) for grid conditions, customer demand and available energy supplies;

[0547] A prediction unit (102) uses an algorithm to predict energy demand patterns, grid outages, and energy output fluctuations;

[0548] An integration unit (103) for integrating demand response capabilities to adjust power load according to grid conditions and peak demand periods;

[0549] and an energy storage device integrated module (104) for storing excess energy during periods of low demand and releasing it during periods of high demand, thereby balancing supply and demand.

[0550] Optionally, optimization algorithms are used to improve the efficient allocation of energy resources, reduce energy waste, and maintain grid stability.

[0551] Optionally, an optimization scheduling device (100) of an integrated intelligent energy source system based on fuzzy logic, wherein the system can smoothly transition between normal operation and demand control periods, thereby ensuring user comfort and convenience.

[0552] Optionally, dynamic monitoring involves the use of advanced sensors and communication networks to collect and analyze grid data.

[0553] Optionally, the integrated design of the energy storage device is suitable for high energy density and extended cycle life, thereby ensuring reliability and efficiency during energy storage and release.

[0554] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0555] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each optional technical feature can be combined with other embodiments in any reasonable manner. The contents of each embodiment and under each title can also be combined in any reasonable manner. Each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0556] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms of "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two. It should be understood that the term "and / or" used in this article is only an association relationship describing an associated object, indicating that three relationships can exist, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally represents that the associated objects before and after are a kind of "or" relationship.

[0557] Note: The “attribution paradigm” in each embodiment can be understood as or replaced by: membership function or fuzzy set function. The “target amount function” can be understood as or replaced by: objective function. The “boundary condition” can be understood as or replaced by: constraint condition. The “volatility factor” can be understood as or replaced by: uncertainty factor.

[0558] Although the specific implementation methods of the present application are described above, those skilled in the art should understand that this is only an example, and the protection scope of the present application is defined by the appended claims. Those skilled in the art may make various changes or modifications to these implementation methods without departing from the principles and essence of the present application, but these changes and modifications all fall within the protection scope of the present application.

Claims

1. An optimization scheduling device (10) for an integrated intelligent energy source system based on fuzzy logic, characterized in that: include: An energy source demand component (1) is configured to manage energy source demand, the energy source demand component (1) is connected to a plurality of energy source components (12), and the energy source demand component (1) comprises a data storage area (11) for recording the energy source demand of the plurality of energy source components (12); A demand monitoring component (2) is used to monitor energy source demand, the demand monitoring component (2) is connected to the energy source demand component (1), and the demand monitoring component (2) is used to monitor the state of the power grid, consumer demand and available energy resources in real time, and monitor energy source output and energy source demand; A control component (3) for determining the priority order of energy source supply, and for arranging the priority order of energy source supply according to the preset priority order of the multiple energy source components (12); and a control component (4) configured to regulate and manage the energy source demand component (1), the demand monitoring component (2) and the energy source supply priority control component (3), and, The control component (4) includes a machine learning module (41) configured to predict energy demand patterns, grid outages and energy production fluctuations by storing characteristics and data of multiple energy source components (12), and integrate demand response functions to adaptively adjust power consumption based on grid conditions and peak demand periods.

2. The optimization scheduling device (10) of the comprehensive intelligent energy source system based on fuzzy logic according to claim 1 is characterized in that: The energy source demand component (1) is a computing device that receives a demand request from a communication unit of an energy source component (12) connected thereto; and The sequence is preset according to user needs and matches the sequence of the various energy source components (12).

3. The optimization scheduling device (10) of the comprehensive intelligent energy source system based on fuzzy logic according to claim 1 is characterized in that: It also includes optimization algorithm units for efficiently allocating energy resources, minimizing energy waste, and maintaining grid stability.

4. The optimization scheduling device (10) of the comprehensive intelligent energy source system based on fuzzy logic according to claim 1, wherein: The control component (4) is operable to enable the optimization scheduling device (10) to seamlessly switch between normal operation and demand side management periods; or to smoothly transition between normal operation and demand regulation periods; as well as, The control component (4) is a control device driven by a microprocessor and is configured to execute an optimization scheduling method for an integrated smart energy system based on fuzzy logic, the method comprising the steps of: S1. The cost function of building an integrated energy system; S2. setting the operation target of the integrated energy system, and determining the operation boundary conditions of the integrated energy system accordingly, wherein the boundary conditions reflect the operation limitations of the integrated energy system under specific targets; S3. Using fuzzy logic to process the volatility factors in the integrated energy system, the volatility factors include fluctuations in energy demand, unstable output of renewable energy, and market price fluctuations, and establishing an attribution paradigm for the volatility factors through a fuzzy set method; S4. Using a linear programming optimization algorithm, the optimal scheduling strategy is calculated according to the attribution paradigm and the cost quota function to minimize the operating cost of the integrated energy system while satisfying the boundary conditions.

5. The optimization scheduling device (10) of the comprehensive intelligent energy source system based on fuzzy logic according to claim 4, wherein: The target amount function is: Where TC(t) represents the total energy cost at time t; C e (t) represents the energy consumption cost at time t; C s (t) represents the energy storage system cost at time t; C d (t) represents the demand response cost at time t; C c (t) represents the carbon emission cost at time t.

6. An optimization scheduling method for a comprehensive smart energy system based on fuzzy logic, characterized in that: include: S1. The target amount function of the cost of building a comprehensive energy system, the target amount function is: Where TC(t) represents the total energy cost at time t; C e (t) represents the energy consumption cost at time t; C s (t) represents the energy storage system cost at time t; C d (t) represents the demand response cost at time t; C c (t) represents the carbon emission cost at time t; S2. setting the operation target of the integrated energy system, and determining the operation boundary conditions of the integrated energy system accordingly, wherein the boundary conditions reflect the operation limitations of the integrated energy system under specific targets; S3. Using fuzzy logic to process the volatility factors in the integrated energy system, the volatility factors include fluctuations in energy demand, unstable output of renewable energy, and market price fluctuations, and establishing an attribution paradigm for the volatility factors through a fuzzy set method; S4. Using a linear programming optimization algorithm, the optimal scheduling strategy is calculated according to the attribution paradigm and the cost quota function to minimize the operating cost of the integrated energy system while satisfying the boundary conditions.

7. The optimization scheduling method of the integrated smart energy system based on fuzzy logic according to claim 6, wherein: The fuzzy set method includes: Define fuzzy sets and attribution paradigms to quantify the uncertainty of input parameters; The uncertainty of energy demand, wind power output, electricity price fluctuations and operating cost changes are modeled using the attribution paradigm; and the target amount function is defined by the following formula: TC=∑t(C energy (t)·P grid (t)+C storage (t)·(P charge (t)+P discharge (t))+C response (t)·(P cut (t)+P regain (t))+C emission (t)·E total (t)) Among them, E total (t) Total energy consumption including electricity, wind power and gas.

8. The optimization scheduling method of the integrated smart energy system based on fuzzy logic according to claim 7, wherein: The boundary conditions include energy balance, grid operation restrictions, gas grid restrictions and wind power restrictions; The energy requirement attribution paradigm is defined based on the following formula: Where E is the actual demand and E0 is the benchmark demand; The wind power attribution paradigm is defined based on the following formula: Where P is the wind power output, P min and P max are the minimum and maximum values ​​of power generation output respectively.

9. The optimization scheduling method of the integrated smart energy system based on fuzzy logic according to claim 8, wherein: The electricity price attribution paradigm is defined based on the following formula: Where C is the electricity price, C avg is the average electricity price, σ C is the standard deviation of electricity prices The operating cost attribution paradigm is defined based on the following formula: Where C is the operating cost, C min and C max are the minimum and maximum costs respectively.

10. The optimization scheduling method of the integrated smart energy system based on fuzzy logic according to claim 9, wherein: The step S3 further comprises: In the demand response dispatch of integrated energy systems, the fuzzy set method is used to model the uncertainty of input parameters in order to capture and express the fuzziness and uncertainty of these parameters.

11. An electronic device, characterized in that: It includes a processor that is operable to execute the optimization scheduling method for an integrated smart energy system based on fuzzy logic as described in any one of claims 6-10.

12. A non-volatile storage medium, characterized in that: A program is stored which can be activated to execute the optimization scheduling method of the integrated smart energy system based on fuzzy logic according to any one of claims 6 to 10.

Images