Renewable energy transfer distribution system and method

Abstract

A renewable energy transfer distribution system and method provide a model, perform green power optimization operation on at least one power consumption terminal based on a genetic algorithm and a gradient descent method, and generate at least one target-based transfer scheme according to a plurality of power generation parameters and at least one power consumption parameter, comprising a pairing relationship between the power consumption of at least one power consumption end and the green power ratio of a plurality of power generation ends; and repeatedly performing green power optimization operation on the specific power utilization end based on the plurality of targets to generate a plurality of transfer schemes, and calculating the ratio of the power purchase cost variable to the green power increment of any two adjacent targets based on the plurality of transfer schemes and the cost parameters as the renewable energy marginal cost. Therefore, the demand of renewable energy distribution can be effectively met.

Description

TECHNICAL FIELD

[0001] The present application relates to an energy configuration technology, in particular to a renewable energy transfer distribution system and method. BACKGROUND

[0002] Based on the global carbon reduction trend, the use of renewable energy has become an important demand for enterprises. However, if the energy distribution between supply and demand is not planned in detail, the use of renewable energy may cause waste of renewable energy and cost due to seasonal characteristics and time characteristics. Although some energy distribution technologies have been developed, there is still room for improvement. SUMMARY

[0003] The present application aims to provide a renewable energy transfer distribution system and method to effectively meet the needs of renewable energy distribution.

[0004] To achieve the above-mentioned purpose, one aspect of the present application provides a renewable energy transfer distribution system, comprising: a processor and a memory, the processor being coupled to the memory, the memory storing instructions, the processor being configured to execute the instructions to perform: providing a model, performing green electricity optimization operation on at least one power consumption end based on genetic algorithm and gradient descent method, generating at least one transfer scheme based on target according to a plurality of power generation parameters and at least one power consumption parameter, including the pairing relationship of the power consumption of at least one power consumption end and the green electricity proportion of a plurality of power generation ends; and repeating the green electricity optimization operation on a specific power consumption end based on a plurality of targets to generate a plurality of transfer schemes, and calculating the ratio of the electricity purchase cost variable and the green electricity increment of any two adjacent targets based on a plurality of transfer schemes and cost parameters as the marginal cost of renewable energy.

[0005] To achieve the above-mentioned purpose, another aspect of the present application provides a renewable energy transfer distribution method applied to a system, such as a renewable energy transfer distribution system, the system comprising a processor and a memory, the processor being coupled to the memory, the memory storing instructions, the processor executing the instructions to perform the method, comprising: providing a model, performing green electricity optimization operation on at least one power consumption end based on genetic algorithm and gradient descent method, generating at least one transfer scheme based on target according to a plurality of power generation parameters and at least one power consumption parameter, including the pairing relationship of the power consumption of at least one power consumption end and the green electricity proportion of a plurality of power generation ends; and repeating the green electricity optimization operation on a specific power consumption end based on a plurality of targets to generate a plurality of transfer schemes, and calculating the ratio of the electricity purchase cost variable and the green electricity increment of any two adjacent targets based on a plurality of transfer schemes and cost parameters as the marginal cost of renewable energy.

[0006] To achieve the above object, another aspect of the present application provides a renewable energy transfer distribution system, comprising a processor and a memory, the processor being coupled to the memory, the memory storing instructions, the processor being configured to execute the instructions to: generate at least one transfer scheme based on a target according to a plurality of power generation parameters and at least one power consumption parameter, including a pairing relationship of power consumption of at least one power consumption end and green power proportion of a plurality of power generation ends; and repeatedly perform green power optimization operation on a specific power consumption end based on a plurality of targets to generate a plurality of transfer schemes, and calculate a ratio of power purchase cost variable and green power increment of any two adjacent targets based on the plurality of transfer schemes and a cost parameter as a marginal cost of renewable energy.

[0007] To achieve the above object, another aspect of the present application provides a renewable energy transfer distribution system, comprising a processor and a memory, the processor being coupled to the memory, the memory storing instructions, the processor being configured to execute the instructions to: generate at least one transfer scheme based on a target according to a plurality of power generation parameters and at least one power consumption parameter, including a pairing relationship of power consumption of at least one power consumption end and green power proportion of a plurality of power generation ends; and repeatedly perform green power optimization operation on a specific power consumption end based on a plurality of targets to generate a plurality of transfer schemes, and generate a plurality of unit power purchase costs corresponding to the plurality of targets according to a plurality of power purchase fees and power purchase units corresponding to the plurality of targets, generate a power purchase guide according to the plurality of unit power purchase costs and a certificate unit cost, the power purchase guide indicating a recommended purchase of renewable energy purchase units or renewable energy certificate purchase units.

[0008] The renewable energy transfer distribution system and method of the present application, for example, provides a model to perform green power optimization operation on at least one power consumption end based on a genetic algorithm and gradient descent method, generate at least one transfer scheme based on a target according to a plurality of power generation parameters and at least one power consumption parameter, including a pairing relationship of power consumption of at least one power consumption end and green power proportion of a plurality of power generation ends; and repeatedly perform green power optimization operation on a specific power consumption end based on a plurality of targets to generate a plurality of transfer schemes; calculate a ratio of power purchase cost variable and green power increment of any two adjacent targets based on the plurality of transfer schemes and a cost parameter as a marginal cost of renewable energy, or generate a power purchase guide according to a plurality of power purchase fees, power purchase units and certificate unit costs corresponding to the plurality of targets. Thus, it is beneficial to accurately achieve the transfer target, easy to control the cost, and also can consider alternative solutions such as purchasing energy certificates according to the cost demand. BRIEF DESCRIPTION OF DRAWINGS

[0009] Figure 1 is a schematic diagram of a renewable energy supply and demand situation of an embodiment of the present application;

[0010] Figure 2 is a functional configuration schematic diagram of a renewable energy transfer distribution system of an embodiment of the present application;

[0011] Figure 3is a schematic diagram of an application scenario of the optimization process of the embodiment of the present application;

[0012] Figures 4 to 9 is Figure 3 is a schematic diagram of a multi-stage calculation process of optimization;

[0013] Figure 10 is a schematic diagram of the visualization of the transfer result of the embodiment of the present application;

[0014] Figure 11 is a schematic diagram of an application scenario of the optimization algorithm of the embodiment of the present application;

[0015] Figure 12 is a schematic diagram of the execution flow of the optimization algorithm of the embodiment of the present application;

[0016] Figures 13 to 16 is Figure 12 is a schematic diagram of a multi-stage execution scenario of the double-layer algorithm;

[0017] Figure 17A and Figure 17B is a schematic diagram of a bidirectional RE cost trend scanning of the embodiment of the present application;

[0018] Figure 18 is a schematic diagram of a renewable energy cost analysis of the embodiment of the present application;

[0019] Figure 19 is a schematic diagram of a renewable energy unit price analysis of the embodiment of the present application.

[0020] Explanation of reference signs

[0021] 10: renewable energy supply and demand scenario example

[0022] 11: transfer optimization system

[0023] 12: power generation end

[0024] 13: power consumption end

[0025] 20: functional configuration example

[0026] 21: system

[0027] 211: optimization setting module

[0028] 212: target definition module

[0029] 213: optimization estimation module

[0030] 214: renewable energy trend optimization module

[0031] 215: transfer calculation module

[0032] 216: analysis module

[0033] 217: optimization review module

[0034] 23: power database

[0035] 25: human-machine interface

[0036] 30: optimization process example

[0037] 40, 50, 60, 70, 80, 90: calculation process example

[0038] 100: transfer visualization example

[0039] 110: application context example of optimization algorithm

[0040] 120: execution flow example of optimization algorithm

[0041] 130, 140, 150, 160: calculation process example

[0042] 170A, 170B: RE trend example

[0043] 180: renewable energy cost analysis example

[0044] 190: renewable energy unit price analysis example

[0045] C, CA, CB, CC: contract

[0046] D, D1, D2, D3, D4: power consumption end

[0047] G, G1, G2, G3: power generation end

[0048] P1, P1', P1A, P2, P2A: parameter

[0049] L ni : first parameter

[0050] P mi : second parameter

[0051] R: residual power

[0052] S1, S2, S21, S22, S23, S24, S25, S3: step

[0053] U: user

[0054] U1: first flow direction feature

[0055] U2: second flow direction feature

[0056] U3: third flow direction feature

[0057] U4: fourth flow direction feature

[0058] U5: Fifth flow direction feature

[0059] U6: Sixth flow direction feature

[0060] U7: Seventh flow direction feature

[0061] V1, V2, V3, V4, V5, V6: Curve

[0062] V21: Initial result

[0063] V22: Fine-tuned result

[0064] V23: Final-tuned result

[0065] Z1, Z2: Zone DETAILED DESCRIPTION

[0066] In order to make the above and other objects, features, and advantages of the present application more comprehensible, preferred embodiments will be described below with reference to the accompanying drawings, in which:

[0067] Based on the global carbon reduction trend, the use of renewable energy has become an important demand for enterprises. For example, the Global Renewable Energy Initiative brings together the world's most influential enterprises to work together to improve the green electricity use-friendly environment from the perspective of electricity demand. For example, in Taiwan, China, the current practice is to set up a transfer contract in a manual manner based on the transfer calculation rules proposed by the Taipower Company, wherein the transfer refers to the process of distributing green electricity (renewable energy) from the power generation end to the power consumption end. However, this method cannot accurately achieve the goal and can only be adjusted manually, and the cost is difficult to control; moreover, this method only provides a solution for transferring green electricity in the green electricity use-friendly environment, and has not considered alternative solutions such as purchasing energy certificates to meet the cost demand. Therefore, the present application proposes a renewable energy transfer solution. For example, but not limited thereto.

[0068] In one aspect, embodiments of the present disclosure provide a renewable energy transfer distribution system, comprising: a processor and a memory, the processor coupled to the memory, the memory storing instructions, the processor configured to execute the instructions to: provide a model, perform a green energy optimization operation on at least one electricity consumption end based on a genetic algorithm and a gradient descent method, generate at least one transfer scheme based on a target according to a plurality of power generation parameters and at least one electricity consumption parameter, including a pairing relationship of electricity consumption of the at least one electricity consumption end and a green energy proportion of the plurality of power generation ends; and repeat the green energy optimization operation on a specific electricity consumption end based on a plurality of targets to generate a plurality of transfer schemes, and calculate a ratio of a power purchase cost variable and a green energy increment of any two adjacent targets based on the plurality of transfer schemes and a cost parameter as a renewable energy marginal cost. However, this is not the case, in other embodiments, the processor of the renewable energy transfer distribution system can also be configured to execute the instructions to perform a part of the features of the embodiments described above or below, such as, in addition to providing a model, performing a green energy optimization operation on at least one electricity consumption end based on a genetic algorithm and a gradient descent method, other features.

[0069] For example, as Figure 1 A renewable energy supply and demand situation example 10 includes a transfer optimization system 11 for generating at least one transfer scheme, such as generating a transfer contract, in order to transfer green energy from a plurality of power generation ends (such as power plants of renewable energy such as wind, solar, hydro, geothermal and tidal energy) 12 to at least one electricity consumption end (such as an office or a factory) 13.

[0070] For example, as Figure 2 A function configuration example 20 includes a system 21, such as a renewable energy transfer distribution system, which can receive data from an electricity database 23 and receive instruction and target data from a human-machine interface 25 to generate at least one transfer scheme, which can be presented on the human-machine interface 25 so that the user U can obtain the transfer scheme.

[0071] For example, as Figure 2The system 21 can be a computer or a cloud computing platform, the power database 23 can be a database of a power company, and the human-machine interface 25 can be a device with a display, such as a touch screen, a smartphone, a tablet computer, a notebook computer, or the like. For example, the system 21 includes at least one processor and at least one memory electrically connected to the processor. The memory stores at least one instruction. When the processor executes the instruction, the processor generates a plurality of software modules to perform a renewable energy transfer distribution method for determining how to distribute the power between the power generation end and the power consumption end, such as in association with the calculation rules specified in the transfer contract and the renewable energy operation regulations of the power company. After the power distribution process is completed, the actual power that each power consumption end can obtain from the power generation end (for example, through the transfer contract) can be known. In other embodiments, at least a part of the above-mentioned software modules can also be configured as hardware modules, such as application-specific integrated circuits (ASICs).

[0072] Additionally, the embodiments of the present application can also calculate other indicators, such as the RE value (e.g., RE1, RE2, RE3, …, RE99, and RE100) of the power consumption end, which is the percentage of the transferred green power divided by the power consumption; the gray power of the power consumption end, which is the difference between the power consumption and the transferred green power; the surplus power of the power generation end, which is the difference between the power generation and the transferred green power; the surplus power purchase cost (Top), which is the cost of the surplus power (the price per degree needs to be negotiated with the power generation company); and the total cost, which is the sum of the product of the gray power and the gray power rate, the product of the transferred green power and the green power rate, and the surplus power purchase cost.

[0073] For example, the system 21 can be a computer or a cloud computing platform, the power database 23 can be a database of a power company, and the human-machine interface 25 can be a device with a display, such as a touch screen, a smartphone, a tablet computer, a notebook computer, or the like. For example, the system 21 includes at least one processor and at least one memory electrically connected to the processor. The memory stores at least one instruction. When the processor executes the instruction, the processor generates a plurality of software modules to perform a renewable energy transfer distribution method for determining how to distribute the power between the power generation end and the power consumption end, such as in association with the calculation rules specified in the transfer contract and the renewable energy operation regulations of the power company. After the power distribution process is completed, the actual power that each power consumption end can obtain from the power generation end (for example, through the transfer contract) can be known. In other embodiments, at least a part of the above-mentioned software modules can also be configured as hardware modules, such as application-specific integrated circuits (ASICs). Figure 2, the system 21 comprises an optimization setting module 211, a target defining module 212, an optimization estimation module 213, a renewable energy trend optimization module 214, a wheeling calculation module 215, an analysis module 216 and an optimization review module 217, for example, the optimization setting module 211 can be used to set the parameters that can be optimized in the wheeling contract, such as the proportion of the generation end in the wheeling contract, whether the wheeling contract is wheeled to the power consumption end, the number of wheeling contracts and the wheeling upper limit, etc., the optimization setting module 211 can also send signals to the power database 23 to input data, such as the power generation data and the power consumption data obtained intermittently (such as every 15 minutes), the optimization setting module 211 can also send signals to the power database 23 to output data, such as the power actually wheeled to the power consumption end by the generation end according to the contract; the target defining module 212 can define the target according to the data from the optimization setting module 211, for example, the renewable proportion (such as RE1 to RE100) of the green power obtained by the wheeling, which can be output to the wheeling calculation module 215 to calculate at least one wheeling result; the optimization estimation module 213 can perform an optimization estimation process according to the parameters input by the user U through the human-computer interface 25, for example, the parameters that can be optimized in the wheeling contract are optimized to generate an optimization result, which is used as the basis for the wheeling contract; the renewable energy trend optimization module 214 can generate at least one renewable energy optimization trend according to the optimization result from the optimization estimation module 213 and the wheeling result from the wheeling calculation module 215, for example, the optimization trend of RE90 to RE100, the optimization trend includes a plurality of renewable energy proportion values corresponding to an optimization scheme, such as the electricity cost of a plurality of renewable energy proportions, a plurality of optimization schemes can be analyzed by the analysis module 216 to analyze a trend, for example, when the renewable proportion value is increased / decreased in a forward / backward scanning, the total procurement electricity cost is monotonically increased / decreased; the output result of the renewable energy trend optimization module 214 can also be reviewed by the optimization review module 217 to generate an optimization review (such as a waterfall chart) to be output to the human-computer interface 25.

[0074] The following illustrates an optimization process, which discusses how a power consumption enterprise wants to achieve RE90 by signing a wheeling contract under the condition of stable power consumption, but is not limited thereto.

[0075] For example, as Figure 3 In an optimization process example 30, it is assumed that there are three generation ends G, four power consumption ends D and three contracts C, in terms of the parameters that can be optimized in the wheeling contract, ① between the generation end G and the contract C represents the wheeling proportion (P mi), ② indicates whether the nth (e.g., n = 1-4) power consumer D participates in the ith (e.g., i = 1-3) contract C between the power consumer D and the contract C, and the two ends of the arrow indicate that there is a correlation between the two; in addition, the number of transfer contracts can be confirmed by the exhaustion method; it is practical to set the transfer upper limit to a large value, so it is assumed that the transfer upper limit can be infinite.

[0076] It should be understood that in this paper, the transfer calculation rule can refer to the specification of the power company, and only the thirteenth point of the operating regulations of Taipower Company is taken as an example, but it is not limited to this, and other power transfer calculation rules can also be used; in addition, the transfer calculation, for example, includes two stages: the first stage is to transfer power every 15 minutes, and after the transfer is completed, the power shortage and the surplus power can be calculated; the second stage is to distribute the results of all 15-minute power transfers in the same month, for example, according to the power company's calendar, which is classified into four periods: "peak", "semi-peak", "off-peak", and "Saturday semi-peak"; then, according to the transferable power, the distribution of the same period is carried out; in addition, the input data required for transfer calculation includes the power generation data and the power consumption data of each power generation end and each power consumption end every 15 minutes, as well as the transfer contract; in addition, the output data of the transfer calculation includes the power actually transferred by the power generation end to the power consumption end through the transfer contract. The following is an example, but it is not limited to this.

[0077] As Figure 4 In a calculation process example 40, it includes: not considering the transfer upper limit; the numerical value is rounded to the first decimal place; it is assumed that the current period is the peak period; there are three power generation ends G1, G2 and G3, and the power generation is 150, 90 and 180 power units (e.g., degrees) respectively; there are four power consumption ends D1, D2, D3 and D4, and the power consumption is 50, 80, 30 and 70 power units (e.g., degrees) respectively; there are three contracts (e.g., transfer contracts) CA, CB and CC, contract CA indicates that the green power ratio from power generation end G1 is 100% and is distributed to power consumption ends D1, D2 and D4, contract CB indicates that the green power ratio from power generation ends G2 and G3 is 100% and 30% respectively and is distributed to power consumption ends D2 and D3, and contract CC indicates that the green power ratio from power generation end G3 is 70% and is distributed to power consumption ends D2 and D4. The following is an example of 15-minute transfer calculation process.

[0078] The first process, such as Figure 5In a calculation process example 50, the following is included: calculating the generation degree of the generation end that can participate in the contract for transfer, i.e. the sum of the product of the generation amount of each generation end and the proportion of the single contract for transfer. For example, the contract CA can obtain the amount of electricity 150 (= 150 * 100%) from the generation end Gl, i.e. the contract CA can transfer the amount of electricity 150; the contract CB can obtain the amount of electricity 90 (= 90 * 100%) from the generation end G2 and the amount of electricity 54 (= 180 * 30%) from the generation end G3, i.e. the contract CB can transfer the amount of electricity 144 (= 90 + 54); the contract CC can obtain the amount of electricity 126 (= 180 * 70%) from the generation end G3, i.e. the contract CC can transfer the amount of electricity 126.

[0079] The second process, as Figure 6 In a calculation process example 60, the following is included: calculating the degree of the contract for transfer that can be transferred to the electricity end, i.e. the product of the amount of electricity that can be transferred by the single contract for transfer and the proportion of the amount of electricity of each electricity end to the total amount of electricity of all electricity ends in the entire contract for transfer. For example, the contract CA can transfer the amount of electricity 50 (= 50 * 150 / (150)) to the electricity end Dl, the contract CA can transfer the amount of electricity 28.6 (= 80 * 150 / (150 + 144 + 126)) to the electricity end D2, the contract CA can transfer the amount of electricity 38 (= 70 * 150 / (150 + 126)) to the electricity end D4, the contract CB can transfer the amount of electricity 27.4 (= 80 * 144 / (150 + 144 + 126)) to the electricity end D2, the contract CB can transfer the amount of electricity 30 (= 30 * 144 / (144)) to the electricity end D3, the contract CC can transfer the amount of electricity 24 (= 80 * 126 / (150 + 144 + 126)) to the electricity end D2, and the contract CC can transfer the amount of electricity 32 (= 70 * 126 / (150 + 126)) to the electricity end D4. In addition, the total amount of electricity that can be transferred to each electricity end is calculated by adding the amount of electricity from each contract for transfer to the single electricity end. For example, the electricity end Dl has the amount of electricity 50 from the contract CA, the electricity end D2 has the amount of electricity 80 (= 28.6 + 27.4 + 24) from the contracts CA, CB and CC, the electricity end D3 has the amount of electricity 30 from the contract CB, and the electricity end D4 has the amount of electricity 70 (= 38 + 32) from the contracts CA and CC.

[0080] The third process, as Figure 7In a calculation process example 70, the following steps are included: calculating the electricity that can be mediated between the contract and the electricity end, if the transferable electricity of the contract meets (is greater than or equal to) the to-be-transferred electricity of the contract, no adjustment is needed; if the to-be-transferred electricity of the contract exceeds the transferable electricity of the contract, the to-be-transferred electricity needs to be adjusted according to the electricity proportion. For example, the transferable electricity of the contract CA is 116.6 (= 50 + 28.6 + 38), the transferable electricity of the contract CB is 57.4 (= 27.4 + 30), and the transferable electricity of the contract CC is 56 (= 24 + 32); then, it is determined whether the to-be-transferred electricity needs to be adjusted: the transferable electricity of the contract CA is 150 and the to-be-transferred electricity is 111.6 (no adjustment is needed because 116.6 is less than 150), the transferable electricity of the contract CB is 144 and the to-be-transferred electricity is 57.4 (no adjustment is needed because 57.4 is less than 144), and the transferable electricity of the contract CC is 126 and the to-be-transferred electricity is 56 (no adjustment is needed because 56 is less than 126). In this example, the contracts CA, CB and CC do not need to adjust the electricity, but in order to illustrate the adjustment case of the to-be-transferred electricity and the adjustment method, the following example is given. For example, assuming that the transferable electricity of the contract CC is 50 (less than the to-be-transferred electricity of 56), the to-be-transferred electricity needs to be adjusted to match the transferable electricity, and assuming that the to-be-transferred electricity of the contract CC for the electricity end D2 is adjusted from 24 to 21.4 (= 50 * 24 / (24 + 32)), and the to-be-transferred electricity of the contract CC for the electricity end D4 is adjusted from 32 to 28.6 (= 50 * 32 / (24 + 32)), so that the to-be-transferred electricity of the contract CC is 50 in total.

[0081] The fourth process is as follows: Figure 8 In a calculation process example 80, the following steps are included: calculating the actual transferred electricity between the electricity end and the contract, and back-propagating the actual transferred electricity of each electricity end according to the proportion of the electricity end to the contract. For example, the actual transferred electricity of the electricity end G1 is 116.6, which includes the to-be-transferred electricity of 116.6 for the contract CA, the actual transferred electricity of the electricity end G2 is 35.9, which includes the to-be-transferred electricity of 35.9 (= 57.4 * 90 / (90 + 180)) for the contract CB, and the actual transferred electricity of the electricity end G3 is 77.5, which includes the to-be-transferred electricity of 21.5 (= 57.4 * 180 / (90 + 180)) for the contract CB and the to-be-transferred electricity of 56 for the contract CC, so that the electricity end G1 is transferred by 116.6 (less than the electricity of 150), the electricity end G2 is transferred by 35.9 (less than the electricity of 90), and the electricity end G3 is transferred by 77.5 (less than the electricity of 180).

[0082] The fifth process is as follows: Figure 9In a calculation process example 90, the relevant indicators, such as the regeneration ratio and cost, are calculated after the calculation of the power transfer, which are the results that the power consumers, such as enterprises, are most concerned about, and are the indicators that the optimization process is finally concerned about. For example, the total power generation of the power generation ends G1, G2 and G3 is 420 (= 150 + 90 + 180), the total power consumption of the power consumers D1, D2, D3 and D4 is 230 (= 50 + 80 + 30 + 70), the total power transfer of the contracts CA, CB and CC is 230 (= 116.6 + 57.4 + 56), the regeneration ratio RE% is 100.00 (= 230 / 230), the excess power is 190 (= 420-230), and the gray power is 0 (= 230-230).

[0083] In the present application, since the power transfer calculation process calculates the power transfer information of each power generation end (or power consumer), the aforementioned statistics can also be calculated for a single power generation end (or power consumer); in addition, if the unit price of the renewable energy of each power generation end is known, the renewable energy cost can be further calculated by multiplying the actual power transfer of each power generation end by the unit price to obtain the renewable energy cost; in addition, the gray power cost can be referred to the pricing of the power company to query the 15-minute period rate calculated, and multiplied by the corresponding price to obtain the gray power cost. In the present example, the period is the peak period, and assuming that the peak period is 7 yuan per degree, the gray power cost is 0 (= 0*7).

[0084] In some embodiments, the system can perform a green power optimization operation on a plurality of power consumers based on a single target in response to a request; and generate a display interface according to the pairing relationship between the power consumption of the plurality of power consumers and the green power ratio of the plurality of power generation ends in the power transfer scheme, the display interface including a plurality of first visual features corresponding to the plurality of power generation ends, a plurality of second visual features corresponding to the plurality of power consumers, and a plurality of intermediate visual features corresponding to the pairing relationship, the plurality of intermediate visual features being located between the plurality of first visual features and the plurality of second visual features, the display interface further including a flow direction of each of the plurality of first visual features connected to at least one of the plurality of second visual features through at least one of the plurality of intermediate visual features.

[0085] For example, the relative relationship between the power generation ends and the power consumers and the contracts therebetween in the above-mentioned examples can be further visualized. The following provides a visualization case with excess power, but is not limited thereto. For example, the visualization case can not present the excess power, or the visualization case can present the gray power, wherein the visualization content can be adjusted according to the actual application requirements; for example, the power transfer results are presented by Snakey Chart, as shown in Figure 10In the visualization example 100, on the left side are the power generation ends G1, G2 and G3 (the power generation amounts are 150, 90 and 180 respectively), on the right side are the power consumption ends D1, D2, D3 and D4 (the power consumption amounts are 50, 80, 30 and 70 respectively), in the middle are the contracts CA, CB and CC (the transferable power amounts are 116.6, 57.4 and 56.0 respectively), and in the middle is also the surplus power R with an amount of 190. As can be clearly seen in the figure, the power amounts between the power generation ends and the power consumption ends are transferred via which contracts (acting as intermediaries or bridges or distributors, interface / bridge / distributer) and the power flow directions of the transferred power and the surplus power can be represented by different visual features (such as colors, patterns or designs, etc.). The power amounts provided by each power generation end are distributed to which contract(s) (such as intermediary symbols), the transferable power amounts of each contract are distributed to which power consumption end(s), for example, a first flow direction feature (such as a first pattern) U1 represents the power amounts from the power generation end G1 being distributed to the contract CA and the surplus power R, a second flow direction feature (such as a second pattern) U2 represents the power amounts from the power generation end G2 being distributed to the contract CB and the surplus power R, a third flow direction feature (such as a third pattern) U3 represents the power amounts from the power generation end G3 being distributed to the contract CB, the contract CC and the surplus power R, a fourth flow direction feature (such as a fourth pattern) U4 represents the power amounts distributed by the contract CA to the power consumption end D1, a fifth flow direction feature (such as a fifth pattern) U5 represents the power amounts distributed by the contract CA, the contract CB and the contract CC to the power consumption end D2, a sixth flow direction feature (such as a sixth pattern) U6 represents the power amounts distributed by the contract CB to the power consumption end D3, and a seventh flow direction feature (such as a seventh pattern) U7 represents the power amounts distributed by the contract CA and the contract CC to the power consumption end D4, but not limited to this, such as Figure 10 The first flow direction feature U1, the second flow direction feature U2, the third flow direction feature U3, the fourth flow direction feature U4, the fifth flow direction feature U5, the sixth flow direction feature U6 and the seventh flow direction feature U7 shown in the figure can also be different colors, such as red, orange, yellow, green, blue, indigo, purple, etc. Among them, the two sides of the contract CA are connected to (the first flow direction pattern U1) and (the fourth flow direction pattern U4, the fifth flow direction pattern U5 and the seventh flow direction pattern U7) respectively, indicating that part of the power amount of the power generation end G1 is transferred to the power consumption ends D1, D2 and D4 via the contract CA; the two sides of the contract CB are connected to (the second flow direction pattern U2 and the third flow direction pattern U3) and (the fifth flow direction pattern U5 and the sixth flow direction pattern U6) respectively, indicating that part of the power amount of the power generation end G2 and part of the power amount of the power generation end G3 are transferred to the power consumption ends D2 and D3 via the contract CB; the two sides of the contract CC are connected to (the third flow direction pattern U3) and (the fifth flow direction pattern U5 and the seventh flow direction pattern U7) respectively, indicating that part of the power amount of the power generation end G3 is transferred to the power consumption ends D2 and D4 via the contract CC. Among them, each power generation end, each contract, the surplus power and each power consumption end can also be represented by different visual features (such as colors, patterns or designs, etc.).

[0086] In some embodiments, the display interface further comprises an intermediary visual feature located between the first visual features and the second visual features, and the display interface further comprises flow directions connecting the intermediary visual feature with at least one of the first visual features; further, the system can form a waterfall data according to the flow directions, set the waterfall data to associate at least one flow direction of each first visual feature with a color, set the waterfall data to associate at least one flow direction of each second visual feature with a color, and the color associated with each first visual feature and the color associated with each second visual feature are different from each other; further, the system can also set the first visual features, the second visual features, and the intermediary visual features to be associated with colors. In this way, a WYSIWYG visualization of the allocation result of the contract can be provided for the user to understand the pairing relationship between the generation end, the consumption end, and the contract therebetween.

[0087] In addition, as Figure 11 , the application context example 110 of the optimization algorithm is shown, which optimizes the contract parameters in the contract situation according to the user's target. Assuming that the upper limit of the contract and the number of contracts are not considered, the contract parameters that can be optimized include the power ratio between the contracts CA, CB, and CC and the generation ends G1, G2, and G3 (if the ratio is 0, it can be considered as no connection), which is called P mi in the algorithm, which is a real number such as a percentage or a decimal; and whether there is a connection relationship between the contracts CA, CB, and CC and the consumption ends D1, D2, D3, and D4, which is called L ni in the algorithm, which can be an integer such as 1 (representing "yes") or 0 (representing "no"). The application context example can be: how should the contracts CA, CB, and CC be set to achieve the target set by the user for the RE 100.

[0088] As Figure 12 , the execution flow example 120 of the optimization algorithm includes steps S1 to S3. Step S1, input data, including 15-minute power data, initial contract parameters, and optimization targets; then, step S2, execute a double-layer algorithm, such as a genetic algorithm as the outer layer and a gradient descent method as the inner layer, including steps S21 to S25. Step S21, execute the genetic algorithm, randomly guess S sets of first parameters L ni , where S is the number of parents; then, step S22, solve the S sets of first parameters L ni each with an optimized second parameter P mi ; then, step S23, evaluate the K sets of first parameters L niK is the optimal number of second parameters used for each generation to select those close to the optimal value; then, step S24 is performed to retain the optimal K sets of first parameters L. ni Next, proceed to step S25, based on the optimal K groups of first parameters L. ni The mixture produces a new (SK) group with the first parameter L. ni After step S25 is completed, return to step S22 and repeat steps S21 to S25 for Y generations (i.e., the number of generations, which can be adjusted according to the actual case). In step S25 of the Yth generation, the optimal transfer contract parameters can be generated, such as the first and second parameters of a recommended scheme. Then, proceed to step S3 to output the optimal transfer contract parameters. The calculation process of step S2 is illustrated below as an example, but it is not a limitation.

[0089] In some embodiments, the genetic algorithm generates a transfer decision on whether the electricity consumer needs to purchase renewable energy based on the electricity consumption parameter, and the gradient descent method generates the green electricity ratio of the several power generation terminals based on the transfer decision and the target. The green electricity ratio and the target are real number parameters, and the power generation parameter and the electricity consumption parameter are integer parameters.

[0090] The first process, corresponding to Figure 12 Step S21 as shown, as Figure 13 Example 130 of the calculation process includes: randomly guessing the first parameter L of group S. ni (As shown in the right half of the dashed box area in the figure, parameter P1 is derived). Here, S represents the number of groups to be tested. During the calculation, S is equivalent to the parent parameter in the gene algorithm. In this example, the first parameter L... ni The algorithm represents whether there is a transfer relationship between contract CA, CB or CC and the power users D1, D2, D3 or D4 (as shown in the figure). After the guessing process is completed, S binary matrices will be generated. For example, the value 0 indicates no connection (that is, there is no transfer relationship between the contract and the power user), and the value 1 indicates a connection (that is, there is a transfer relationship between the contract and the power user). In this example, the genetic algorithm can be used to process the transfer relationship represented by integers (such as 0 and 1).

[0091] The second process, corresponding to Figure 12 Step S22 as shown, as Figure 14 Example 140 of the calculation process includes: applying gradient descent to the first parameter L of group S. ni Solve for the corresponding second parameter P mi (Parameter P2 derived from the dashed area in the left half of the figure). Among them, the second parameter P... miThe ratio of electricity generated between contract CA, CB, or CC and generator terminals G1, G2, or G3 is expressed as a value between 0 and 1 (such as a percentage or its equivalent real number). Based on gradient descent, the first parameter L in the right half is... ni Keeping it constant, we solve for the optimal second parameter P in the left half. mi In this example, gradient descent can be used to handle the proportion of electricity expressed as a real number (such as a percentage between 0 and 1 or its corresponding value).

[0092] The third process, corresponding to Figure 12 Step S23 as shown, as Figure 15 Example 150 of the calculation process includes: evaluating the first parameter L of group S. ni (This represents an integer matrix indicating the relationship between contracts CA, CB, or CC and terminals D1, D2, D3, or D4, such as...) Figure 15 The parameters P1 (e.g., represented in matrix form) and the second parameter P mi (This represents a real-valued matrix indicating the relationship between contracts CA, CB, or CC and generator terminals G1, G2, or G3, such as...) Figure 15 The parameter P2 (e.g., represented in matrix form) is substituted into the calculation process to select K approaching targets (e.g., RE96, RE81, ..., RE74) whose difference from the target (e.g., RE100) is less than a threshold. For example, for the first parameter L in group S... ni and the second parameter P mi The scores are evaluated using the objective function, and then sorted in descending order. The first parameter L corresponding to the K optimal groups is selected. ni and the second parameter P mi .

[0093] The fourth process, corresponding to Figure 12 Steps S24 and S25 are shown as follows: Figure 16 Example 160 of the calculation process includes: based on the selected K groups of first parameters L ni For example, retaining the first parameter L of the optimal K groups ni To generate a new (SK) group of first parameters L by mixing ni Then, preparations can be made for the next generation, that is, to execute the corresponding [process] again. Figure 12 Step S22 as shown, as Figure 14 Example 140 of the calculation process is shown. If there is a next generation to be performed (i.e., the number of generations already executed is less than Y), then based on the selected K groups of first parameters, a crossover and mutation calculation process is performed to generate new (SK) groups of first parameters L. ni (like Figure 16 The parameter P1' shown is then returned to...Figure 12 The step S22 shown (i.e., as shown) Figure 14 Example of the calculation process shown in Example 140); if the current generation is the last generation (i.e., the number of generations executed is equal to Y), then the optimal first parameter L is returned. ni and the second parameter P mi (like Figure 16 The parameters P1A and P2A shown contain the transfer relationship between different contracts and different power users, as well as the power ratio between different contracts and different power generators, which serve as the basis for outputting the optimal transfer contract parameters later.

[0094] It should be understood that the above example only illustrates the target value of RE100, but is not limited to this. In the optimization calculation process, each RE value can be analyzed. That is, the target value can also be set to other values, such as RE99, RE98, and other RE values. For example, if the transfer contract parameters of several adjacent RE values ​​with a difference of one (such as RE90, RE81, RE92, ... and RE100) are established in sequence, the green electricity consumption and grey electricity consumption of the electricity user at different RE target values ​​can be known. Combined with the relevant green electricity rate and grey electricity rate, the related electricity costs such as green electricity cost and grey electricity cost can be calculated, thereby estimating the trend line derived from the total purchase electricity cost of the electricity user at different RE target values.

[0095] For example, a two-way RE-Cost trend line scan can be performed to gradually estimate the electricity cost for each RE target value during the optimization process. This helps to confirm whether the cost of electricity purchase increases monotonically with the RE target value, serving as a reference for renewable energy allocation policies.

[0096] For example, such as Figure 17A Example 170A of RE trend is shown, including curve V1, which is scanned in a forward manner from left to right. Each RE value from RE90 to RE100 is continuously optimized based on previous transfer results. For example, the total purchase cost of each RE value can be used as the initial value for searching the next RE value, thereby speeding up the search. For example, RE100 is continuously optimized based on the optimization result of RE99, RE99 is continuously optimized based on the optimization result of RE98, and so on.

[0097] In some embodiments, a unit electricity purchase cost curve includes several electricity purchase costs corresponding to several targets. The values ​​of the several targets increase in the positive direction and decrease in the negative direction. The system can scan the electricity purchase costs of any two adjacent targets in the negative direction. If the electricity purchase cost of the larger value among the two adjacent targets is lower than the electricity purchase cost of the smaller value among the two adjacent targets, the electricity purchase cost of the smaller value among the two adjacent targets is updated based on the electricity purchase cost of the larger value among the two adjacent targets.

[0098] likeFigure 17B The example 170B shows an RE trend, including curve V2. Using a reverse scan method from right to left, it confirms whether the trend line is monotonically increasing. In this example, the RE cost trend line is not monotonically increasing. Figure 17B Within the dashed box area, the total purchase cost of RE96 is higher than that of RE97, meaning the initial result V21 of RE96 is worse than that of RE97. Therefore, the result of RE97 can be used to optimize the result of RE96, generating a fine-tuning result V22 for RE96, aiming to make V22 better than the result of RE97. However, it should be noted that if the fine-tuning result V22 of RE96 is not as expected, for example, if the purchase cost of RE96 is higher than that of RE97, RE96 can be replaced by the result of RE97 to generate the final adjustment result V23 for RE96, thus eliminating unreasonable renewable energy purchase costs. Subsequently, the renewable energy cost optimization scheme can be evaluated based on the RE cost trend line, such as simply purchasing renewable energy or using renewable energy in combination with renewable energy certificates to achieve green electricity use and environmental friendliness.

[0099] In some embodiments, the system can generate a unit electricity purchase cost curve based on several electricity purchase costs corresponding to several targets and an electricity purchase unit. The unit electricity purchase cost curve includes several unit electricity purchase costs corresponding to several targets. Based on several unit electricity purchase costs and a voucher unit cost, an electricity purchase guide is generated. The electricity purchase guide indicates and recommends purchasing a renewable energy purchase unit or a renewable energy voucher purchase unit.

[0100] For example, such as Figure 18 Example 180 of renewable energy cost analysis is shown, where curve V3 is the RE cost trend line from RE87 to RE100; curve V4 is the marginal cost trend line with gradual adjustments of 1% of RE from RE87 to RE100, for example, the marginal cost of increasing RE by 1% is the ratio of the change in the total purchase cost of two adjacent RE values ​​to the change in the amount of gray electricity (such as the reduction in gray electricity or the increase in renewable energy usage) between the two adjacent RE values; curve V5 is the cost trend line of renewable energy certificates (such as Taiwan Renewable Energy Certificates, T-REC), assuming the average price of T-REC is NT$5 per kilowatt-hour. Figure 18 It can be seen that drawing an RE dividing line around the intersection of curves V4 and V5 can divide the region into regions Z1 and Z2. Region Z1 indicates that the marginal cost of increasing RE by 1% is lower than the cost of renewable energy vouchers. That is, to achieve the RE value in region Z1, it is advisable to purchase more renewable energy to reduce gray electricity. Region Z2 indicates that the marginal cost of increasing RE by 1% is higher than the cost of renewable energy vouchers. That is, to achieve the RE value in region Z2, it is advisable to purchase more renewable energy vouchers to reduce gray electricity.

[0101] In some embodiments, the system can determine whether a selected unit of the cost of purchasing electricity is greater than the unit cost of the certificate, and if the determination is yes, the electricity purchasing guide indicates that the purchase of the renewable energy certificate unit is recommended, and if the determination is no, the electricity purchasing guide indicates that the purchase of the renewable energy purchase unit is recommended. Thus, as the RE value is used as the determination basis, in addition to using direct purchase of green electricity to achieve the renewable energy planning target, purchase of renewable energy certificates can also be used to achieve the renewable energy planning target, diversifying the options for the electricity end to achieve the renewable energy planning target, so as to meet the electricity and cost needs of renewable energy.

[0102] For example, according to the renewable energy cost analysis as described above, the number of renewable energy certificates and the upper limit of the price of different RE stages can also be planned. For example, Figure 19 , a renewable energy unit price analysis example 190 is shown, in which the curve V6 is a curve of the additional cost per degree of green electricity for each 1% increase in RE starting from RE90. In this example, the reference point is set at RE90, i.e. if you want to use the purchase of renewable energy certificates to increase from RE90 to RE96, a total of 7,803 T-RECs need to be purchased (assuming that there are 7,802.257 degrees of electricity for each 6% increase in RE), and the average cost per degree of electricity must be less than 9.77 yuan, and it is more cost-effective to purchase renewable energy certificates; if the average cost per degree of electricity is greater than 9.77 yuan, it is more cost-effective to directly purchase renewable energy. Thus, if the average electricity price is used as the determination basis, when achieving the renewable energy planning target, it can also be determined which of the purchase of green electricity or renewable energy certificates has a lower cost (is more cost-effective), so as to meet the electricity and cost needs of renewable energy.

[0103] On the other hand, embodiments of the present application provide a renewable energy transfer distribution method, applied to a system, such as a renewable energy transfer distribution system, the system comprising a processor and a memory, the processor being coupled to the memory, the memory storing instructions, when the processor executes the instructions, the method comprises: providing a model, performing green electricity optimization on at least one electricity end based on a genetic algorithm and a gradient descent method, generating at least one transfer scheme based on a target according to a plurality of power generation parameters and at least one electricity parameter, including the pairing relationship of the electricity consumption of at least one electricity end and the green electricity proportion of a plurality of power generation ends; and repeatedly performing green electricity optimization on a specific electricity end based on a plurality of targets to generate a plurality of transfer schemes, and calculating the ratio of the electricity cost variable and the green electricity increment of any two adjacent targets based on a plurality of transfer schemes and cost parameters as a renewable energy marginal cost. Wherein, the implementation schemes of the method embodiments of the present application are corresponding to the system embodiments, please refer to the above, no further description.

[0104] The renewable energy transfer distribution system and method embodiments of the present application, for example, provide a model based on genetic algorithm and gradient descent method to perform green electricity optimization operation on at least one power consumption end, generate at least one transfer scheme based on target according to a plurality of power generation parameters and at least one power consumption parameter, including the matching relationship of the power consumption of at least one power consumption end and the green electricity proportion of a plurality of power generation ends; and repeatedly perform green electricity optimization operation on a specific power consumption end based on a plurality of targets to generate a plurality of transfer schemes; the ratio of the electricity purchase cost variable and the green electricity increment of any two adjacent targets based on a plurality of transfer schemes and cost parameters is the marginal cost of renewable energy, or the electricity purchase guide is generated according to the electricity purchase cost, electricity purchase unit and certificate unit cost corresponding to the plurality of targets. Therefore, it is beneficial to accurately achieve the transfer target, easy to control the cost, and also can consider alternative solutions such as purchasing energy certificates according to the cost demand.

[0105] Although the present application has been disclosed with the preferred embodiments, any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application, therefore the protection scope of the present application shall be subject to the right claims.

Claims

1. A renewable energy transfer distribution system, comprising a processor and a memory, the processor coupled to the memory, the memory storing instructions, the processor configured to execute the instructions to perform: providing a model, performing a green energy optimization operation on at least one electricity consuming end based on a genetic algorithm and a gradient descent method, generating a target-based at least one transfer scheme according to a plurality of power generation parameters and at least one electricity consuming parameter, including a pairing relationship of electricity consumption of the at least one electricity consuming end and green energy proportion of the plurality of power generation ends; and repeating the green energy optimization operation on a specific electricity consuming end based on a plurality of targets to generate a plurality of transfer schemes, calculating a ratio of a power purchase cost variable and a green energy increment of any two adjacent targets based on the plurality of transfer schemes and a cost parameter as a renewable energy marginal cost. 2.The renewable energy transfer distribution system of claim 1, wherein the processor is further configured to execute the instructions to perform: generating a unit power purchase cost curve according to a plurality of power purchase costs and a power purchase unit corresponding to the plurality of targets, the unit power purchase cost curve including a plurality of unit power purchase costs corresponding to the plurality of targets, generating a power purchase guide according to the plurality of unit power purchase costs and a certificate unit cost, the power purchase guide indicating a recommendation of purchasing a renewable energy purchase unit or a renewable energy certificate purchase unit. 3.The renewable energy transfer distribution system of claim 2, wherein the processor is further configured to execute the instructions to perform: determining whether a selected unit power purchase cost in the plurality of unit power purchase costs is greater than the certificate unit cost, if the determination is yes, the power purchase guide indicating the recommendation of purchasing the renewable energy certificate purchase unit, if the determination is no, the power purchase guide indicating the recommendation of purchasing the renewable energy purchase unit. 4.The renewable energy transfer distribution system of claim 1, wherein a unit power purchase cost curve includes a plurality of power purchase costs corresponding to the plurality of targets, values of the plurality of targets increasing in a positive direction and decreasing in a reverse direction, the processor is further configured to execute the instructions to perform: scanning power purchase costs of any two adjacent targets in a reverse direction, if a power purchase cost of a value greater one of the two adjacent targets is lower than a power purchase cost of a value smaller one of the two adjacent targets, updating the power purchase cost of the value smaller one of the two adjacent targets based on the power purchase cost of the value greater one of the two adjacent targets.

5. The renewable energy transfer distribution system of claim 1, wherein the processor is further configured to execute the instructions to perform: performing the green energy optimization job based on a single objective for a plurality of electricity consuming ends in response to a request; and generating a display interface in accordance with a pairing relationship of electricity consumption of a plurality of electricity consuming ends and green energy proportion of a plurality of electricity generating ends in the transfer scheme, the display interface comprising a plurality of first visual features corresponding to the plurality of electricity generating ends, a plurality of second visual features corresponding to the plurality of electricity consuming ends, and a plurality of intermediate visual features corresponding to the pairing relationship, the plurality of intermediate visual features being located between the plurality of first visual features and the plurality of second visual features, the display interface further comprising a flow direction of each of the plurality of first visual features connecting at least one of the plurality of second visual features through at least one of the plurality of intermediate visual features.

6. The renewable energy transfer distribution system of claim 5, wherein the display interface further comprises a residual visual feature, the residual visual feature being located between the plurality of first visual features and the plurality of second visual features, the display interface further comprising a flow direction of at least one of the plurality of first visual features connecting the residual visual feature.

7. The renewable energy transfer distribution system of claim 5 or 6, wherein the processor is further configured to execute the instructions to perform: forming a waterfall chart data in accordance with the flow direction, setting at least one flow direction and color of the waterfall chart data corresponding to each of the plurality of first visual features, setting at least one flow direction and color of the waterfall chart data corresponding to each of the plurality of second visual features, the color associated with each of the plurality of first visual features and the color associated with each of the plurality of second visual features being different from each other.

8. The renewable energy transfer distribution system of claim 5 or 6, wherein the processor is further configured to execute the instructions to perform: setting the plurality of first visual features, the plurality of second visual features, and the plurality of intermediate visual features associated with a plurality of colors.

9. The renewable energy transfer distribution system of claim 1, wherein the processor is further configured to execute the instructions to perform: the genetic algorithm generating a transfer decision of whether the electricity consuming end needs to purchase renewable energy in accordance with the electricity consumption parameter, the gradient descent method generating the green energy proportion of the plurality of electricity generating ends in accordance with the transfer decision and the objective, wherein the green energy proportion and the objective are real number parameters, and the electricity consumption parameter and the electricity generation parameter are integer parameters.

10. The renewable energy transfer distribution system of claim 1, wherein the processor is further configured to execute the instructions to perform: a first job, performing a genetic algorithm, randomly guessing a first plurality of first parameters based on the electricity consumption parameter, the first plurality of first parameters indicating a transfer relationship between the at least one electricity consuming end and a plurality of intermediate ends; ​ a second operation of performing a gradient descent method to solve an optimized second plurality of second parameters based on the first plurality of first parameters, the second plurality of second parameters indicating a proportion of electricity between the plurality of intermediate ends and the plurality of power generation ends; a third operation of estimating a correlation integer matrix of the first plurality of first parameters and a correlation real number matrix of the second plurality of second parameters, selecting a third plurality of first and second parameters approaching a target from the correlation integer matrix of the first plurality of first parameters and the correlation real number matrix of the second plurality of second parameters according to a target function, a difference value of the third plurality of first and second parameters approaching the target being less than a threshold value; a fourth operation of generating a fourth plurality of first parameters based on the third plurality of first parameters, the fourth plurality of first parameters being the first plurality of first parameters minus a difference value of the third plurality of first parameters; and repeating the second operation, the third operation, and the fourth operation each once based on the fourth plurality of first parameters as a generation until a fifth plurality of generations are repeated to generate optimized first and second parameters as one of the at least one transfer supply scheme.

11. A renewable energy transfer distribution method applied to a system, the system comprising a processor and a memory, the processor coupled to the memory, the memory storing instructions that, when executed by the processor, perform the method, comprising: providing a model, performing a green electricity optimization operation on at least one electricity consumption end based on a genetic algorithm and a gradient descent method, generating at least one transfer supply scheme based on a target according to a plurality of power generation parameters and at least one electricity consumption parameter, including a pairing relationship of electricity consumption of at least one electricity consumption end and a proportion of green electricity of a plurality of power generation ends; and repeating the green electricity optimization operation for a specific electricity consumption end based on a plurality of targets to generate a plurality of transfer supply schemes, calculating a ratio of a power purchase cost variable and a green electricity increment of any two adjacent targets based on the plurality of transfer supply schemes and a cost parameter as a marginal cost of renewable energy. generating a unit power purchase cost curve according to a plurality of power purchase fees and a power purchase unit corresponding to the plurality of targets, the unit power purchase cost curve including a plurality of unit power purchase costs corresponding to the plurality of targets, generating a power purchase guide according to the plurality of unit power purchase costs and a certificate unit cost, the power purchase guide indicating a recommendation to purchase a renewable energy purchase unit or a renewable energy certificate purchase unit.

12. The renewable energy transfer dispensing method of claim 11, further comprising: determining whether a selected unit power purchase cost in the plurality of unit power purchase costs is greater than the certificate unit cost, if the determination is yes, the power purchase guide indicates a recommendation to purchase the renewable energy certificate purchase unit, if the determination is no, the power purchase guide indicates a recommendation to purchase the renewable energy purchase unit.

13. The renewable energy transfer distribution method of claim 12, wherein generating the electricity purchase guide from the number of unit electricity purchase costs and the certificate unit cost comprises: scanning the power purchase fees of any two adjacent targets in a reverse direction, if the power purchase fee of a larger value of the two adjacent targets is lower than the power purchase fee of a smaller value of the two adjacent targets, updating the power purchase fee of the smaller value of the two adjacent targets based on the power purchase fee of the larger value of the two adjacent targets.

14. The renewable energy transfer distribution method of claim 11, wherein the unit electricity purchase cost curve comprises a plurality of electricity purchase costs corresponding to the plurality of objectives, the plurality of objectives having values that increase in a positive direction and decrease in a negative direction, the method further comprising: ​ 15. The renewable energy transfer distribution method of claim 11, further comprising: performing the green electricity optimization job based on a single objective for a plurality of electricity consuming ends in response to a request; and generating a display interface according to a pairing relationship of electricity consumption of a plurality of electricity consuming ends and green electricity proportion of a plurality of electricity generating ends in the power supply scheme, the display interface comprising a plurality of first visual features corresponding to the plurality of electricity generating ends, a plurality of second visual features corresponding to the plurality of electricity consuming ends, and a plurality of intermediate visual features corresponding to the pairing relationship, the plurality of intermediate visual features being located between the plurality of first visual features and the plurality of second visual features, the display interface further comprising a flow direction of each of the plurality of first visual features connecting at least one of the plurality of second visual features through at least one of the plurality of intermediate visual features.

16. The renewable energy power supply allocation method of claim 15, wherein the display interface further comprises a residual visual feature, the residual visual feature being located between the plurality of first visual features and the plurality of second visual features, the display interface further comprising a flow direction of at least one of the plurality of first visual features connecting the residual visual feature.

17. The renewable energy power supply allocation method of claim 15 or 16, wherein a waterfall chart data is formed according to the flow direction, the waterfall chart data being configured to associate at least one flow direction of each of the plurality of first visual features with a color, the waterfall chart data being configured to associate at least one flow direction of each of the plurality of second visual features with a color, the color associated with each of the plurality of first visual features and the color associated with each of the plurality of second visual features being different from each other.

18. The renewable energy power supply allocation method of claim 15 or 16, wherein the plurality of first visual features, the plurality of second visual features, and the plurality of intermediate visual features are configured to be associated with a plurality of colors.

19. The renewable energy power supply allocation method of claim 11, wherein the genetic algorithm generates a power supply decision of whether the electricity consuming end needs to purchase renewable energy according to the electricity consumption parameter, the gradient descent method generates the green electricity proportion of the plurality of electricity generating ends according to the power supply decision and the objective, wherein the green electricity proportion and the objective are real number parameters, and the electricity generation parameter and the electricity consumption parameter are integer parameters.

20. The renewable energy power supply allocation method of claim 11, wherein the model runtime job comprises: a first job of performing a genetic algorithm to randomly guess a first plurality of first parameters based on the electricity consumption parameter, the first plurality of first parameters indicating a power supply relationship between the at least one electricity consuming end and a plurality of intermediate ends; a second job of performing a gradient descent method to solve an optimized second plurality of second parameters based on the first plurality of first parameters, the second plurality of second parameters indicating an electricity proportion between the plurality of intermediate ends and the plurality of electricity generating ends. a third operation of estimating a relevance integer matrix of the first plurality of first parameters and a relevance real matrix of the second plurality of second parameters, and selecting a third plurality of first parameters and second parameters approaching the target from the relevance integer matrix of the first plurality of first parameters and the relevance real matrix of the second plurality of second parameters according to the objective function, wherein a difference between the third plurality of first parameters and second parameters and the target is less than a threshold value; a fourth operation of generating a fourth plurality of first parameters based on the third plurality of first parameters and second parameters, wherein the fourth plurality of first parameters is the first plurality of first parameters minus the difference between the third plurality of first parameters and second parameters; and repeating the second operation, the third operation and the fourth operation based on the fourth plurality of first parameters as one generation until a fifth plurality of generations are repeated to generate optimal first parameters and second parameters as one of the at least one transfer scheme.

21. A renewable energy transfer distribution system comprising a processor and a memory, the processor coupled to the memory, the memory storing instructions, the processor configured to execute the instructions to perform: generating at least one target-based transfer scheme based on a plurality of generation parameters and at least one consumption parameter, comprising a pairing relationship between a consumption amount of at least one consumption end and a green energy amount proportion of a plurality of generation ends; and repeating a green energy optimization operation for a specific consumption end based on a plurality of targets to generate a plurality of transfer schemes, and calculating a ratio of a power purchase cost variable and a green energy increment of any two adjacent targets based on the plurality of transfer schemes and a cost parameter as a renewable energy marginal cost.

22. A renewable energy transfer distribution system comprising a processor and a memory, the processor coupled to the memory, the memory storing instructions, the processor configured to execute the instructions to perform: generating at least one target-based transfer scheme based on a plurality of generation parameters and at least one consumption parameter, comprising a pairing relationship between a consumption amount of at least one consumption end and a green energy amount proportion of a plurality of generation ends; and repeating a green energy optimization operation for a specific consumption end based on a plurality of targets to generate a plurality of transfer schemes, generating a plurality of unit power purchase costs corresponding to the plurality of targets based on a plurality of power purchase fees and power purchase units corresponding to the plurality of targets, and generating a power purchase guide based on the plurality of unit power purchase costs and a certificate unit cost, the power purchase guide indicating a recommendation to purchase a renewable energy purchase unit or a renewable energy certificate purchase unit.

Images