Multi-source power system real-time optimization energy scheduling method and system

Abstract

The application provides a kind of multi-source power system real-time optimization energy scheduling method and system, belongs to multi-source power system technical field, the running condition of load carrying equipment is collected;According to the running condition collected, the state of charge of energy storage unit is combined, the globally optimal diesel generator output power and energy storage unit output power are calculated offline;According to the globally optimal diesel generator output power and energy storage unit output power calculated, energy distribution rule is obtained;According to the energy distribution rule obtained, the real-time energy scheduling of multi-source power system is carried out.The application has small amount of calculation, high reliability and strong real-time performance;Without complex real-time optimization calculation, only according to the typical running condition of load carrying equipment, the energy distribution rule that can be approximately substituted for global optimization effect is obtained by optimizing training method through offline iterative calculation result, that is, energy saving and emission reduction of multi-source power system can be realized.

Description

Technical Field

[0001] This invention relates to the field of multi-source power system technology, specifically to a method and system for real-time optimized energy scheduling of multi-source power systems. Background Technology

[0002] To achieve long-distance transportation operations, most transport equipment still relies on diesel generators as its primary power source. However, due to the frequent switching of operating conditions required by the transport equipment, diesel generators struggle to maintain high-efficiency operation. Furthermore, traditional single-diesel power systems cannot effectively utilize the braking energy generated during braking, hindering optimal transmission system design. With the development of new energy technologies, multi-source power systems have become a hot topic in the optimization design of transport equipment transmission systems. Multi-source power systems primarily rely on energy management strategies to control the power output of energy storage units during transport, maintaining the diesel generator within its high-efficiency range and thus achieving energy optimization.

[0003] Common optimization methods for multi-source power systems often employ energy management strategies based on deterministic logic rules to schedule energy among the power sources. This approach suffers from low accuracy and poor optimization performance. Some scholars have proposed energy management strategies using optimization algorithms, which allocate energy among the power sources through real-time calculation of the optimization objective. These methods offer better energy-saving performance compared to deterministic logic rule-based energy allocation strategies, but their computation time is too long, making them difficult to apply to real-time energy management of multi-source power systems. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for real-time optimization of energy scheduling of multi-source power systems, which can improve the energy-saving effect of multi-source power systems, reduce the amount of computation, and improve the dynamic response capability of multi-source power systems, so as to solve at least one of the technical problems existing in the background art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] On one hand, the present invention provides a method for real-time optimized energy scheduling of a multi-source power system, comprising:

[0007] Collect data on the operating conditions of the transport equipment;

[0008] Based on the collected operating conditions and the state of charge of the energy storage unit, the globally optimal output power of the diesel generator and the output power of the energy storage unit are calculated offline.

[0009] Based on the calculated globally optimal output power of the diesel generator and the output power of the energy storage unit, the energy distribution rule is obtained.

[0010] Based on the obtained energy allocation rules, energy scheduling is carried out for the multi-source power system.

[0011] Preferably, based on the typical operating conditions of the selected transport equipment, the state of charge (SOC) of the energy storage unit is used as the state variable, with a stage division step size of 0.0001, and calculated according to the following formula:

[0012]

[0013] The output power of the energy storage unit is selected as the decision variable. The decision at each stage constitutes a series of control variables, which are calculated according to the following formula:

[0014]

[0015] Among them, T s E represents the time step. ESS P represents the energy of the energy storage unit. ESS This indicates the output power of the energy storage unit.

[0016] Preferably, the state variable is transferred from the current stage to the next stage through decision-making, calculated according to the following formula:

[0017]

[0018] in, Let i represent the decision variable from state i to state j;

[0019] The iterative process of the calculation satisfies the following constraints:

[0020] P load =P DG +P ESS

[0021]

[0022] Among them, P load This indicates the typical operating condition of the selected transport equipment, i.e., the load power of the transport equipment; P DG This indicates the generator's output power.

[0023] Preferably, the objective function for calculating the output power of the diesel generator and the output power of the energy storage unit for the global optimal fuel consumption offline is: L(k)=F(x(k),u(k));

[0024] The loop conditions of the entire offline iterative computation are discretized into n stages, and the overall optimization objective is:

[0025]

[0026] The optimal energy distribution of the diesel generator and energy storage unit for the transport equipment under this typical operating condition was calculated.

[0027] Preferably, fuzzy logic rules are established using the load power of the vehicle and the SOC of the energy storage unit as input variables, and the output power of the generator as the output variable; the membership function of the fuzzy logic rules is:

[0028]

[0029] Where a represents the center value of the Gaussian function and b represents the width of the Gaussian function.

[0030] Preferably, the load power and state of charge dataset of the energy storage unit obtained through offline iterative calculation are used as the input set for training the optimization method, and the output power of the diesel generator obtained through offline iterative calculation is used as the output set for training the optimization method. The method undergoes five layers of processing, including:

[0031] In the first layer, the input set is blurred using a Gaussian function;

[0032] Each processing unit in the second layer is used to multiply the input signals, and the output of the processing unit represents the confidence level of the fuzzy logic rule.

[0033] Each processing unit in the third layer will normalize the input variables;

[0034] Each processing unit in the fourth layer is an adaptive adjustment process used to calculate the output of the fuzzy logic rules based on the output of the third layer;

[0035] The fifth layer is used to calculate the total output of the energy allocation rule optimization; where, once the forward parameters are determined, the output can be written as a linear combination of the backward parameters.

[0036] Secondly, the present invention provides a real-time optimized energy scheduling system for a multi-source power system, comprising:

[0037] The data acquisition module is used to collect the operating conditions of the transport equipment.

[0038] The first calculation module is used to calculate the globally optimal output power of the diesel generator and the output power of the energy storage unit offline, based on the collected operating conditions and the state of charge of the energy storage unit.

[0039] The second calculation module is used to calculate the energy distribution rules based on the globally optimal output power of the diesel generator and the output power of the energy storage unit.

[0040] The scheduling module is used to perform real-time energy scheduling of the multi-source power system according to the obtained energy allocation rules.

[0041] Thirdly, the present invention provides a non-transitory computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the real-time optimized energy scheduling method for a multi-source power system as described above.

[0042] Fourthly, the present invention provides a computer program product, including a computer program that, when run on one or more processors, is used to implement the real-time optimized energy scheduling method for a multi-source power system as described above.

[0043] Fifthly, the present invention provides an electronic device, comprising: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions for implementing the real-time optimized energy scheduling method for a multi-source power system as described above.

[0044] The beneficial effects of this invention are: low computational load, high reliability, and strong real-time performance; no complex real-time optimization calculations are required, and the training method is optimized based on the typical operating conditions of the transport equipment through offline iterative calculation results, thereby obtaining an energy allocation rule that can approximately replace the global optimization effect, thus realizing energy saving and emission reduction of multi-source power systems.

[0045] The advantages of additional aspects of the invention will be set forth more clearly in the following description or will be learned by practice of the invention. Attached Figure Description

[0046] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a schematic diagram of the real-time optimized energy scheduling method for a multi-source power system according to an embodiment of the present invention.

[0048] Figure 2 This is a flowchart of the offline global iterative optimization algorithm for energy allocation in a multi-source power system according to an embodiment of the present invention.

[0049] Figure 3 This is a schematic diagram of the energy allocation training and optimization algorithm for a multi-source power system according to an embodiment of the present invention. Detailed Implementation

[0050] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0051] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0052] It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless defined as here.

[0053] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, and / or groups thereof.

[0054] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0055] To facilitate understanding of the present invention, the present invention will be further explained and described below with reference to the accompanying drawings and specific embodiments. However, the specific embodiments do not constitute a limitation on the embodiments of the present invention.

[0056] Those skilled in the art should understand that the accompanying drawings are merely schematic diagrams of embodiments, and the components in the drawings are not necessarily essential for implementing the present invention.

[0057] Example 1

[0058] This embodiment 1 provides a real-time optimized energy scheduling system for a multi-source power system, including:

[0059] The data acquisition module is used to collect the operating conditions of the transport equipment.

[0060] The first calculation module is used to calculate the globally optimal output power of the diesel generator and the output power of the energy storage unit offline, based on the collected operating conditions and the state of charge of the energy storage unit.

[0061] The second calculation module is used to calculate the energy distribution rules based on the globally optimal output power of the diesel generator and the output power of the energy storage unit.

[0062] The scheduling module is used to perform energy scheduling for the multi-source power system based on the obtained energy allocation rules.

[0063] In this embodiment 1, the above-described system is used to implement a real-time optimized energy scheduling method for a multi-source power system, including:

[0064] Collect data on the operating conditions of the transport equipment;

[0065] Based on the collected operating conditions and the state of charge of the energy storage unit, the globally optimal output power of the diesel generator and the output power of the energy storage unit are calculated offline.

[0066] Based on the calculated globally optimal output power of the diesel generator and the output power of the energy storage unit, the energy distribution rule is obtained.

[0067] Based on the obtained energy allocation rules, energy scheduling is carried out for the multi-source power system.

[0068] Based on the selected typical operating conditions of the transport equipment, the State of Charge (SOC) of the energy storage unit is used as the state variable, with a stage division step size of 0.0001, and is calculated according to the following formula:

[0069]

[0070] The output power of the energy storage unit is selected as the decision variable. The decision at each stage constitutes a series of control variables, which are calculated according to the following formula:

[0071]

[0072] Among them, T s E represents the time step. ESS P represents the energy of the energy storage unit. ESS This indicates the output power of the energy storage unit.

[0073] The state variable is transferred from the current stage to the next stage through a decision, calculated according to the following formula:

[0074]

[0075] in, Let i represent the decision variable from state i to state j;

[0076] The iterative process of the calculation satisfies the following constraints:

[0077] P load =P DG +P ESS

[0078]

[0079] Among them, P load This indicates the typical operating condition of the selected transport equipment, i.e., the load power of the transport equipment; P DG This indicates the generator's output power.

[0080] The objective function for calculating the globally optimal diesel generator output power and energy storage unit output power offline is: L(k) = F(x(k), u(k));

[0081] The loop conditions of the entire offline iterative computation are discretized into n stages, and the overall optimization objective is:

[0082]

[0083] The optimal energy distribution of the diesel generator and energy storage unit for the transport equipment under this typical operating condition was calculated.

[0084] Using the load power of the vehicle and the SOC of the energy storage unit as input variables, and the output power of the generator as the output variable, fuzzy logic rules are established; the membership functions of the fuzzy logic rules are:

[0085]

[0086] Where a represents the center value of the Gaussian function and b represents the width of the Gaussian function.

[0087] The load power and state-of-charge dataset of the energy storage unit obtained through offline iterative calculation are used as the input set for training the optimization method, and the output power of the diesel generator obtained through offline iterative calculation is used as the output set for training the optimization method. The method undergoes five layers of processing, including:

[0088] In the first layer, the input set is blurred using a Gaussian function;

[0089] Each processing unit in the second layer is used to multiply the input signals, and the output of the processing unit represents the confidence level of the fuzzy logic rule.

[0090] Each processing unit in the third layer will normalize the input variables;

[0091] Each processing unit in the fourth layer is an adaptive adjustment process used to calculate the output of the fuzzy logic rules based on the output of the third layer;

[0092] The fifth layer is used to calculate the total output of the energy allocation rule optimization; where, once the forward parameters are determined, the output can be written as a linear combination of the backward parameters.

[0093] Example 2

[0094] This embodiment 2 provides a real-time optimized energy scheduling method for multi-source power systems. It eliminates the need for complex real-time optimization calculations and allows for the formulation of effective real-time energy scheduling strategies through offline training.

[0095] The real-time optimization energy scheduling method for multi-source power systems includes the following steps:

[0096] Select typical operating conditions of the transport equipment; based on the collected operating conditions and the SOC of the energy storage unit, calculate the globally optimal diesel generator output power and energy storage unit output power offline to optimize the target; based on the calculation results, train an energy allocation rule that approximates the global optimization result according to the optimization algorithm of this invention; perform real-time energy scheduling according to the trained rule.

[0097] Based on the selected typical operating conditions of the transport equipment, the SOC of the energy storage unit is used as the state variable, with a stage division step size of 0.0001, and is calculated according to the following formula:

[0098]

[0099] The output power of the energy storage unit is selected as the decision variable. The decision at each stage constitutes a series of control variables, which are calculated according to the following formula:

[0100]

[0101] Among them, T s This is the time step, typically set to 0.1s. ESS It is the energy of the energy storage unit; P ESS It is the output power of the energy storage unit.

[0102] The state variable is transferred from the current stage to the next stage through a decision, calculated according to the following formula:

[0103]

[0104] in, Decision variables from state i to state j.

[0105] The iterative calculation process satisfies certain constraints and is performed according to the following formula:

[0106] P load =P DG +P ESS (4)

[0107]

[0108] Among them, P load This refers to the typical operating conditions of the selected transport equipment; P DG It is the output power of the diesel generator;

[0109] The objective function is calculated as follows:

[0110] L(k)=F(x(k),u(k)) (6)

[0111] Where F(x(k),u(k)) is the objective function that needs to be optimized for the multi-source dynamic system.

[0112] The loop conditions of the entire offline iterative computation are discretized into n stages, and the overall optimization objective is calculated according to the following formula:

[0113]

[0114] The optimal energy distribution of the diesel generator and energy storage unit for the transport equipment under this typical operating condition was calculated.

[0115] The input variable is the load power (P) of the vehicle. load The input variables are the state of charge (SOC) of the energy storage unit and the output variable is the output power (P) of the diesel generator. DG As the output variable, the fuzzy logic rule table is established as shown in Table 1.

[0116] Table 1

[0117]

[0118] The membership function of a fuzzy rule is calculated according to the following formula:

[0119]

[0120] Where 'a' is the center value of the Gaussian function, and 'b' is the width of the Gaussian function. The values ​​of 'a' and 'b' for the membership functions of each layer are obtained using the training optimization method described below.

[0121] The load power (P) obtained from offline iterative calculation load The SOC dataset of the energy storage unit and the diesel generator are used as the input set for training the optimization method. The output power (P) of the diesel generator is obtained through offline iterative calculation. DG The output set of the training optimization method is processed through five layers:

[0122] First layer: The input set is fuzzified using a Gaussian function, and the output functions of processing units i and j are calculated according to the following formula:

[0123]

[0124] Among them, P load SOC(k) and SOC(k) are the input variables of processing units i and j. and These are the output variables of processing units i and j. a and b are called forward parameters, and their values ​​are determined by the training results of the training optimization method.

[0125] The second layer: Each processing unit multiplies the input signals, and the output of the processing unit represents the confidence level of the rule, calculated according to the following formula:

[0126]

[0127] The third layer: Each processing unit will normalize the input variables, calculated according to the following formula:

[0128]

[0129] Fourth layer: Each processing unit in this layer is an adaptive adjustment process used to calculate the output of the fuzzy rule, calculated according to the following formula:

[0130]

[0131]

[0132] in, It is the output variable of the third layer; {c i,0 ,c i,1 ,c i,2} is the parameter set of processing unit i, called the inverse parameter set. It is used to evaluate the training results of the training optimization method.

[0133] Fifth layer: This layer is used to calculate the total output of the training and optimization method, calculated according to the following formula:

[0134]

[0135] Once the forward parameters are determined, the output of the training optimization method can be written as a linear combination of the backward parameters, calculated according to the following formula:

[0136]

[0137] in,

[0138]

[0139] In summary, the optimized training method proposed in this embodiment combines an optimization algorithm with adaptive optimization of the forward and backward parameters. When the difference between the energy allocation result calculated by the optimized training method and the energy allocation result calculated offline iteratively is less than 2%, the optimized training method is considered reasonable. The fuzzy rules obtained by the optimized training method are then applied to the real-time energy allocation of the transport equipment, approximating the effect of global optimization.

[0140] The method provided in this embodiment does not require complex real-time optimization calculations. Instead, it optimizes the training method based on offline iterative calculation results according to the typical operating conditions of the transport equipment, thereby obtaining an energy allocation rule that can approximately replace the effect of global optimization, thus achieving energy conservation and emission reduction in multi-source power systems. This technical solution has the advantages of low computational load, high reliability, and strong real-time performance.

[0141] Example 3

[0142] like Figure 1 As shown in the figure, this embodiment 3 provides a method for real-time optimized energy scheduling of a multi-source power system, including the following steps:

[0143] S1. First, perform an offline global iterative optimization algorithm for energy allocation in a multi-source power system.

[0144] like Figure 2 As shown. The offline global iterative optimization algorithm for energy allocation in a multi-source power system includes the following steps: selecting typical operating conditions of the transport equipment; calculating the globally optimal diesel generator output power and energy storage unit output power offline, with the goal of minimizing fuel consumption, based on the collected operating conditions and the SOC of the energy storage unit; training an energy allocation rule that approximates the global optimization result according to the optimization algorithm of this invention based on the calculation results; and performing real-time energy scheduling based on the trained rule.

[0145] Based on the selected typical operating conditions of the transport equipment, the SOC of the energy storage unit is used as the state variable, with a stage division step size of 0.0001, and is calculated according to the following formula:

[0146]

[0147] The output power of the energy storage unit is selected as the decision variable. The decision at each stage constitutes a series of control variables, which are calculated according to the following formula:

[0148]

[0149] Among them, T s This is the time step, typically set to 0.1 sE. ESS It is the energy of the energy storage unit; P ESS It is the output power of the energy storage unit.

[0150] The state variable is transferred from the current stage to the next stage through a decision, calculated according to the following formula:

[0151]

[0152] in, Decision variables from state i to state j.

[0153] The iterative calculation process satisfies certain constraints and is performed according to the following formula:

[0154] P load =P DG +P ESS (4)

[0155]

[0156] Among them, P load This refers to the typical operating conditions of the selected transport equipment; P DG This refers to the output power of the diesel generator.

[0157] In this embodiment 3, the objective function is the fuel consumption of the diesel generator, calculated according to the following formula: L(k)=FC(k)=FC DG (x(k),u(k)) (6)

[0158] Among them, FC DG This refers to the fuel consumption of a diesel generator, which can be obtained from the output characteristics of the diesel generator.

[0159] The loop conditions of the entire offline iterative computation are discretized into n stages, and the overall optimization objective is calculated according to the following formula:

[0160]

[0161] The optimal energy distribution of the diesel generator and energy storage unit for the transport equipment under this typical operating condition was calculated.

[0162] S2. Then, train and optimize the energy allocation algorithm for the multi-source power system.

[0163] like Figure 3 As shown, the specific steps are as follows:

[0164] The load power (P) of the transport vehicle load The output power (P) of the diesel generator and the SOC of the energy storage unit are used as input variables for training the optimization algorithm. DG As the output variable for training the optimization algorithm, the fuzzy logic rule table is established as shown in Table 2.

[0165] Table 2

[0166]

[0167] The membership function of a fuzzy rule is calculated according to the following formula:

[0168]

[0169] Where 'a' is the center value of the Gaussian function, and 'b' is the width of the Gaussian function. The values ​​of 'a' and 'b' for the membership functions of each layer are obtained using the training optimization method described below.

[0170] The load power (P) obtained from offline iterative calculation load The SOC dataset of the energy storage unit and the diesel generator are used as the input set for training the optimization method. The output power (P) of the diesel generator is obtained through offline iterative calculation. DG The output set of the training optimization method is processed through five layers:

[0171] First layer: The input set is fuzzified using a Gaussian function, and the output functions of processing units i and j are calculated according to the following formula:

[0172]

[0173] Among them, P load SOC(k) and SOC(k) are the input variables of processing units i and j. and These are the output variables of processing units i and j. a and b are called forward parameters, and their values ​​are determined by the training results of the training optimization method.

[0174] The second layer: Each processing unit multiplies the input signals, and the output of the processing unit represents the confidence level of the rule, calculated according to the following formula:

[0175]

[0176] The third layer: Each processing unit will normalize the input variables, calculated according to the following formula:

[0177]

[0178] Fourth layer: Each processing unit in this layer is an adaptive adjustment process used to calculate the output of the fuzzy rule, calculated according to the following formula:

[0179]

[0180]

[0181] in, It is the output variable of the third layer; {c i,0 ,c i,1 ,ci,2} is the parameter set of processing unit i, called the inverse parameter set. It is used to evaluate the training results of the training optimization method.

[0182] Fifth layer: This layer is used to calculate the total output of the training and optimization method, calculated according to the following formula:

[0183]

[0184] Once the forward parameters are determined, the output of the training optimization method can be written as a linear combination of the backward parameters, calculated according to the following formula:

[0185]

[0186] in,

[0187]

[0188] In this embodiment, the forward and backward parameters of the training method are adaptively optimized by combining a backpropagation neural network and a least quadratic algorithm. The optimized training method is considered reasonable when the difference between the energy allocation result calculated by the optimized training method and the energy allocation result calculated offline iteratively is less than 2%.

[0189] S3. Finally, the fuzzy rules obtained by the optimized training method are applied to the real-time energy allocation of the transport equipment to approximate the optimization effect of minimizing global fuel consumption.

[0190] Example 4

[0191] Embodiment 4 of the present invention provides a non-transitory computer-readable storage medium for storing computer instructions. When executed by a processor, the computer instructions implement a real-time optimized energy scheduling method for a multi-source power system. The method includes:

[0192] Collect data on the operating conditions of the transport equipment;

[0193] Based on the collected operating conditions and the state of charge of the energy storage unit, the globally optimal output power of the diesel generator and the output power of the energy storage unit are calculated offline.

[0194] Based on the calculated globally optimal output power of the diesel generator and the output power of the energy storage unit, the energy distribution rule is obtained.

[0195] Based on the obtained energy allocation rules, energy scheduling is carried out for the multi-source power system.

[0196] Example 5

[0197] Embodiment 5 of the present invention provides a computer program (product), including a computer program that, when run on one or more processors, is used to implement a real-time optimized energy scheduling method for a multi-source power system. The method includes:

[0198] Collect data on the operating conditions of the transport equipment;

[0199] Based on the collected operating conditions and the state of charge of the energy storage unit, the globally optimal output power of the diesel generator and the output power of the energy storage unit are calculated offline.

[0200] Based on the calculated globally optimal output power of the diesel generator and the output power of the energy storage unit, the energy distribution rule is obtained.

[0201] Based on the obtained energy allocation rules, energy scheduling is carried out for the multi-source power system.

[0202] Example 6

[0203] Embodiment 6 of the present invention provides an electronic device, including: a processor, a memory, and a computer program; wherein, the processor is connected to the memory, and the computer program is stored in the memory. When the electronic device is running, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions for implementing a real-time optimized energy scheduling method for a multi-source power system, the method including:

[0204] Collect data on the operating conditions of the transport equipment;

[0205] Based on the collected operating conditions and the state of charge of the energy storage unit, the globally optimal output power of the diesel generator and the output power of the energy storage unit are calculated offline.

[0206] Based on the calculated globally optimal output power of the diesel generator and the output power of the energy storage unit, the energy distribution rule is obtained.

[0207] Based on the obtained energy allocation rules, energy scheduling is carried out for the multi-source power system.

[0208] In summary, the real-time optimized energy scheduling method for multi-source power systems provided by this invention achieves more accurate and effective energy scheduling by calculating the optimal result offline and training optimized energy allocation rules. Compared with energy management strategies based on logical rules, it improves the optimization effect; compared with energy management strategies based on optimization algorithms, it reduces the computational load and improves the dynamic response capability of multi-source power systems.

[0209] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0210] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0211] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0212] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment, whereby a series of operational steps are performed to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0213] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that, based on the technical solutions disclosed in the present invention, various modifications or variations that can be made by those skilled in the art without creative effort should be included within the scope of protection of the present invention.

Claims

1. A method for real-time optimized energy scheduling of a multi-source power system, characterized in that, include: Collect data on the operating conditions of the transport equipment; Based on the collected operating conditions and the state of charge of the energy storage unit, the globally optimal output power of the diesel generator and the output power of the energy storage unit are calculated offline. Based on the calculated globally optimal output power of the diesel generator and the output power of the energy storage unit, the energy distribution rule is obtained. Based on the obtained energy allocation rules, real-time energy scheduling of the multi-source power system is carried out. The objective function for offline calculation of the globally optimal diesel generator output power and energy storage unit output power is: Where x(k) represents the state of charge of the energy storage unit at time k, u(k) represents the output power of the energy storage unit at time k; F() represents the objective function based on the state variable x(k) and the decision variable u(k); L(k) represents the fuel consumption at time k; Discretize the loop conditions of the entire offline iterative calculation as follows: The overall optimization goal for each stage is: Among them, T s Indicates the time step; The optimal energy distribution results of the diesel generator and energy storage unit for the transport equipment under this typical operating condition were calculated. Based on the load power of the vehicle and the energy storage unit Using the generator's output power as the input variable and the generator's output power as the output variable, fuzzy logic rules are established; the membership function of the fuzzy logic rules is: Where a represents the center value of the Gaussian function; b represents the width of the Gaussian function; and exp represents the natural exponential function. Describes a membership function; The load power and state-of-charge dataset of the energy storage unit obtained through offline iterative calculation are used as the input set for training the optimization method, and the output power of the diesel generator obtained through offline iterative calculation is used as the output set for training the optimization method. The method undergoes five layers of processing, including: In the first layer, the input set is blurred using a Gaussian function; Each processing unit in the second layer is used to multiply the input signals, and the output of the processing unit represents the confidence level of the fuzzy logic rule. Each processing unit in the third layer will normalize the input variables; Each processing unit in the fourth layer is an adaptive adjustment process used to calculate the output of the fuzzy logic rules based on the output of the third layer; The fifth layer is used to calculate the total output of the energy allocation rule optimization; where, once the forward parameters are determined, the output can be written as a linear combination of the backward parameters; Among them, the state of charge of the energy storage unit is adopted according to the typical operating conditions of the selected transport equipment. As a state variable, the stage division step size is 0.0001, calculated according to the following formula: SOC(k) represents the state of charge of the energy storage unit at time k; The output power of the energy storage unit is selected as the decision variable. The decision at each stage constitutes a series of control variables, which are calculated according to the following formula: ;P ESS (k) represents the output power of the energy storage unit at time k; E ESS This indicates the energy of the energy storage unit; The state variable is transferred from the current stage to the next stage through a decision, calculated according to the following formula: ;in, The decision variable represents the transition from state i to state j, i.e., the output power of the energy storage unit from state i to state j; SOC i The state variable representing state i is the state of charge of the energy storage unit in state i; SOC j This represents the state variable in state j, i.e., the charge state of the energy storage unit in state j. The iterative process of the calculation satisfies the following constraints: Among them, P load This indicates the typical operating condition of the selected transport equipment, i.e., the load power of the transport equipment; P DG P represents the generator's output power; ESS Indicates the output power of the energy storage unit; ； Where SOC represents the state of charge of the energy storage unit; min State of Charge (SOC) represents the minimum value of the energy storage unit's state of charge. max P represents the maximum value of the state of charge of the energy storage unit; DGmin P represents the minimum output power of the generator; DGmax P represents the maximum output power of the generator; ESSmin P represents the minimum output power of the energy storage unit. ESSmax This indicates the maximum output power of the energy storage unit.

2. A real-time optimized energy dispatching system for a multi-source power system based on the method described in claim 1, characterized in that, include: The data acquisition module is used to collect the operating conditions of the transport equipment. The first calculation module is used to calculate the globally optimal output power of the diesel generator and the output power of the energy storage unit offline, based on the collected operating conditions and the state of charge of the energy storage unit. The second calculation module is used to calculate the energy distribution rules based on the globally optimal output power of the diesel generator and the output power of the energy storage unit. The scheduling module is used to perform real-time energy scheduling of the multi-source power system according to the obtained energy allocation rules.

3. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium is used to store computer instructions, which, when executed by a processor, implement the real-time optimized energy scheduling method for a multi-source power system as described in claim 1.

4. A computer program product, characterized in that, It includes a computer program, which, when run on one or more processors, is used to implement the real-time optimized energy scheduling method for a multi-source power system as described in claim 1.

5. An electronic device, characterized in that, include: The device includes a processor, a memory, and a computer program; wherein the processor is connected to the memory, and the computer program is stored in the memory. When the electronic device is running, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions that implement the real-time optimized energy scheduling method for a multi-source power system as described in claim 1.

Images