Comprehensive energy management and control method and system, storage medium and electronic equipment

Abstract

The invention belongs to the technical field of comprehensive energy management, and provides a comprehensive energy management and control method and system, a storage medium and electronic equipment, and the method comprises the steps: generating a power generation prediction power sequence corresponding to a preset time length based on historical power generation data through employing a first prediction algorithm; based on the historical energy consumption data of the plurality of energy consumption devices, using a second prediction algorithm to generate a device prediction load sequence corresponding to a preset duration; constructing a load scheduling algorithm of the adjustable load equipment, and generating a load scheduling model according to the power generation prediction power sequence and the equipment prediction load sequence; constructing a scheduling optimization algorithm of energy supply and energy load, and generating a scheduling optimization model based on the power generation prediction power sequence, the equipment prediction load sequence and the load scheduling model; and based on the load scheduling model and the scheduling optimization model, managing and controlling the energy consumption condition of the energy consumption equipment in a future preset duration range. The flexibility and the accuracy of load scheduling are improved; the solving efficiency is improved, and the precision of an optimization result is ensured.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of integrated energy management, and particularly relates to an integrated energy control method, system, storage medium, and electronic device. Background Art

[0002] By integrating multiple energy forms such as electric energy, thermal energy, and gas, an integrated energy system can improve energy utilization efficiency, reduce dependence on external energy, and thus reduce energy costs and carbon emissions. In terms of energy control methods, rule-based energy control methods and optimization-based energy control methods each have their own advantages and disadvantages.

[0003] Rule-based energy control methods have the advantages of being mature, having low computational requirements, and being responsive. Such methods are simple and easy to implement, can quickly provide solutions, and are suitable for scenarios with high real-time requirements. However, due to mainly relying on experience or simple mathematical models, rule-based energy control methods often cannot consider all parameters and constraints globally, which may lead to non-optimal energy control solutions. At the same time, during the energy control process, the adaptability to scenarios is poor, and it cannot adapt to different or complex scenarios.

[0004] Optimization-based energy control methods can find the optimal solution or approximate optimal solution under given constraints by constructing a mathematical model and using an optimization algorithm to solve it. Optimization-based energy control methods can consider various parameters and constraints globally, making energy management more refined and efficient. However, during the process of optimizing the integrated energy, optimization-based energy control methods usually require high computational resources and computational time. Therefore, they are generally not applicable to scenarios with high real-time requirements for energy control. Summary of the Invention

[0005] To solve the above problems, the present disclosure provides an integrated energy control method, system, storage medium, and electronic device. By using a prediction algorithm, a power generation prediction power sequence and an equipment prediction load sequence are generated, the load adjustability of energy-consuming equipment is determined, a load scheduling algorithm for adjustable load equipment is constructed, and based on the power generation prediction power sequence and the equipment prediction load sequence, the load scheduling algorithm is used to generate a load scheduling model; a scheduling optimization algorithm for energy supply and energy load is constructed, and based on the power generation prediction power sequence, the equipment prediction load sequence, and the load scheduling model, the scheduling optimization algorithm is used to generate a scheduling optimization model; based on the load scheduling model and the scheduling optimization model, the energy consumption situation of energy-consuming equipment within a preset future time range is controlled. It can improve the flexibility and accuracy of load scheduling, reduce the complexity of the scheduling optimization algorithm and the dimension of optimization variables, improve the solution efficiency, and ensure the accuracy of the optimization result.

[0006] The present invention is realized through the following technical solutions:

[0007] In a first aspect, embodiments of the present disclosure provide a comprehensive energy management and control method, the method comprising:

[0008] Based on historical power generation data, using a first prediction algorithm, generating a power generation prediction power sequence corresponding to a preset duration;

[0009] Based on historical energy consumption data of multiple energy-consuming devices, using a second prediction algorithm, generating a device prediction load sequence corresponding to a preset duration;

[0010] Obtaining the load information of all energy-consuming devices, determining the load adjustability of the energy-consuming devices, constructing a load scheduling algorithm for adjustable load devices, and using the load scheduling algorithm according to the power generation prediction power sequence and the device prediction load sequence to generate a load scheduling model;

[0011] Constructing a scheduling optimization algorithm for energy supply and energy load, and using the scheduling optimization algorithm based on the power generation prediction power sequence, the device prediction load sequence and the load scheduling model to generate a scheduling optimization model;

[0012] Based on the load scheduling model and the scheduling optimization model, managing and controlling the energy consumption of energy-consuming devices within a preset duration range in the future.

[0013] Further,

[0014] Obtaining the load information of all energy-consuming devices, determining the load adjustability of the energy-consuming devices, and using five-variable to define the adjustment characteristics of the adjustable load devices;

[0015] Based on the five-variable of the adjustable load device, setting preset judgment conditions for the operating power ratio, the operable state, the load adjustable state and the operating power of the adjustable load device, and constructing a load scheduling algorithm for the adjustable load device;

[0016] Using the power generation prediction power sequence and the device prediction load sequence as boundary conditions, and generating the load scheduling model based on the load scheduling algorithm.

[0017] Further,

[0018] The five-variable is expressed as:

[0019] [n, I n (t), O n (t), S n (t), P n (t)];

[0020] In the formula, n represents the device number of the adjustable load device, the device numbers of the adjustable load devices are set according to a preset priority, and the smaller the device number, the higher the corresponding preset priority, where the value range of n is from 1 to m, and both n and m are natural numbers; In (t) represents the operating power ratio of the adjustable load device with device number n at time t; O n (t) represents the operable state of the adjustable load device with device number n at time t; S n (t) represents the load adjustable state of the adjustable load device with device number n at time t; P n (t) represents the operating power of the adjustable load device with device number n at time t, where the value range of t is determined according to the preset duration.

[0021] Furthermore,

[0022] The preset judgment condition for the operable state O n (t) of the adjustable load device with device number n at time t is:

[0023] If then O n (t) = 1;

[0024] If then O n (t) = 0;

[0025] where b i represents the start time of the adjustable load device; U n represents the preset maximum operating time corresponding to the adjustable load device with device number n;

[0026] The preset judgment condition for the load adjustable state S n (t) of the adjustable load device with device number n at time t is:

[0027] If then S n (t) = 1;

[0028] If then S n (t) = 0;

[0029] where c i represents the start time of the adjustable load device; D n represents the preset operating time that the adjustable load device with device number n needs to reach for adjusting the load;

[0030] The preset judgment condition for the operating power P n (t) of the adjustable load device with device number n at time t is:

[0031] If P PV (t) > P FL (t), according to the preset priority of the adjustable load device, sequentially execute the following judgments in the order of the preset priority:

[0032] If O n (t) = 1, then I n (t) = 1,

[0033] If P PV (t) ≤ P FL (t), and P e (t) > P e-avg , according to the preset priority of the adjustable load equipment, the following judgments are executed in reverse order of the preset priority:

[0034] If S n (t) = 1, then I n (t) = 0, P n (t) = 0;

[0035] Among them, P PV (t) is the photovoltaic power generation power at time t, P FL (t) is the total equipment load at time t; represents the maximum operating power of the adjustable load equipment with equipment number n; P e (t) is the electricity price at time t, P e-avg is the average electricity price; P PV (t) is determined by the equipment predicted load sequence, P FL (t) is determined by the equipment predicted load sequence.

[0036] Furthermore,

[0037] Set the objective function and constraint conditions of the energy supply and energy load, and construct the scheduling optimization algorithm according to the objective function and constraint conditions;

[0038] Use the power generation prediction power sequence, equipment predicted load sequence, and load scheduling model as boundary conditions, and generate the scheduling optimization model based on the scheduling optimization algorithm.

[0039] Furthermore,

[0040] The objective function is expressed as:

[0041]

[0042] Among them, ω1, ω2, ω3 are weight coefficients, ω1 + ω2 + ω3 = 1, and 0 ≤ ω1, ω2, ω3 ≤ 1; Min(P purch ) represents the minimum power purchase target from the power grid; Min(P sold ) represents the minimum power supply target to the power grid; represents the net expenditure sub-target for reducing the electricity cost; Min(F(x)) represents the objective function.

[0043] Furthermore,

[0044] The minimum power purchase target from the power grid Min(P purch ), which is expressed as:

[0045]

[0046] where P purch represents the power taken from the power grid; P GL,t represents the power taken from the power grid by the load device at time t, and P GEV,t represents the power taken from the power grid by the new energy vehicle battery at time t;

[0047] The minimum power supply target to the power grid Min(P sold ), which is expressed as:

[0048]

[0049] where P sold represents the power supplied to the power grid, and P PVG,t represents the power supplied to the power grid by the surplus power of the photovoltaic power generation system at time t;

[0050] The sub - target of reducing the net expenditure of electricity cost is expressed as:

[0051]

[0052] B T =B PV,T +B ESS,T +B EV,T ;

[0053] where S T represents the power purchase cost of the load device and the new energy vehicle battery charging; C PV,ESS,EV represents the daily attenuation cost of the photovoltaic power generation system, the energy storage system and the new energy vehicle battery, represents the daily attenuation cost of the photovoltaic power generation system, represents the daily attenuation cost of the energy storage system, represents the daily attenuation cost of the new energy vehicle battery; B T represents the total revenue of the photovoltaic power generation system, the energy storage system and the new energy vehicle battery charging, B PV,T represents the revenue of the photovoltaic power generation system, B ESS,T represents the revenue of the energy storage system, B EV,T represents the revenue of the new energy vehicle battery charging; ρ t represents the electricity price at time t.

[0054] Furthermore,

[0055] The constraints include power balance constraints, photovoltaic output inequality constraints, SOC boundary constraints, power exchange constraints, energy flow constraints and new energy vehicle travel energy constraints.

[0056] Further,

[0057] Power balancing constraints include:

[0058]

[0059] Among them, P purch,t represents the amount of electricity drawn from the grid at time t, P PV,t represents the photovoltaic power generation at time t, Indicates the amount of electricity taken from the energy storage system. P represents the discharge capacity of the new energy vehicle battery at time t; L,t represents the power consumption of the energy-consuming equipment at time t, P sold,t represents the amount of power supplied to the grid at time t, represents the amount of charge to the energy storage system at time t, Indicates the amount of power supplied to the new energy vehicle battery at time t;

[0060] The photovoltaic output inequality constraints include:

[0061] P PV,t ≥P PVL,t +P PVEV,t +P PVESS,t +P sold,t ;

[0062] Among them, P PV,t represents the photovoltaic power generation at time t, P PVL,t represents the power consumption of the photovoltaic power generation system at time t, P PVEV,t represents the power consumption of new energy vehicle batteries in the photovoltaic power generation system at time t, P PVESS,t represents the power consumption of the energy storage system in the photovoltaic power generation system at time t, P sold,t It represents the amount of power supplied to the grid at time t;

[0063] SOC boundary constraints include:

[0064] SOC ESS,min ≤SOC ESS,t ≤SOC ESS,max ;

[0065] SOC EV,min ≤SOC EV,t ≤SOC EV,max ;

[0066] Among them, SOC ESS,min Indicates the minimum state of charge of the energy storage system, SOC ESS,tIndicates the state of charge of the energy storage system at time t, SOC ESS,max Indicates the maximum state of charge of the energy storage system; SOC EV,min Indicates the minimum state of charge of the new energy vehicle battery, SOC EV,t Indicates the state of charge of the new energy vehicle battery at time t, SOC EV,max Indicates the maximum state of charge of the new energy vehicle battery;

[0067] The power exchange constraint includes:

[0068]

[0069] Among them, P GL,t Indicates the power taken by the load device from the power grid at time t, P GEV,t Indicates the power taken by the new energy vehicle battery from the power grid at time t, P PVG,t Indicates the power supplied by the surplus power of the photovoltaic power generation system to the power grid at time t; Indicates the maximum power purchase from the power grid, Indicates the maximum power injection into the power grid from the power grid, γ represents the power grid state variable, γ = 0 or 1;

[0070] The energy flow constraint includes:

[0071]

[0072] Among them, Indicates the maximum power taken by the load device from the power grid; Indicates the maximum power taken by the new energy vehicle battery from the power grid; Indicates the maximum power consumption of the photovoltaic power generation system; Indicates the maximum power consumption of the new energy vehicle battery in the photovoltaic power generation system; The maximum power consumption of the energy storage system in the photovoltaic power generation system; Indicates the maximum power supplied by the surplus power of the photovoltaic power generation system to the power grid; P ESSL,t Indicates the power consumption of the storage battery at time t, Indicates the maximum power consumption of the storage battery; P EVL,t Indicates the charging power consumption of the new energy vehicle battery at time t, Indicates the maximum charging power consumption of the new energy vehicle battery;

[0073] The energy constraint for new energy vehicle trips includes:

[0074] SOC EV,t ≥SOC EV,t-need ;

[0075] Among them, SOC EV,t Indicates the state of charge of the electric vehicle battery at time t, SOC EV,t-needIt represents the minimum state of charge that a new energy vehicle needs to maintain to meet travel requirements during the time period at time t.

[0076] In a second aspect, based on the same inventive concept, an embodiment of the present disclosure also provides an integrated energy management and control system, which includes: a first prediction module, a second prediction module, a load scheduling module, a scheduling optimization module, and a device control module;

[0077] The first prediction module is used to generate a predicted power generation sequence corresponding to a preset duration based on historical power generation data using a first prediction algorithm;

[0078] The second prediction module is used to generate a predicted load sequence of devices corresponding to a preset duration based on historical energy consumption data of multiple energy-consuming devices using a second prediction algorithm;

[0079] The load scheduling module is used to obtain the load information of all energy-consuming devices, determine the load adjustability of the energy-consuming devices, construct a load scheduling algorithm for adjustable load devices, and generate a load scheduling model according to the predicted power generation sequence and the predicted load sequence of the devices using the load scheduling algorithm;

[0080] The scheduling optimization module is used to construct a scheduling optimization algorithm for energy supply and energy load, and generate a scheduling optimization model based on the predicted power generation sequence, the predicted load sequence of the devices, and the load scheduling model using the scheduling optimization algorithm;

[0081] The device control module is used to control the energy consumption of energy-consuming devices within a future preset duration range based on the load scheduling model and the scheduling optimization model.

[0082] Furthermore,

[0083] The load scheduling module includes an adjustment characteristic generation unit, a load scheduling algorithm generation unit, and a load scheduling model generation unit;

[0084] The adjustment characteristic generation unit is used to obtain the load information of all energy-consuming devices, determine the load adjustability of the energy-consuming devices, and define the adjustment characteristics of the adjustable load devices using five-variable; where the five-variable is expressed as:

[0085] [n, I n (t), O n (t), S n (t), P n (t)];

[0086] In the formula, n represents the device number of the adjustable load device, and the device numbers of the adjustable load devices are set according to a preset priority. The smaller the device number, the higher the corresponding preset priority. Among them, the value range of n is from 1 to m, and both n and m are natural numbers; In (t) represents the operating power ratio of the adjustable load device with device number n at time t; O n (t) represents the operable state of the adjustable load device with device number n at time t; S n (t) represents the load adjustable state of the adjustable load device with device number n at time t; P n (t) represents the operating power of the adjustable load device with device number n at time t, where the value range of t is determined according to a preset duration;

[0087] The load scheduling algorithm generation unit is used to set preset judgment conditions for the operating power ratio, operable state, load adjustable state, and operating power of the adjustable load device based on the five - element variables of the adjustable load device, and construct a load scheduling algorithm for the adjustable load device; where,

[0088] The preset judgment condition for the operable state O n (t) of the adjustable load device with device number n at time t is:

[0089] If Then O n (t) = 1;

[0090] If Then O n (t) = 0;

[0091] Where, b i represents the start - up time of the adjustable load device; U n represents the preset maximum operating time corresponding to the adjustable load device with device number n;

[0092] The preset judgment condition for the load adjustable state S n (t) of the adjustable load device with device number n at time t is:

[0093] If Then S n (t) = 1;

[0094] If Then S n (t) = 0;

[0095] Where, c i represents the start - up time of the adjustable load device; D n represents the preset operating time that the adjustable load device with device number n needs to reach for load adjustment;

[0096] The preset judgment condition for the operating power P n (t) of the adjustable load device with device number n at time t is:

[0097] If P PV (t) > P FL (t), according to the preset priority of the adjustable load device, successively execute the following judgments in the order of the preset priority:

[0098] If O n (t) = 1, then I n (t) = 1,

[0099] If P PV (t) ≤ P FL (t), and P e (t) > P e-avg , according to the preset priority of the adjustable load device, successively execute the following judgments in the reverse order of the preset priority:

[0100] If S n (t) = 1, then I n (t) = 0, P n (t) = 0;

[0101] Among them, P PV (t) is the photovoltaic power generation power at time t, P FL (t) is the total equipment load at time t; represents the maximum operating power of the adjustable load device with equipment number n; P e (t) is the electricity price at time t, P e-avg is the average electricity price; P PV (t) is determined through the equipment predicted load sequence, P FL (t) is determined through the equipment predicted load sequence.

[0102] The load scheduling model generation unit is used to use the generated power prediction sequence and the equipment predicted load sequence as boundary conditions, and generate the load scheduling model based on the load scheduling algorithm.

[0103] Furthermore,

[0104] The scheduling optimization module includes a scheduling optimization algorithm generation unit and a scheduling optimization model generation unit;

[0105] The scheduling optimization algorithm generation unit is used to set the objective function and constraint conditions of the energy supply and the energy load, and construct the scheduling optimization algorithm according to the objective function and the constraint conditions; among them,

[0106] The objective function is expressed as:

[0107]

[0108] where ω1, ω2, ω3 are weight coefficients, ω1 + ω2 + ω3 = 1, and 0 ≤ ω1, ω2, ω3 ≤ 1; Min(P purch ) represents the minimum power purchase target from the power grid; Min(P sold ) represents the minimum power supply target to the power grid; represents the sub-target of reducing the net expenditure of electricity cost; Min(F(x)) represents the objective function;

[0109] The constraint conditions include power balance constraint, photovoltaic output inequality constraint, SOC boundary constraint, power exchange constraint, energy flow constraint and new energy vehicle travel energy constraint;

[0110] The scheduling optimization model generation unit is used to use the generated power prediction power sequence, device predicted load sequence and load scheduling model as boundary conditions, and generate the scheduling optimization model based on the scheduling optimization algorithm.

[0111] Thirdly, based on the same inventive concept, the embodiments of the present disclosure also provide a computer-readable storage medium storing one or more programs, which can implement the foregoing integrated energy management and control method when the one or more programs are executed.

[0112] Fourthly, based on the same inventive concept, the embodiments of the present disclosure also provide an electronic device, including a processor, a communication interface, the foregoing computer-readable storage medium and a communication bus. Among them, the processor, the communication interface and the computer-readable storage medium communicate with each other through the communication bus. Among them, the processor is used to execute the program stored in the foregoing computer-readable storage medium.

[0113] Compared with the prior art, the present disclosure has the following advantages:

[0114] 1. Based on the generated power prediction power sequence and device predicted load sequence of a future preset duration, a load scheduling model corresponding to adjustable load devices is generated, improving the flexibility and accuracy of load scheduling;

[0115] 2. Based on the generated power prediction power sequence of a future preset duration, combined with the load scheduling model, a scheduling optimization model is generated, reducing the complexity of the scheduling optimization algorithm and the dimension of optimization variables, improving the solution efficiency, and ensuring the accuracy of the optimization result;

[0116] 3. A scheduling optimization algorithm corresponding to energy supply and energy load is constructed, combined with the load scheduling model corresponding to adjustable load devices, and a scheduling optimization model is generated, realizing the collaborative optimization of multi-energy systems.

[0117] Other features and advantages of the present disclosure will be set forth in the following description, and in part will be obvious from the description, or can be learned by practicing the present disclosure. The objectives and other advantages of the present disclosure can be realized and attained by the structure pointed out in the description, claims, and drawings. Description of the Drawings

[0118] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0119] Figure 1 Flowchart of a comprehensive energy management and control method provided by an embodiment of the present disclosure;

[0120] Figure 2 Block diagram of a comprehensive energy management and control system provided by an embodiment of the present disclosure. Detailed Embodiments

[0121] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present disclosure with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are some, but not all, of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts fall within the scope of protection of the present disclosure.

[0122] First aspect, Figure 1 Flowchart of a comprehensive energy management and control method provided by an embodiment of the present disclosure, as Figure 1 shown, an embodiment of the present disclosure provides a comprehensive energy management and control method, including:

[0123] S1: Based on historical power generation data, use the first prediction algorithm to generate a power generation prediction power sequence corresponding to a preset duration.

[0124] Specifically, the power generation prediction power sequence includes the power generation powers at different times within a preset time range. The historical power generation data includes the historical power generation power data, meteorological data, and environmental data of the photovoltaic power generation system; among them, the historical power generation power data of the photovoltaic power generation system includes the power generation data per hour or the power generation data volume within a shorter time range; the meteorological data includes solar irradiance, temperature, humidity, wind speed, cloud cover, etc.; the environmental data includes the cleanliness, temperature, etc. of the photovoltaic modules. The first prediction algorithm includes time series algorithms, machine learning algorithms, and deep learning algorithms; among them, the time series algorithms include autoregressive integrated moving average model, seasonal autoregressive integrated moving average model, etc.; the machine learning algorithms include support vector machine, random forest, etc.; the deep learning algorithms include long short-term memory network, convolutional neural network, etc.

[0125] S2: Based on the historical energy consumption data of multiple energy-consuming devices, use the second prediction algorithm to generate the device prediction load sequence corresponding to the preset time range.

[0126] Specifically, the device prediction load sequence includes the total device load at different times within a preset time range. The device prediction load sequence includes multiple load subsequences, each energy-consuming device corresponds to a load subsequence, and the target load subsequence includes the operating power of the target energy-consuming device at different times within a preset time range. The historical energy consumption data includes the electrical load data, meteorological data, date and time data of multiple energy-consuming devices; among them, the electrical load data includes the past power consumption data; the meteorological data includes meteorological data such as temperature, humidity, wind speed, etc.; the date and time data includes time factor-related data such as weekdays, weekends, holidays, etc. The second prediction algorithm includes time series algorithms, machine learning algorithms, and deep learning algorithms; among them, the time series algorithms include autoregressive integrated moving average model, seasonal autoregressive integrated moving average model, etc.; the machine learning algorithms include support vector machine, random forest, etc.; the deep learning algorithms include long short-term memory network, convolutional neural network, etc.

[0127] S3: Obtain the load information of all energy-consuming devices, determine the load adjustability of the energy-consuming devices, construct the load scheduling algorithm for adjustable load devices, and use the load scheduling algorithm to generate the load scheduling model according to the power generation prediction power sequence and the device prediction load sequence.

[0128] S4: Construct the scheduling optimization algorithm for energy supply and energy load, and use the scheduling optimization algorithm to generate the scheduling optimization model based on the power generation prediction power sequence, the device prediction load sequence, and the load scheduling model.

[0129] S5: Based on the load scheduling model and the scheduling optimization model, control the energy consumption situation of the energy-consuming devices within the future preset time range.

[0130] In the integrated energy management and control method in the embodiments of the present disclosure, a prediction algorithm is adopted to generate a power generation prediction power sequence and an equipment prediction load sequence, determine the load adjustability of energy-consuming equipment, construct a load scheduling algorithm for adjustable load equipment, and use the load scheduling algorithm based on the power generation prediction power sequence and the equipment prediction load sequence to generate a load scheduling model; construct a scheduling optimization algorithm for energy supply and energy load, and use the scheduling optimization algorithm based on the power generation prediction power sequence, the equipment prediction load sequence and the load scheduling model to generate a scheduling optimization model; based on the load scheduling model and the scheduling optimization model, manage and control the energy consumption situation of energy-consuming equipment within a preset future time range. It can improve the flexibility and accuracy of load scheduling, reduce the complexity of the scheduling optimization algorithm and the dimension of optimization variables, improve the solution efficiency, and ensure the accuracy of the optimization result.

[0131] In some examples, obtaining the load information of all energy-consuming equipment, determining the load adjustability of the energy-consuming equipment, constructing a load scheduling algorithm for adjustable load equipment, and using the load scheduling algorithm based on the power generation prediction power sequence and the equipment prediction load sequence to generate a load scheduling model includes:

[0132] S31: Obtain the load information of all energy-consuming equipment, determine the load adjustability of the energy-consuming equipment, and use five-variable to define the adjustment characteristics of the adjustable load equipment.

[0133] Specifically, the five-variable is expressed as:

[0134] [n, I n (t), O n (t), S n (t), P n (t)];

[0135] In the formula, n represents the equipment number of the adjustable load equipment, and the equipment numbers of the adjustable load equipment are set according to a preset priority. The smaller the equipment number, the higher the corresponding preset priority. Among them, the value range of n is from 1 to m, and both n and m are natural numbers; I n (t) represents the operating power ratio of the adjustable load equipment with the equipment number n at the moment t; O n (t) represents the operable state of the adjustable load equipment with the equipment number n at the moment t; S n (t) represents the load adjustable state of the adjustable load equipment with the equipment number n at the moment t; P n (t) represents the operating power of the adjustable load equipment with the equipment number n at the moment t, where the value range of t is determined according to the preset duration.

[0136] S32: Based on the five - element variables of the adjustable load device, set the preset judgment conditions for the operating power ratio, operable state, load - adjustable state, and operating power of the adjustable load device, and construct a load - scheduling algorithm for the adjustable load device.

[0137] Specifically, the preset judgment condition for the operable state O n (t) of the adjustable load device with device number n at time t is:

[0138] If then O n (t) = 1;

[0139] If then O n (t) = 0;

[0140] where b i represents the start - up time of the adjustable load device; U n represents the preset maximum operating time corresponding to the adjustable load device with device number n;

[0141] The preset judgment condition for the load - adjustable state S n (t) of the adjustable load device with device number n at time t is:

[0142] If then S n (t) = 1;

[0143] If then S n (t) = 0;

[0144] where c i represents the start - up time of the adjustable load device; D n represents the preset operating time required for the adjustable load device with device number n to adjust the load;

[0145] The preset judgment condition for the operating power P n (t) of the adjustable load device with device number n at time t is:

[0146] If P PV (t)>P FL (t), in accordance with the preset priority of the adjustable load device, sequentially execute the following judgments in the order of the preset priority:

[0147] If O n (t) = 1, then I n (t) = 1,

[0148] If P PV (t)≤P FL (t), and P e(t) > P e-avg , perform the following judgments in reverse order of the preset priority according to the preset priority of the adjustable load equipment:

[0149] If S n (t) = 1, then I n (t) = 0, P n (t) = 0;

[0150] Among them, P PV (t) is the photovoltaic power generation at time t, and P FL (t) is the total equipment load at time t; represents the maximum operating power of the adjustable load equipment with equipment number n, P PV (t) > P FL (t) means that the photovoltaic power generation at time t is greater than the total equipment load; P e (t) is the electricity price at time t, and P e-avg is the average electricity price, P e (t) > P e-avg means that the electricity price at time t is greater than the average electricity price; P PV (t) ≤ P FL (t) means that the photovoltaic power generation at time t is less than or equal to the total equipment load; P PV (t) is determined through the equipment predicted load sequence, and P FL (t) is determined through the equipment predicted load sequence.

[0151] S33: Use the power generation prediction power sequence and the equipment predicted load sequence as boundary conditions, and generate a load scheduling model based on the load scheduling algorithm.

[0152] Specifically, using the power generation prediction power sequence and the equipment predicted load sequence as boundary conditions, it is necessary to determine the photovoltaic power generation P at time t according to the power generation prediction power sequence PV (t), determine the total equipment load P at time t according to the equipment predicted load sequence FL (t), and generate a load scheduling model based on the load scheduling algorithm.

[0153] In some examples, construct a scheduling optimization algorithm for energy supply and energy load. Based on the power generation prediction power sequence, the equipment predicted load sequence, and the load scheduling model, use the scheduling optimization algorithm to generate a scheduling optimization model, including:

[0154] S41: Set the objective function and constraint conditions for energy supply and energy load, and construct a scheduling optimization algorithm according to the objective function and constraint conditions.

[0155] Specifically, the objective function is expressed as:

[0156]

[0157] Among them, ω1, ω2, ω3 are weight coefficients, ω1 + ω2 + ω3 = 1, and 0 ≤ ω1, ω2, ω3 ≤ 1; Min(P purch ) represents the minimum power purchase target from the power grid; Min(P sold ) represents the minimum power supply target to the power grid; represents the sub - target of reducing the net expenditure of electricity cost; Min(F(x)) represents the objective function. The constraint conditions include power balance constraint, photovoltaic output inequality constraint, SOC boundary constraint, power exchange constraint, energy flow constraint and new energy vehicle travel energy constraint.

[0158] S42: Use the power generation prediction power sequence, equipment predicted load sequence and load scheduling model as boundary conditions, and generate a scheduling optimization model based on the scheduling optimization algorithm.

[0159] Specifically, after constructing the scheduling optimization algorithm according to the objective function and constraint conditions, use the power generation prediction power sequence, equipment predicted load sequence and load scheduling model as boundary conditions, and generate a scheduling optimization model based on the scheduling optimization algorithm. The power generation prediction power sequence and equipment predicted load sequence provide some numerical values to the objective function and constraint conditions, and the preset judgment conditions in the load scheduling model will also affect the objective function and constraint conditions, thereby affecting the generation of the final scheduling optimization model.

[0160] The integrated energy management and control method provided by the present disclosure has the following advantages:

[0161] 1. Based on the power generation prediction power sequence and equipment predicted load sequence of a preset future duration, generate a load scheduling model corresponding to adjustable load equipment, improving the flexibility and accuracy of load scheduling;

[0162] 2. Based on the power generation prediction power sequence of a preset future duration, combined with the load scheduling model, generate a scheduling optimization model, reducing the complexity of the scheduling optimization algorithm and the dimension of optimization variables, improving the solution efficiency, and ensuring the accuracy of the optimization result;

[0163] 3. Construct a scheduling optimization algorithm corresponding to energy supply and energy load, combined with the load scheduling model corresponding to adjustable load equipment, generate a scheduling optimization model, and realize the coordinated optimization of multi - energy systems.

[0164] Example 1:

[0165] Taking the integrated energy management and control of the same energy system as an example for illustration, the energy - using equipment of this energy system mainly includes an electric vehicle charging system and a load equipment system, and also includes a photovoltaic power generation system, an energy storage system and a power grid system for providing power to the energy system.

[0166] Obtain the predicted power sequence of power generation:

[0167] Based on historical power generation data, use the first prediction algorithm to generate a predicted power sequence of power generation corresponding to a preset duration; wherein, the predicted power sequence of power generation includes the power generation powers at different moments within the preset duration. The predicted power sequence of power generation includes P EG (1), P EG (2), ……, P EG (t), where P EG (t) represents the power generation power of the power generation system at time t, and the value range of t is determined according to the preset duration; the power generation system includes a photovoltaic power generation subsystem, and may also be provided with multiple power generation subsystems such as a wind power generation subsystem and a hydraulic power generation subsystem according to the actual geographical location, actual power system and actual power supply demand, and no further specific limitations are made here; in this disclosure, taking the power generation system including a photovoltaic power generation subsystem and the preset duration being 24 hours as an example, the value range of t is positive integers from 1 to 24.

[0168] Further, the predicted power sequence of power generation includes multiple photovoltaic power generation powers P PV (t) within the preset duration of 24 hours, and P Pv (t) represents the photovoltaic power generation power of the photovoltaic power generation subsystem at time t, where t takes positive integers from 1 to 24; P EG (t) includes P PV (t), and P EG (t) may also include the power generation powers of other power generation subsystems at time t.

[0169] The historical power generation data includes the historical power generation power data of the photovoltaic power generation system, meteorological data, and environmental data; wherein, the historical power generation power data of the photovoltaic power generation system includes the power generation data per hour or the power generation data volume within a shorter time range; the meteorological data includes solar irradiance, temperature, humidity, wind speed, cloud amount, etc.; the environmental data includes the cleanliness, temperature, etc. of the photovoltaic modules.

[0170] The first prediction algorithm includes time series algorithms, machine learning algorithms, and deep learning algorithms; wherein, the time series algorithms include autoregressive integrated moving average models, seasonal autoregressive integrated moving average models, etc.; the machine learning algorithms include support vector machines, random forests, etc.; the deep learning algorithms include long short-term memory networks, convolutional neural networks, etc.

[0171] It should be understood that during the configuration process, the preset duration can be adjusted according to the actual situation. Here, it is only used as an example and no specific limitation is made. The historical power generation data can include not only the historical power generation power data of the photovoltaic power generation system, but also the historical power generation power data of other power generation methods. The specific selection of the first prediction algorithm needs to consider factors such as the preset duration and the data volume of the historical power generation data, and no further specific limitation is made here.

[0172] Obtain the device predicted load sequence:

[0173] Based on the historical energy consumption data of multiple energy-consuming devices, use the second prediction algorithm to generate a device predicted load sequence corresponding to the preset duration; where the device predicted load sequence includes the total device load at different times within the preset duration. The device predicted load sequence includes Wherein, represents the energy consumption load of the energy-consuming device numbered n at time t. The value range of t is determined according to the preset duration. In this disclosure, an example with a preset duration of 24 hours is used for illustration. The energy consumption load includes data such as electricity consumption.

[0174] Furthermore, the device predicted load sequence includes multiple load subsequences. Each energy-consuming device corresponds to a load subsequence. The target load subsequence includes the operating power of the target energy-consuming device at different times within the preset duration.

[0175] The historical energy consumption data includes the electrical load data, meteorological data, date and time data of multiple energy-consuming devices; wherein, the electrical load data includes the past electricity consumption data; the meteorological data includes meteorological data such as temperature, humidity, wind speed, etc.; the date and time data includes time factor-related data such as weekdays, weekends, holidays, etc.

[0176] The second prediction algorithm includes time series algorithms, machine learning algorithms, and deep learning algorithms; wherein, the time series algorithms include autoregressive integrated moving average models, seasonal autoregressive integrated moving average models, etc.; the machine learning algorithms include support vector machines, random forests, etc.; the deep learning algorithms include long short-term memory networks, convolutional neural networks, etc.

[0177] It should be understood that during the configuration process, the preset duration can be adjusted according to the actual situation. Here, it is only used as an example and no specific limitation is made. The specific selection of the second prediction algorithm needs to consider factors such as the preset duration and the data volume of the historical energy consumption data, and no further specific limitation is made here.

[0178] Generate a load scheduling model:

[0179] Obtain the load information of all energy-consuming devices, and determine the load adjustability of the energy-consuming devices according to the load information of the energy-consuming devices; use five-variable to define the adjustment characteristics of the adjustable load devices, and the five-variable is expressed as:

[0180] [n, I n (t), O n (t), S n (t), P n (t)];

[0181] Among them, n represents the device number of the adjustable load device, n takes natural numbers from 1 to m, the device numbers of the adjustable load devices are set according to the preset priority, and the smaller the device number, the higher the corresponding preset priority; I n (t) represents the operating power ratio of the adjustable load device with device number n at time t; O n (t) represents the operable state of the adjustable load device with device number n at time t; S n (t) represents the load adjustable state of the adjustable load device with device number n at time t; P n (t) represents the operating power of the adjustable load device with device number n at time t.

[0182] The adjustable load devices include flexible adjustable load devices and switching-type adjustable load devices. The operating power ratio I of the flexible adjustable load device with device number n at time t n (t) ranges from 0 ≤ I n (t) ≤ 1; the operating power ratio I of the switching-type adjustable load device with device number n at time t n (t) takes the value of 0 or 1.

[0183] The operable state of the adjustable load device includes operable and inoperable. When O n (t) = 0, the adjustable load device with device number n is operable at time t. When O n (t) = 1, the adjustable load device with device number n is inoperable at time t; within the planned operation time period of the adjustable load device, when its cumulative operation time does not reach the preset maximum operation time, the adjustable load device is considered operable; the preset judgment condition for the operable state O of the adjustable load device with device number n at time t n (t) is:

[0184] If Then O n (t) = 1;

[0185] If Then O n (t) = 0;

[0186] Among them, bi Indicates the start time of the adjustable load device; U n Indicates the preset maximum operating time corresponding to the adjustable load device with equipment number n.

[0187] The load adjustable state of the adjustable load device includes adjustable and non - adjustable, S n When S(t)=0, the adjustable load device with equipment number n is non - adjustable at time t. n When S(t)=1, the adjustable load device with equipment number n is adjustable at time t; for some adjustable load devices, especially switching adjustable load devices, it is required that the load can be adjusted after running for the preset operating time. The load adjustable state S(t) of the adjustable load device with equipment number n at time t n The preset judgment condition of S(t) is:

[0188] If Then S n (t)=1;

[0189] If Then S n (t)=0;

[0190] Among them, c i Indicates the start time of the adjustable load device; D n Indicates the preset operating time that the adjustable load device with equipment number n needs to reach to adjust the load; usually, there is such a limit for switching adjustable load devices. Therefore, c i Indicates the start time of the switching adjustable load device with equipment number n; when the adjustable load device is a flexible adjustable device, this judgment can be not carried out, or D corresponding to the flexible adjustable device n Is set to 0.

[0191] Configure the operating power P(t) of the adjustable load device with equipment number n at time t n The preset judgment condition of P(t) is:

[0192] If P PV (t)>P FL (t), schedule all operable adjustable load devices to operate at rated power according to the preset priority of the adjustable load device, that is, for equipment numbers from 1 to m, the following judgments are executed in sequence:

[0193] If O n (t)=1, then I n (t)=1,

[0194] Among them, Indicates the maximum operating power of the adjustable load device with equipment number n; P PV(t) is the photovoltaic power generation at time t, P FL (t) is the total equipment load at time t, P PV (t) > P FL (t) indicates that the photovoltaic power generation at time t is greater than the total equipment load. At this time, there is a surplus in photovoltaic power generation. Therefore, all adjustable load devices can operate at full power;

[0195] If P PV (t) ≤ P FL (t), and P e (t) > P e-avg , according to the preset priority of the adjustable load device, all stoppable adjustable load devices are scheduled to stop running in reverse order of the preset priority, that is, starting from device number m to 1, the following judgments are executed in sequence:

[0196] If S n (t) = 1, then I n (t) = 0, P n (t) = 0;

[0197] Among them, P e (t) is the electricity price at time t obtained in advance, P e-avg is the average electricity price obtained in advance, P PV (t) ≤ P FL (t) indicates that the photovoltaic power generation at time t is less than or equal to the total equipment load. At this time, there is no surplus in photovoltaic power generation or other power supply methods besides photovoltaic power generation are needed to supply power to the energy-consuming equipment; P e (t) > P e-avg indicates that the electricity price at time t is greater than the average electricity price; P e (t) and P e-avg can be obtained in real time from an external system through a software interface, or the electricity price and average electricity price at different times can be determined through historical data before running the scheduling strategy model of the schedulable load; P PV (t) needs to be determined through the equipment predicted load sequence. Since only the photovoltaic power generation subsystem is included in this disclosure, therefore P PV (t) is P EG (t), P FL (t) needs to be determined through the equipment predicted load sequence. The sum of the energy consumption loads of all energy-consuming equipment at the same time is P FL (t).

[0198] According to the foregoing preset judgment conditions of the operating power ratio, operable state, load adjustable state and operating power of the adjustable load device, a load scheduling algorithm for the adjustable load device is constructed.

[0199] Using the predicted power sequence of power generation and the predicted load sequence of equipment as boundary conditions, a scheduling optimization model is generated based on the load scheduling algorithm. It is necessary to determine the photovoltaic power generation P PV (t) at time t according to the predicted power sequence of power generation, and determine the total equipment load P FL (t) at time t according to the predicted load sequence of equipment.

[0200] Generate a scheduling optimization model:

[0201] Set the objective function and constraint conditions for energy supply and energy load, and construct a scheduling optimization algorithm according to the objective function and constraint conditions; among them, energy supply includes photovoltaic power generation, energy storage system, power purchase from the grid, etc., and energy load includes power consumption of load equipment and battery charging of new energy vehicles, etc.

[0202] The objective function is expressed as:

[0203]

[0204] Among them, ω1, ω2, ω3 are weight coefficients, which need to satisfy ω1 + ω2 + ω3 = 1, and 0 ≤ ω1, ω2, ω3 ≤ 1; Min(P purch ) represents the sub-objective of minimizing power purchase from the grid; Min(P sold ) represents the sub-objective of minimizing power supply to the grid; represents the sub-objective of reducing the net expenditure of electricity cost; Min(F(x)) represents the objective function.

[0205] Min(P purch ) includes the power taken from the grid by all energy-consuming equipment. When classifying energy-consuming equipment according to the functions of the equipment, the energy-consuming equipment includes load equipment and new energy vehicle batteries. The calculation formula of Min(P purch ) is:

[0206]

[0207] Among them, P purch represents the power taken from the grid; P GL,t represents the power taken from the grid by the load equipment at time t, and P GEV,t represents the power taken from the grid by the new energy vehicle battery at time t.

[0208] The calculation formula of Min(P sold ) is:

[0209]

[0210] Among them, P sold represents the power supplied to the grid, and P PVG,tIt represents the amount of electricity supplied from the excess power of the photovoltaic power generation system to the power grid at time t. When there is a surplus in photovoltaic power generation, the surplus part is supplied to the power grid.

[0211] Its calculation formula is:

[0212]

[0213]

[0214] B T = B PV,T + B ESS,T + B EV,T ;

[0215] Among them, S T represents the electricity purchase cost of load equipment and new energy vehicle batteries; C PV,ESS,EV represents the daily attenuation cost of the photovoltaic power generation system, energy storage system and new energy vehicle batteries. represents the daily attenuation cost of the photovoltaic power generation system. represents the daily attenuation cost of the energy storage system. represents the daily attenuation cost of the new energy vehicle battery; B T represents the total income of the photovoltaic power generation system, energy storage system and new energy vehicle battery charging. B PV,T represents the income of the photovoltaic power generation system. B ESS,T represents the income of the energy storage system. B EV,T represents the income of the new energy vehicle battery charging; ρ t represents the electricity price at time t.

[0216] The constraint conditions include power balance constraint, photovoltaic output inequality constraint, SOC (state of charge) boundary constraint, power exchange constraint, energy flow constraint and new energy vehicle travel energy constraint:

[0217] The power balance constraint includes:

[0218]

[0219] Among them, P purch,t represents the amount of electricity taken from the power grid at time t. P PV,t represents the photovoltaic power generation at time t. represents the amount of electricity taken from the energy storage system. represents the discharge amount of the new energy vehicle battery at time t; P L,t represents the electricity consumption of the energy-consuming equipment at time t. P sold,t represents the amount of electricity supplied to the power grid at time t. represents the amount of electricity charged to the energy storage system at time t. represents the amount of electricity supplied to the new energy vehicle battery at time t.

[0220] The photovoltaic output inequality constraints include:

[0221] P PV,t ≥P PVL,t +P PVEV,t +P PVESS,t +P sold,t ;

[0222] Among them, P PV,t represents the photovoltaic power generation at time t, P PVL,t represents the power consumption of the photovoltaic power generation system at time t, P PVEV,t represents the power consumption of the new energy vehicle battery in the photovoltaic power generation system at time t, P PvESS,t represents the power consumption of the energy storage system in the photovoltaic power generation system at time t, P sold,t represents the power supplied to the power grid at time t.

[0223] The SOC boundary constraints include:

[0224] SOC ESS,min ≤SOC ESS,t ≤SOC ESS,max ;

[0225] SOC EV,min ≤SOC Ev,t ≤SOC EV,max ;

[0226] Among them, SOC ESS,min represents the minimum state of charge of the energy storage system, SOC ESS,t represents the state of charge of the energy storage system at time t, SOC ESS,max represents the maximum state of charge of the energy storage system; SOC EV,min represents the minimum state of charge of the new energy vehicle battery, SOC EV,t represents the state of charge of the new energy vehicle battery at time t, SOC EV,max represents the maximum state of charge of the new energy vehicle battery.

[0227] The power exchange constraints include:

[0228] Introduce the grid state variable γ, γ = 0 or 1;

[0229]

[0230] Among them, P GL,t represents the power taken by the load device from the grid at time t, P GEV,t represents the power taken by the new energy vehicle battery from the grid at time t, P PVG,t represents the power supplied to the grid by the surplus power of the photovoltaic power generation system at time t; represents the maximum power purchase from the grid, It means the maximum power fed into the grid. When feeding power into the grid, no power is supplied to the energy-consuming devices.

[0231] The energy flow constraints include:

[0232]

[0233] Among them, P GL,t represents the power taken from the grid by the load device at time t, represents the maximum power that the load device can take from the grid; P GEV,t represents the power taken from the grid by the new energy vehicle battery at time t, represents the maximum power that the new energy vehicle battery can take from the grid; P PvL,t represents the power consumption of the photovoltaic power generation system at time t, represents the maximum power consumption of the photovoltaic power generation system; P PVEV,t represents the power consumption of the new energy vehicle battery in the photovoltaic power generation system at time t, represents the maximum power consumption of the new energy vehicle battery in the photovoltaic power generation system; P PVESS,t represents the power consumption of the energy storage system in the photovoltaic power generation system at time t, the maximum power consumption of the energy storage system in the photovoltaic power generation system; P PVG,t represents the power fed from the surplus power of the photovoltaic power generation system to the grid at time t, represents the maximum power that the surplus power of the photovoltaic power generation system can feed to the grid; P ESSL,t represents the power consumption of the storage battery at time t, represents the maximum power consumption of the storage battery; P EVL,t represents the power consumption for charging the new energy vehicle battery at time t, represents the maximum power consumption for charging the new energy vehicle battery.

[0234] Energy constraint for new energy vehicle travel:

[0235] To ensure that the energy stored in the new energy vehicle battery is greater than the energy required for the new energy vehicle to travel. To provide the energy required for the travel distance of the electric vehicle, the energy constraint for new energy vehicle travel includes:

[0236] SOC EV,t ≥SOC EV,t-need ;

[0237] Among them, SOC EV,t represents the state of charge of the electric vehicle battery at time t, and SOC EV,t-need represents the minimum state of charge that the new energy vehicle needs to maintain to meet travel requirements during the time period at time t.

[0238] After constructing the scheduling optimization algorithm according to the objective function and constraint conditions, using the power generation prediction power sequence, the device prediction load sequence, and the load scheduling model as boundary conditions, based on the scheduling optimization algorithm, a scheduling optimization model is generated. The power generation prediction power sequence and the device prediction load sequence provide partial numerical values to the objective function and constraint conditions, and the preset judgment conditions in the load scheduling model will also affect the objective function and constraint conditions, thereby affecting the generation of the final scheduling optimization model. For example, the sub-objective of minimizing the electricity purchase from the power grid Min(P purch ) in the objective function used to construct the scheduling optimization algorithm includes the electricity consumption P GL,t of the load device from the power grid at time t and the electricity consumption P GEV,t of the new energy vehicle battery from the power grid at time t. Both the load device and the new energy vehicle battery are energy-consuming devices, and P GL,t and P GEV,t need to be determined through the device prediction load sequence; Min(P sold ) includes the electricity supply P PVG,t from the surplus power of the photovoltaic power generation system to the power grid at time t, and P PVG,t needs to be determined through the power generation prediction power sequence; similarly, the parameters included in the sub-objective of reducing the net expenditure of electricity cost and the parameters included in the constraint conditions also need to be determined in combination with the power generation prediction power sequence and the device prediction load sequence; therefore, after completing the scheduling optimization algorithm, the power generation prediction power sequence and the device prediction load sequence need to be used as boundary conditions for generating the scheduling optimization model. The preset judgment conditions of the operating power ratio, operable state, load adjustable state, and operating power of the adjustable load device in the load scheduling model need to be used as reference conditions and constraints for the objective function and constraint conditions. When using the scheduling optimization algorithm to generate the scheduling optimization model, the preset judgment conditions in the load scheduling model need to be satisfied. Therefore, the load scheduling model is also used as a boundary condition for the scheduling optimization algorithm, combined with the power generation prediction power sequence and the device prediction load sequence, to generate the scheduling optimization model.

[0239] Input the load scheduling model and the scheduling optimization model into the device or system for comprehensive energy management and control, and based on the load scheduling model and the scheduling optimization model, manage and control the energy consumption of energy-consuming devices within a preset future time range.

[0240] In the second aspect, Figure 2 This is a block diagram of a comprehensive energy management and control system provided by an embodiment of the present disclosure. As Figure 2 shown, based on the same inventive concept, an embodiment of the present disclosure also provides a comprehensive energy management and control system. The comprehensive energy management and control system includes: a first prediction module, a second prediction module, a load scheduling module, a scheduling optimization module, and a device control module;

[0241] The first prediction module is used to generate a power generation prediction power sequence corresponding to a preset duration based on historical power generation data using a first prediction algorithm;

[0242] The second prediction module is used to generate a device prediction load sequence corresponding to a preset duration based on historical energy consumption data of multiple energy-consuming devices using a second prediction algorithm;

[0243] The load scheduling module is used to obtain the load information of all energy-consuming devices, determine the load adjustability of the energy-consuming devices, construct a load scheduling algorithm for adjustable load devices, and generate a load scheduling model according to the power generation prediction power sequence and the device prediction load sequence using the load scheduling algorithm;

[0244] The scheduling optimization module is used to construct a scheduling optimization algorithm for energy supply and energy load, and generate a scheduling optimization model based on the power generation prediction power sequence, the device prediction load sequence and the load scheduling model using the scheduling optimization algorithm;

[0245] The device control module is used to control the energy consumption of energy-consuming devices within a future preset duration range based on the load scheduling model and the scheduling optimization model.

[0246] In some examples, the load scheduling module includes an adjustment characteristic generation unit, a load scheduling algorithm generation unit and a load scheduling model generation unit;

[0247] The adjustment characteristic generation unit is used to obtain the load information of all energy-consuming devices, determine the load adjustability of the energy-consuming devices, and define the adjustment characteristics of the adjustable load devices using a five-variable; where the five-variable is expressed as:

[0248] [n, I n (t), O n (t), S n (t), P n (t)];

[0249] In the formula, n represents the device number of the adjustable load device, and the device numbers of the adjustable load devices are set according to a preset priority. The smaller the device number, the higher the corresponding preset priority. Among them, the value range of n is from 1 to m, and both n and m are natural numbers; I n (t) represents the operating power ratio of the adjustable load device with device number n at time t; O n (t) represents the operable state of the adjustable load device with device number n at time t; S n (t) represents the load adjustable state of the adjustable load device with device number n at time t; P n (t) represents the operating power of the adjustable load device with device number n at time t, where the value range of t is determined according to the preset duration;

[0250] A load scheduling algorithm generation unit is used to set the operating power ratio, operable state, load adjustable state, and preset judgment conditions of the operating power of the adjustable load device based on the five - element variables of the adjustable load device, and construct a load scheduling algorithm for the adjustable load device; where,

[0251] The operable state O of the adjustable load device numbered n at time t n (t)'s preset judgment condition is:

[0252] If then O n (t) = 1;

[0253] If then O n (t) = 0;

[0254] Where, b i represents the start time of the adjustable load device to operate; U n represents the preset maximum operating time corresponding to the adjustable load device numbered n;

[0255] The load adjustable state S of the adjustable load device numbered n at time t n (t)'s preset judgment condition is:

[0256] If then S n (t) = 1;

[0257] If then S n (t) = 0;

[0258] Where, c i represents the start time of the adjustable load device to operate; D n represents the preset operating time that the adjustable load device numbered n needs to adjust the load to reach;

[0259] The operating power P of the adjustable load device numbered n at time t n (t)'s preset judgment condition is:

[0260] If P PV (t) > P FL (t), in accordance with the preset priority of the adjustable load device, sequentially execute the following judgments in the order of the preset priority:

[0261] If O n (t) = 1, then I n (t) = 1,

[0262] If P PV (t) ≤ P FL (t), and Pe (t) > P e-avg , according to the preset priorities of the adjustable load devices, the following judgments are sequentially executed in reverse order of the preset priorities:

[0263] If S n (t) = 1, then I n (t) = 0, P n (t) = 0;

[0264] Among them, P PV (t) is the photovoltaic power generation at time t, P FL (t) is the total equipment load at time t; represents the maximum operating power of the adjustable load device with equipment number n; P e (t) is the electricity price at time t, P e-avg is the average electricity price; P PV (t) is determined through the equipment predicted load sequence, P FL (t) is determined through the equipment predicted load sequence.

[0265] The load scheduling model generation unit is used to use the power generation prediction power sequence and the equipment predicted load sequence as boundary conditions, and generate a load scheduling model based on the load scheduling algorithm.

[0266] In some examples, the scheduling optimization module includes a scheduling optimization algorithm generation unit and a scheduling optimization model generation unit;

[0267] The scheduling optimization algorithm generation unit is used to set the objective function and constraint conditions of the energy supply and energy load, and construct a scheduling optimization algorithm according to the objective function and constraint conditions; among them,

[0268] The objective function is expressed as:

[0269]

[0270] In the formula, ω1, ω2, ω3 are weight coefficients, ω1 + ω2 + ω3 = 1, and 0 ≤ ω1, ω2, ω3 ≤ 1; Min(P purch ) represents the minimum power purchase target from the power grid; Min(P sold ) represents the minimum power supply target to the power grid; represents the sub-target of reducing the net expenditure of electricity cost; Min(F(x)) represents the objective function;

[0271] The constraint conditions include power balance constraint, photovoltaic output inequality constraint, SOC boundary constraint, power exchange constraint, energy flow constraint and new energy vehicle travel energy constraint;

[0272] A scheduling optimization model generation unit, which is used to generate a scheduling optimization model based on a scheduling optimization algorithm by using a power generation prediction power sequence, a device prediction load sequence, and a load scheduling model as boundary conditions.

[0273] Thirdly, based on the same inventive concept, an embodiment of the present disclosure further provides a computer-readable storage medium storing one or more programs, which can implement the foregoing integrated energy management and control method when the one or more programs are executed.

[0274] Fourthly, based on the same inventive concept, an embodiment of the present disclosure further provides an electronic device, including a processor, a communication interface, the foregoing computer-readable storage medium, and a communication bus. Among them, the processor, the communication interface, and the computer-readable storage medium communicate with each other through the communication bus. Among them, the processor is used to execute the program stored in the foregoing computer-readable storage medium.

[0275] It should be noted that the electrical connections between the above-mentioned various units do not necessarily represent the connections between the lines. An indirect connection method can be applied to the embodiments of the present disclosure as long as the purpose of the present disclosure is achieved.

[0276] Although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A comprehensive energy management and control method, characterized in that, The method includes: Based on historical power generation data, using a first prediction algorithm, generating a power generation prediction power sequence corresponding to a preset duration; Based on the historical energy consumption data of multiple energy-consuming devices, using a second prediction algorithm, generating a device prediction load sequence corresponding to a preset duration; Obtaining the load information of all energy-consuming devices, determining the load adjustability of the energy-consuming devices, constructing a load scheduling algorithm for adjustable load devices, and using the load scheduling algorithm to generate a load scheduling model according to the power generation prediction power sequence and the device prediction load sequence; Constructing a scheduling optimization algorithm for energy supply and energy load, and using the scheduling optimization algorithm to generate a scheduling optimization model based on the power generation prediction power sequence, the device prediction load sequence, and the load scheduling model; Based on the load scheduling model and the scheduling optimization model, controlling the energy consumption situation of energy-consuming devices within a preset future duration range.

2. The method according to claim 1, characterized in that, The obtaining the load information of all energy-consuming devices, determining the load adjustability of the energy-consuming devices, constructing a load scheduling algorithm for adjustable load devices, and using the load scheduling algorithm to generate a load scheduling model according to the power generation prediction power sequence and the device prediction load sequence includes: Obtaining the load information of all energy-consuming devices, determining the load adjustability of the energy-consuming devices, and using five-variable to define the adjustment characteristics of the adjustable load devices; Based on the five-variable of the adjustable load device, setting preset judgment conditions for the operable state, load adjustable state, operating power ratio, and operating power of the adjustable load device, and constructing a load scheduling algorithm for the adjustable load device; Using the power generation prediction power sequence and the device prediction load sequence as boundary conditions, and generating the load scheduling model based on the load scheduling algorithm.

3. The method according to claim 2, wherein The five-variable is expressed as: [n, I n (t), O n (t), S n (t), P n (t)]; In the formula, n represents the device number of the adjustable load device. The device numbers of the adjustable load devices are set according to a preset priority. The smaller the device number, the higher the corresponding preset priority. Here, the value range of n is from 1 to m, and both n and m are natural numbers; I n (t) represents the operating power ratio of the adjustable load device with device number n at time t; O n (t) represents the operable state of the adjustable load device with device number n at time t; S n (t) represents the load adjustable state of the adjustable load device with device number n at time t; P n (t) represents the operating power of the adjustable load device with device number n at time t. Here, the value range of t is determined according to a preset duration.

4. The method according to claim 3, wherein Based on the five-variable of the adjustable load device, setting preset judgment conditions for the operable state, load adjustable state, operating power ratio, and operating power of the adjustable load device includes: The operable state O of the adjustable load device with device number n at time t n (t)'s preset judgment condition is: If then O n (t) = 1; If then O n (t) = 0; Among them, b i represents the start time of the adjustable load device; U n represents the preset maximum operation time corresponding to the adjustable load device with the device number n; The adjustable load state S of the adjustable load device with device number n at time t n (t) has the following preset judgment conditions: If then S n (t) = 1; If then S n (t) = 0; Among them, c i represents the start operation time of the adjustable load device; D n represents the preset operation time that the adjustable load device with equipment number n needs to reach when adjusting the load. The operating power P of the adjustable load device with device number n at time t n (t) has the following preset judgment conditions: If P PV (t) > P FL (t), the following judgments are sequentially executed in accordance with the preset priority of the adjustable load device in the order of the preset priority: If O n (t) = 1, then I n (t) = 1, If P PV (t) ≤ P FL (t), and P e (t) > P e-avg , according to the preset priority of the adjustable load device, the following judgments are sequentially executed in reverse order of the preset priority: If S n (t) = 1, then I n (t) = 0, P n (t) = 0; Among them, P PV (t) is the photovoltaic power generation at time t, and P FL (t) is the total equipment load at time t; represents the maximum operating power of the adjustable load device with equipment number n; P e (t) is the electricity price at time t, and P e-avg is the average electricity price; P PV (t) is determined through the equipment predicted load sequence, and P FL (t) is determined through the equipment predicted load sequence.

5. The method according to claim 1, wherein The constructing a scheduling optimization algorithm for energy supply and energy load, and using the scheduling optimization algorithm to generate a scheduling optimization model based on the power generation prediction power sequence, the device prediction load sequence, and the load scheduling model includes: Setting the objective function and constraint conditions for energy supply and energy load, and constructing the scheduling optimization algorithm according to the objective function and the constraint conditions; Using the power generation prediction power sequence, the device prediction load sequence, and the load scheduling model as boundary conditions, and generating the scheduling optimization model based on the scheduling optimization algorithm.

6. The method according to claim 5, characterized in that The objective function is expressed as: Among them, ω1, ω2, ω3 are weight coefficients, ω1 + ω2 + ω3 = 1, and 0 ≤ ω1, ω2, ω3 ≤ 1; Min(P purch ) represents the minimum power purchase target from the power grid; Min(P sold ) represents the minimum power supply target to the power grid; represents the sub-target of reducing the net expenditure of electricity cost; Min(F(x)) represents the objective function.

7. The method according to claim 6, characterized in that, The minimum power purchase target Min(P purch ) from the power grid is expressed as: Among them, P purch represents the power taken from the power grid; P GL,t represents the power taken from the power grid by the load device at time t, and P GEV,t represents the power taken from the power grid by the new energy vehicle battery at time t; The minimum power supply sub-goal Min(P sold ) to the power grid is expressed as: Among them, P sold represents the power supplied to the power grid, and P PVG,t represents the power supplied to the power grid by the surplus power of the photovoltaic power generation system at time t; The sub-goal of reducing the net expenditure on electricity costs is expressed as: B T = B PV,T + B ESS,T + B EV,T ; Among them, S T represents the electricity purchase cost for charging the load device and the new energy vehicle battery; C PV,ESS,EV represents the daily attenuation cost of the photovoltaic power generation system, energy storage system and new energy vehicle battery. <� represents the daily attenuation cost of the photovoltaic power generation system. represents the daily attenuation cost of the energy storage system. represents the daily attenuation cost of the new energy vehicle battery; B T represents the total revenue of the photovoltaic power generation system, energy storage system and new energy vehicle battery charging. B PV,T represents the revenue of the photovoltaic power generation system. B ESS,T represents the revenue of the energy storage system. B EV,T represents the revenue of new energy vehicle battery charging; ρ t represents the electricity price at time t. It should be noted that there is a misrepresentation in the original text where "<� " should likely be " ", and this has been corrected in the translation for better readability. If this is not an error, please let me know.

8. The method according to claim 5, wherein The constraint conditions include power balance constraint, PV output inequality constraint, SOC boundary constraint, power exchange constraint, energy flow constraint, and new energy vehicle travel energy constraint.

9. The method according to claim 8, characterized in that, The power balance constraint includes: Among them, P purch,t represents the power consumption from the power grid at time t, and P PV,t represents the photovoltaic power generation at time t, represents the power consumption from the energy storage system, represents the battery discharge of new energy vehicles at time t; P L,t represents the power consumption of energy-consuming equipment at time t, and P sold,t represents the power supply to the power grid at time t, represents the charging amount to the energy storage system at time t, represents the power supply to the battery of new energy vehicles at time t; The PV output inequality constraint includes: P PV,t ≥P PVL,t +P PVEV,t +P PVESS,t +P sold,t ; Among them, P PV,t represents the photovoltaic power generation at time t, P PVL,t represents the power consumption of the photovoltaic power generation system at time t, P PVEV,t represents the power consumption of the new energy vehicle battery in the photovoltaic power generation system at time t, P PVESS,t represents the power consumption of the energy storage system in the photovoltaic power generation system at time t, P sold,t represents the power supplied to the power grid at time t; The SOC boundary constraint includes: SOC ESS,min ≤ SOC ESS,t ≤ SOC ESS,max ; SOC EV,min ≤ SOC EV,t ≤ SOC EV,max ; Among them, SOC ESS,min represents the minimum state of charge of the energy storage system, SOC ESS,t represents the state of charge of the energy storage system at time t, SOC ESS,max represents the maximum state of charge of the energy storage system; SOC EV,min represents the minimum state of charge of the new energy vehicle battery, SOC EV,t represents the state of charge of the new energy vehicle battery at time t, SOC EV,max represents the maximum state of charge of the new energy vehicle battery; The power exchange constraint includes: Among them, P GL,t represents the power taken by the load device from the power grid at time t, P GEV,t represents the power taken by the new energy vehicle battery from the power grid at time t, P PVG,t represents the power supplied by the surplus power of the photovoltaic power generation system to the power grid at time t; represents the maximum power purchase from the power grid, represents the maximum power injection into the power grid, and γ represents the power grid state variable, γ = 0 or 1; The energy flow constraint includes: Among them, represents the maximum power taken from the power grid by the load device; represents the maximum power taken from the power grid by the new energy vehicle battery; represents the maximum power consumption of the photovoltaic power generation system; represents the maximum power consumption of the new energy vehicle battery in the photovoltaic power generation system; represents the maximum power consumption of the energy storage system in the photovoltaic power generation system; represents the maximum power supplied from the surplus power of the photovoltaic power generation system to the power grid; P ESSL,t represents the power consumption of the battery at time t, represents the maximum power consumption of the battery; P EVL,t represents the power consumption for charging the new energy vehicle battery at time t, represents the maximum power consumption for charging the new energy vehicle battery; The new energy vehicle travel energy constraint includes: SOC EV,t ≥SOC EV,t-need ; Among them, SOC Ev,t represents the state of charge of the electric vehicle battery at time t, and SOC EV,t-need represents the minimum state of charge that the new energy vehicle needs to maintain to meet travel requirements during the time period at time t.

10. An integrated energy management and control system, characterized in that, The system includes: a first prediction module, a second prediction module, a load scheduling module, a scheduling optimization module, and a device control module; The first prediction module is configured to generate a power generation prediction power sequence corresponding to a preset duration based on historical power generation data using a first prediction algorithm; The second prediction module is configured to generate a device prediction load sequence corresponding to a preset duration based on historical energy consumption data of multiple energy-consuming devices using a second prediction algorithm; The load scheduling module is configured to obtain the load information of all energy-consuming devices, determine the load adjustability of the energy-consuming devices, construct a load scheduling algorithm for the load-adjustable devices, and generate a load scheduling model according to the power generation prediction power sequence and the device prediction load sequence using the load scheduling algorithm; The scheduling optimization module is configured to construct a scheduling optimization algorithm for energy supply and energy load, and generate a scheduling optimization model based on the power generation prediction power sequence, the device prediction load sequence, and the load scheduling model using the scheduling optimization algorithm; The device control module is configured to control the energy consumption of the energy-consuming devices within a preset future duration based on the load scheduling model and the scheduling optimization model.

11. The system according to claim 10, wherein The load scheduling module includes a regulation characteristic generation unit, a load scheduling algorithm generation unit, and a load scheduling model generation unit; The regulation characteristic generation unit is configured to obtain the load information of all energy-consuming devices, determine the load adjustability of the energy-consuming devices, and define the regulation characteristics of the load-adjustable devices using five-variable; wherein, the five-variable is expressed as: [n, I n (t), O n (t), S n (t), P n (t)]; Wherein, n represents the device number of the adjustable load device, and the device numbers of the adjustable load devices are set according to a preset priority. The smaller the device number, the higher the corresponding preset priority. Among them, the value range of n is from 1 to m, and both n and m are natural numbers; I n (t) represents the operating power ratio of the adjustable load device with device number n at time t; O n (t) represents the operable state of the adjustable load device with device number n at time t; S n (t) represents the load adjustable state of the adjustable load device with device number n at time t; P n (t) represents the operating power of the adjustable load device with device number n at time t, wherein the value range of t is determined according to a preset duration; The load scheduling algorithm generation unit is configured to set preset judgment conditions for the operating power ratio, the operable state, the load adjustable state, and the operating power of the load-adjustable devices based on the five-variable of the load-adjustable devices, and construct a load scheduling algorithm for the load-adjustable devices; wherein, The operable state O of the adjustable load device numbered n at time t n (t)'s preset judgment condition is: If then O n (t) = 1; If then O n (t) = 0; Among them, b i represents the start time of the adjustable load device; U n represents the preset maximum operation time corresponding to the adjustable load device with equipment number n; The adjustable load state S of the adjustable load device with device number n at time t n (t) has the following preset judgment conditions: If then S n (t) = 1; If then S n (t) = 0; Among them, c i represents the start running time of the adjustable load device; D n represents the preset running time that the adjustable load device with equipment number n needs to reach when adjusting the load. The operating power P of the adjustable load device with device number n at time t n (t) has the following preset judgment conditions: If P PV (t) > P FL (t), according to the preset priority of the adjustable load device, the following judgments are sequentially executed in the order of the preset priority: If O n (t) = 1, then I n (t) = 1, If P PV (t) ≤ P FL (t), and P e (t) > P e-avg , according to the preset priority of the adjustable load device, the following judgments are sequentially executed in reverse order of the preset priority: If S n (t) = 1, then I n (t) = 0, P n (t) = 0; Among them, P PV (t) is the photovoltaic power generation at time t, and P FL (t) is the total equipment load at time t; represents the maximum operating power of the adjustable load equipment with equipment number n; P e (t) is the electricity price at time t, and P e-avg is the average electricity price; P PV (t) is determined by the equipment predicted load sequence, and P FL (t) is determined by the equipment predicted load sequence; The load scheduling model generation unit is configured to use the power generation prediction power sequence and the device prediction load sequence as boundary conditions, and generate the load scheduling model based on the load scheduling algorithm.

12. The system according to claim 10, wherein The scheduling optimization module includes a scheduling optimization algorithm generation unit and a scheduling optimization model generation unit; The scheduling optimization algorithm generation unit is configured to set the objective function and constraint conditions for energy supply and energy load, and construct the scheduling optimization algorithm according to the objective function and the constraint conditions; wherein, The objective function is expressed as: Where ω1, ω2, and ω3 are weight coefficients, ω1 + ω2 + ω3 = 1, and 0 ≤ ω1, ω2, ω3 ≤ 1; Min(P purch ) represents the minimum power purchase target from the power grid; Min(P sold ) represents the minimum power supply target to the power grid; represents the sub-target of reducing the net expenditure on electricity costs; Min(F(x)) represents the objective function; The constraint conditions include power balance constraint, PV output inequality constraint, SOC boundary constraint, power exchange constraint, energy flow constraint, and new energy vehicle travel energy constraint; The scheduling optimization model generation unit is configured to use the power generation prediction power sequence, the device prediction load sequence, and the load scheduling model as boundary conditions, and generate the scheduling optimization model based on the scheduling optimization algorithm.

13. A computer-readable storage medium storing one or more programs, characterized in that when the one or more programs are executed, the integrated energy management method according to any one of claims 1-9 can be implemented.

14. An electronic device, comprising a processor, a communication interface, the computer-readable storage medium according to claim 13, and a communication bus; wherein, The processor, the communication interface, and the computer-readable storage medium communicate with each other through a communication bus; characterized in that the processor is configured to execute the programs stored in the computer-readable storage medium.

Images