A port-ship multi-energy fusion system and multi-level energy management method thereof

By using neural network prediction model and minimum equivalent fuel consumption method in port-ship multi-energy fusion system, the problem of uncertainty in ship pollution and energy management of traditional internal combustion engines is solved, and hydrogen storage quantity decisions are achieved on a long time scale and energy source optimization improves the energy utilization efficiency of the system.

CN115693727BActive Publication Date: 2024-12-03NINGBO ZHOUSHAN PORT GRP CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202211436803.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-11-16
Publication Date
2024-12-03
Estimated Expiration
2042-11-16

AI Technical Summary

Technical Problem

Traditional internal combustion engine ships release greenhouse gases and harmful gases when they arrive at the port, and there are uncertainties in wind, photoelectric power production and ship load, which brings challenges to the energy management of multi-energy fusion systems.

Method used

A port-ship multi-energy fusion system was designed, including load modules, new energy modules, energy storage modules and energy management modules. The neural network prediction model is used to predict the power generation and load of each energy source, and the minimum equivalent fuel consumption is used. The method is to make real-time optimization decisions to determine the energy distribution of electricity and hydrogen energy loads.

Benefits of technology

The hydrogen storage quantity decision on a longer time scale and the real-time optimal decisions of each energy source are achieved, which reduces the uncertainty of pollution and energy management and improves the energy utilization efficiency of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115693727B_ABST
    Figure CN115693727B_ABST
Patent Text Reader

Abstract

The present invention discloses a port-ship multi-energy fusion system and a multi-level energy management method thereof, including a load module, a new energy module, an energy storage module and an energy management module; the load module includes an electric load and a hydrogen load of a port; the new energy module includes a wind power generation module and a photovoltaic power generation module for supplying power to the electric load; the energy storage module includes an electrochemical energy storage module, a hydrogen energy storage module and a hydrogen production device, and the hydrogen energy storage module is used to supply hydrogen to the hydrogen energy load; the energy management module includes a prediction layer, and the prediction layer predicts the power generation of the wind power generation module, the power generation of the photovoltaic power generation module, the load of the electric load and the load of the hydrogen energy load respectively through a neural network prediction model, and determines the power storage capacity of the electrochemical energy storage module and the hydrogen storage capacity of the hydrogen energy storage module. The present invention can determine the hydrogen storage capacity on a longer time scale and the real-time optimal decision of each energy source.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of multi-energy fusion and management technology, and in particular to a port-ship multi-energy fusion system and a multi-level energy management method thereof. Background Art

[0002] The shipping industry plays a vital role in social and economic development, and its impact on the port environment has also received increasing attention. Traditional internal combustion engine ships release greenhouse gases such as CO2 and harmful gases such as SO2 and NOX when docked, which has an adverse impact on the climate and the health of residents around the port. Clean energy represented by solar energy, wind energy and hydrogen energy can be converted into electric energy required for industrial production through certain technologies, and can achieve zero emissions of harmful gases and substances. Therefore, the use of a port-ship multi-energy fusion system consisting of wind, light, storage and hydrogen in the port to power docked ships and port machinery and equipment can reduce pollution. However, there is uncertainty in the power generation of wind and light energy and the load of docked ships at the port, which brings certain challenges to the energy management of the multi-energy fusion system. Summary of the invention

[0003] In order to solve at least one of the technical problems mentioned in the background technology, the purpose of the present invention is to provide a port-ship multi-energy fusion system and a multi-level energy management method thereof, which can determine the hydrogen storage capacity on a longer time scale and the real-time optimal decision of each energy source.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A port-ship multi-energy fusion system, comprising a load module, a new energy module, an energy storage module and an energy management module;

[0006] The load module includes the port's electrical load and hydrogen energy load;

[0007] The new energy module includes a wind power generation module and a photovoltaic power generation module, which are used to supply power to the electrical load;

[0008] The energy storage module includes an electrochemical energy storage module, a hydrogen energy storage module and a hydrogen production device, and the hydrogen energy storage module is used to supply hydrogen to the hydrogen energy load;

[0009] The energy management module includes a prediction layer, which predicts the power generation of the wind power generation module, the power generation of the photovoltaic power generation module, the load of the electric load and the load of the hydrogen energy load through a neural network prediction model, and determines the power storage capacity of the electrochemical energy storage module and the hydrogen storage capacity of the hydrogen energy storage module.

[0010] Furthermore, it also includes a busbar, and the wind power generation module and the photovoltaic power generation module are connected to the power load via the busbar.

[0011] Furthermore, it also includes an external hydrogen refueling station for supplying hydrogen to the hydrogen energy load when the hydrogen energy storage module does not store enough hydrogen.

[0012] Furthermore, it also includes an external power grid for supplying power to the power load when the wind power generation module, the photovoltaic power generation module, and the electrochemical energy storage module jointly provide insufficient power.

[0013] Furthermore, the energy management module also includes a real-time optimization layer, which uses the minimum equivalent fuel consumption method to make trial decisions on the energy flow of the new energy module and the energy storage module to determine the energy allocated to the power load and the hydrogen energy load.

[0014] A multi-level energy management method for a port-ship multi-energy fusion system comprises the following steps:

[0015] S1. Use the trained neural network prediction model to predict the power generation of the wind power generation module, the power generation of the photovoltaic power generation module, the load of the power load and the load of the hydrogen energy load in the next cycle respectively;

[0016] S2. Calculate the first difference between the sum of the power generation of the wind power generation module and the power generation of the photovoltaic power generation module and the load of the power load; if the first difference is greater than 0, in the next cycle, the power corresponding to the first difference is allocated to the hydrogen production device for hydrogen production or stored in the electrochemical energy storage module and enter S3; otherwise, in the next cycle, the power corresponding to the first difference is dispatched from the electrochemical energy storage module to supply power to the power load;

[0017] S3. Calculate the amount of electricity required to produce the predicted hydrogen energy load according to the electric energy-hydrogen conversion rate of the hydrogen production device, and calculate the second difference between the first difference and the required amount of electricity; if the second difference is greater than 0, store the amount of electricity of the second difference in the electrochemical energy storage module, and distribute the amount of electricity required for the predicted hydrogen energy load to the hydrogen production module; if the second difference is less than 0, draw the amount of electricity corresponding to the second difference from the electrochemical energy storage module to the hydrogen production module for hydrogen production;

[0018] S4, in the operation stage of the next cycle, the power generation of the wind power generation module, the power generation of the photovoltaic power generation module, the output power of the electrochemical energy storage module, and the output hydrogen of the hydrogen energy storage module are collected in real time;

[0019] S5, converting the power generation of the wind power generation module, the power generation of the photovoltaic power generation module, the output power of the electrochemical energy storage module, and the output hydrogen of the hydrogen energy storage module into equivalent fuel consumption respectively;

[0020] S6, constructing an optimal equation to solve the sum of equivalent fuel consumption of the power generation of the wind power generation module, the power generation of the photovoltaic power generation module, the output power of the electrochemical energy storage module, and the output hydrogen of the hydrogen energy storage module to determine the energy provided by the wind power generation module, the photovoltaic power generation module, the electrochemical energy storage module, and the hydrogen energy storage module to the electrical load or the hydrogen energy load.

[0021] Furthermore, the training method of the neural network prediction model includes the following steps:

[0022] S11, split time period;

[0023] S12, constructing an array, each set of data including the power generation of the wind power generation module / the power generation of the photovoltaic power generation module / the load of the electric load / the load of the hydrogen energy load in each cycle and the influencing parameter information of the power generation of the wind power generation module / the power generation of the photovoltaic power generation module / the load of the electric load / the load of the hydrogen energy load in the previous cycle;

[0024] S13, collecting a number of the arrays to construct a training set;

[0025] S14, inputting the training sets into corresponding neural network prediction models for training.

[0026] A terminal device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the multi-level energy management method of the port-ship multi-energy fusion system as described above is implemented.

[0027] A computer storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, the multi-level energy management method of the port-ship multi-energy fusion system as described above is implemented.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] The present invention can determine the amount of hydrogen storage over a longer time scale by predicting the power generation of the wind power generation module, the power generation of the photovoltaic power generation module, the load of the electric load and the load of the hydrogen energy load; on the other hand, the minimum equivalent fuel consumption method is used to make real-time optimal decisions on the energy flow of the wind power generation module, the photovoltaic power generation module, the electrochemical energy storage module and the hydrogen energy storage module in the system, and the energy provided by each energy source to the electric load or the hydrogen energy load can be determined. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a system framework diagram of the present invention.

[0031] Figure 2 It is a flow chart of the multi-level energy management method of the present invention.

[0032] Figure 3 This is a flow chart of the training method of the neural network prediction model of the present invention. DETAILED DESCRIPTION

[0033] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] Embodiment 1:

[0035] See also Figure 1 , This embodiment provides a port-ship multi-energy fusion system, including a load module, a new energy module, an energy storage module and an energy management module;

[0036] The load module includes the port's electrical load and hydrogen energy load;

[0037] The electrical load is equipment driven by electricity, including lighting equipment, bridge cranes, gantry cranes, etc.; the hydrogen energy load is equipment driven by hydrogen, including hydrogen-powered container trucks, hydrogen-powered forklifts, hydrogen-powered stackers, etc.

[0038] The new energy module includes a wind power generation module and a photovoltaic power generation module for supplying power to the power load; and also includes a bus bar, through which the wind power generation module and the photovoltaic power generation module are connected to the power load.

[0039] The energy storage module includes an electrochemical energy storage module, a hydrogen energy storage module and a hydrogen production device, wherein the electrochemical energy storage module is responsible for short-term energy storage, and the hydrogen energy storage module is responsible for long-term energy storage and is used to supply hydrogen to the hydrogen energy load;

[0040] The energy management module includes a prediction layer, which predicts the power generation of the wind power generation module, the power generation of the photovoltaic power generation module, the load of the electric load and the load of the hydrogen energy load through a neural network prediction model, and determines the storage capacity of the electrochemical energy storage module and the storage capacity of the hydrogen energy storage module. Thus, the hydrogen storage capacity and the storage capacity of the energy storage module are determined under the condition of meeting the energy consumption, and hydrogen is prepared by the surplus power generation of wind energy and light energy.

[0041] It also includes an external energy module, wherein the external energy module includes at least one of an external hydrogen refueling station and an external power grid.

[0042] The external hydrogen refueling station is used to supply hydrogen to the hydrogen energy load when the hydrogen energy storage module does not store enough hydrogen.

[0043] The external power grid is used to supply power to the power load when the wind power generation module, the photovoltaic power generation module, and the electrochemical energy storage module provide insufficient power together.

[0044] Since the prediction layer does not take into account the uncertainty of real-time energy consumption, in another embodiment, the energy management module also includes a real-time optimization layer, which uses the minimum equivalent fuel consumption method to make trial decisions on the energy flow of the new energy module and the energy storage module to determine the energy allocated to the power load and the hydrogen energy load.

[0045] Embodiment 2:

[0046] This embodiment provides a multi-level energy management method for the port-ship multi-energy fusion system based on the first embodiment, such as Figure 2 As shown, the following steps are included:

[0047] S1. Use the trained neural network prediction model to predict the power generation of the wind power generation module, the power generation of the photovoltaic power generation module, the load of the power load and the load of the hydrogen energy load in the next cycle respectively;

[0048] S2. Calculate the power generation P of the wind power generation module 风 , the power generation capacity of photovoltaic power generation module P 光 The sum of P 风 +P 光 The load P of the power load 电负荷 The first difference (P 风 +P 光 -P 电负荷 ), recorded as ΔP1; if the first difference ΔP1 is greater than 0, it means that the total power generation of the wind power generation module and the photovoltaic power generation module is sufficient to supply the load of the power load, and the power corresponding to the first difference ΔP1 is allocated to the hydrogen production device for hydrogen production or stored in the electrochemical energy storage module in the next cycle and enters S3; otherwise, it means that the total power generation of the wind power generation module and the photovoltaic power generation module is sufficient to supply the load of the power load, and the power corresponding to the first difference ΔP1 is dispatched from the electrochemical energy storage module in the next cycle to supply power to the power load.

[0049] S3. Calculate the predicted hydrogen load Q according to the electricity-hydrogen conversion rate of the hydrogen production device. 氢负荷 The power required P 氢负荷 , that is, P 氢负荷 =Q 氢负荷 / t; wherein t is the electric energy-to-hydrogen conversion rate of the hydrogen production device of the present invention, which is obtained based on historical conversion data statistics.

[0050] And calculate the first difference ΔP1 and the required power P 氢负荷If the second difference is greater than 0, it means that the excess power ΔP1 obtained in S2 is sufficient to be converted into the amount of hydrogen required by the hydrogen energy load, and the power of the second difference is stored in the electrochemical energy storage module. At this time, the power required by the load corresponding to the predicted hydrogen energy load P 氢负荷 Allocated to the hydrogen production module for hydrogen production; if the second difference ΔP2 is less than 0, it means that the excess electricity ΔP1 obtained in S2 is not enough to be converted into the amount of hydrogen required by the hydrogen energy load. At this time, it is necessary to draw the electricity corresponding to the second difference ΔP2 from the electrochemical energy storage module to the hydrogen production module for hydrogen production, so as to meet the supply of hydrogen required by the hydrogen energy load.

[0051] S4. In the next cycle of operation, the power generation P′ of the wind power generation module is collected in real time 风 , the power generation of photovoltaic power generation module P′ 光 As well as the output power of the electrochemical energy storage module and the output hydrogen volume Q of the hydrogen energy storage module 氢能储能 ;

[0052] S5, the power generation amount P′ of the wind power generation module 风 , the power generation of photovoltaic power generation module P′ 光 And the output power P′ of the electrochemical energy storage module 电化学储能 , the output hydrogen volume Q of hydrogen energy storage module 氢能储能 Converted to equivalent fuel consumption T for supplying power to electric load or hydrogen load respectively ij ; Wherein, the subscript i represents the type of energy, i = 1, 2, 3, 4, respectively represents the power generation P' of the aforementioned wind power generation module 风 , the power generation of photovoltaic power generation module P′ 光 And the output power P′ of the electrochemical energy storage module 电化学储能 、Hydrogen output of hydrogen energy storage module Q 氢能储能 ; The subscript j represents the object of the function, that is, j=1 represents supplying energy to the electric load, and j=2 represents supplying energy to the hydrogen energy load.

[0053] It should be noted that the power generation of the wind power generation module, the power generation of the photovoltaic power generation module and the output power of the electrochemical energy storage module cannot directly power the hydrogen energy load, so there is no corresponding equivalent fuel consumption; similarly, the hydrogen energy storage module cannot function as an electrical load, and the corresponding equivalent fuel consumption does not exist.

[0054] For example: 11 It represents the equivalent fuel consumption of the wind power module's power generation to supply power loads.

[0055] In this scheme, the conversion of equivalent fuel consumption is achieved by the following method:

[0056] For each type of load j (including electric load and hydrogen energy load), obtain the energy consumption S of each type of energy i to achieve the rated workload when it supplies energy to it alone: ij For example, for a bridge crane (power load), the energy consumption required to move 100 tons of cargo when the wind power module is used alone;

[0057] Obtain the fuel consumption S required to achieve the same rated workload as the fuel-powered load 燃油 ; The data can be obtained from a database or by experimental testing;

[0058] Calculate the equivalent fuel factor α of each type of energy i supplying each type of load j ij , that is, α ij =S 燃油 / S ij ;

[0059] The energy supply P of the wind power generation module, photovoltaic power generation module, electrochemical energy storage module, and hydrogen energy storage module to load j obtained by S5 ij Multiplying by the corresponding equivalent fuel factor can get the corresponding equivalent fuel consumption T ij .

[0060] S6, constructing an optimal equation to solve the sum of equivalent fuel consumption of the power generation of the wind power generation module, the power generation of the photovoltaic power generation module, the output power of the electrochemical energy storage module, and the output hydrogen of the hydrogen energy storage module to determine the energy provided by the wind power generation module, the photovoltaic power generation module, the electrochemical energy storage module, and the hydrogen energy storage module to the electrical load or the hydrogen energy load.

[0061] The specific situations are as follows:

[0062] 1. When the first difference ΔP1 calculated in S2 is greater than 0, it means that the total power generation of the wind power generation module and the photovoltaic power generation module is sufficient to supply the load of the power load, so the equivalent fuel consumption of the power load can be optimized between the two. Similarly, although the energy supply to the hydrogen energy load can only be carried out by the hydrogen energy storage module, the amount of hydrogen required by the hydrogen energy storage module comes from the power supply of the other three modules, which involves the power-hydrogen conversion rate t of the hydrogen production device; therefore, in this case, the optimal equation for the total equivalent fuel consumption of this scheme is as follows:

[0063]

[0064] P 11 +P 12 ≤P′ 风

[0065] P 21 +P 22 ≤P′光

[0066] P 32 ≤P′ 电化学储能

[0067] Q 42 ≤Q 氢能储能

[0068] Among them, J min is the minimum equivalent fuel consumption, P i1 Energy type i corresponds to the power supply of the power load; and P i2 is the energy supply of energy type i corresponding to the hydrogen energy load, specifically the amount of electricity supplied to the hydrogen production device by the wind power generation module, photovoltaic power generation module or electrochemical energy storage module; t is the electricity-to-hydrogen conversion rate of the hydrogen production device; Q 42 is the hydrogen supply of the hydrogen energy storage module corresponding to the hydrogen energy load; α i1 (i=1, 2, 3) is the equivalent fuel factor of the wind power generation module and the photovoltaic power generation module supplying power to the power load separately; α 42 The equivalent fuel factor of the hydrogen energy storage module supplying hydrogen to the hydrogen energy load alone; P′ 风 , P′ 光 , P′ 电化学储能 , Q 氢能储能 They respectively represent the power generation of the wind power generation module, the power generation of the photovoltaic power generation module, the output power of the electrochemical energy storage module, and the output hydrogen of the hydrogen energy storage module during this cycle.

[0069] 2. When the first difference ΔP1 calculated in S2 is less than 0, compared with the first case, the difference is that the energy source for powering the power load is not limited to the wind power generation module and the photovoltaic power generation module, but also includes the electrochemical energy storage module; while the energy for supplying the hydrogen production device only comes from the electrochemical energy storage module. Therefore, in this case, the optimal equation for the sum of equivalent fuel consumption of this scheme changes as follows:

[0070]

[0071] P 11 ≤P′ 风

[0072] P 21 ≤P′ 光

[0073] P 31 +P 32 ≤P′ 电化学储能

[0074] Q 42 ≤Q 氢能储能

[0075] like Figure 3 As shown, the training method of the neural network prediction model includes the following steps:

[0076] S11, split time period;

[0077] S12, constructing an array, each set of data including the power generation of the wind power generation module / the power generation of the photovoltaic power generation module / the load of the electric load / the load of the hydrogen energy load in each cycle and the influencing parameter information of the power generation of the wind power generation module / the power generation of the photovoltaic power generation module / the load of the electric load / the load of the hydrogen energy load in the previous cycle;

[0078] Taking the photovoltaic power generation module as an example, its influencing parameter information includes climate information (such as light, temperature), the angle of the solar panel;

[0079] Similarly, the influencing parameter information of the wind power generation module includes climate information (wind power);

[0080] The load influencing parameter information of the power load includes the type and tonnage of the power load (such as a ship) to be docked;

[0081] S13, collecting a number of the arrays to construct a training set;

[0082] S14, inputting the training sets into corresponding neural network prediction models for training.

[0083] Embodiment three:

[0084] A terminal device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the multi-level energy management method of the port-ship multi-energy fusion system as described in Example 2 is implemented.

[0085] Embodiment 4:

[0086] A computer storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, the multi-level energy management method of the port-ship multi-energy fusion system as described in Example 2 is implemented.

[0087] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, the embodiments should be considered exemplary and non-restrictive in all respects, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims be included in the present invention.

Claims

1. A multi-level energy management method based on port-ship multi-energy fusion system, It is characterized in that The port-ship multi-energy fusion system includes a load module, a new energy module, an energy storage module and an energy management module; The load module includes the port's electrical load and hydrogen energy load; The new energy module includes a wind power generation module and a photovoltaic power generation module, which are used to supply power to the electrical load; The energy storage module includes an electrochemical energy storage module, a hydrogen energy storage module and a hydrogen production device, and the hydrogen energy storage module is used to supply hydrogen to the hydrogen energy load; The energy management module includes a prediction layer, which predicts the power generation of the wind power generation module, the power generation of the photovoltaic power generation module, the load of the electric load and the load of the hydrogen energy load respectively through a neural network prediction model, and determines the power storage capacity of the electrochemical energy storage module and the hydrogen storage capacity of the hydrogen energy storage module; The energy management module also includes a real-time optimization layer, which uses the minimum equivalent fuel consumption method to make real-time decisions on the energy flow of the new energy module and the energy storage module to determine the energy allocated to the power load and the hydrogen energy load; The multi-level energy management method comprises the following steps: S1. Use the trained neural network prediction model to predict the power generation of the wind power generation module, the power generation of the photovoltaic power generation module, the load of the power load and the load of the hydrogen energy load in the next cycle respectively; S2. Calculate the first difference between the sum of the power generation of the wind power generation module and the power generation of the photovoltaic power generation module and the load of the power load; if the first difference is greater than 0, in the next cycle, the power corresponding to the first difference is allocated to the hydrogen production device for hydrogen production or stored in the electrochemical energy storage module and enter S3; otherwise, in the next cycle, the power corresponding to the first difference is dispatched from the electrochemical energy storage module to supply power to the power load; S3. Calculate the amount of electricity required to produce the predicted hydrogen energy load according to the electric energy-hydrogen conversion rate of the hydrogen production device, and calculate the second difference between the first difference and the required amount of electricity; if the second difference is greater than 0, store the amount of electricity of the second difference in the electrochemical energy storage module, and distribute the amount of electricity required for the predicted hydrogen energy load to the hydrogen production module; if the second difference is less than 0, draw the amount of electricity corresponding to the second difference from the electrochemical energy storage module to the hydrogen production module for hydrogen production; S4, in the operation stage of the next cycle, the power generation of the wind power generation module, the power generation of the photovoltaic power generation module, the output power of the electrochemical energy storage module, and the output hydrogen of the hydrogen energy storage module are collected in real time; S5, converting the power generation of the wind power generation module, the power generation of the photovoltaic power generation module, the output power of the electrochemical energy storage module, and the output hydrogen of the hydrogen energy storage module into equivalent fuel consumption respectively; S6, constructing an optimal equation to solve the sum of equivalent fuel consumption of the power generation of the wind power generation module, the power generation of the photovoltaic power generation module, the output power of the electrochemical energy storage module, and the output hydrogen of the hydrogen energy storage module to determine the energy provided by the wind power generation module, the photovoltaic power generation module, the electrochemical energy storage module, and the hydrogen energy storage module to the electrical load or the hydrogen energy load.

2. According to claim 1, a multi-level energy management method for a port-ship multi-energy fusion system, It is characterized in that The training method of the neural network prediction model comprises the following steps: S11, split time period; S12, constructing an array, each set of data including the power generation of the wind power generation module / the power generation of the photovoltaic power generation module / the load of the electric load / the load of the hydrogen energy load in each cycle and the influencing parameter information of the power generation of the wind power generation module / the power generation of the photovoltaic power generation module / the load of the electric load / the load of the hydrogen energy load in the previous cycle; S13, collecting a number of the arrays to construct a training set; S14, inputting the training sets into corresponding neural network prediction models for training.

3. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the multi-level energy management method for the port-ship multi-energy fusion system as described in any one of claims 1 to 2 is implemented.

4. A computer storage medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the multi-level energy management method of the port-ship multi-energy fusion system as described in any one of claims 1 to 2 is implemented.

Citation Information

Patent Citations

  • Energy management system for wind-light-fire-hydrogen storage new energy system

    CN113922375A

  • Hydrogen energy storage optimal configuration method for green port shore power system

    CN114914943A