Park energy supply planning method and system for zero-carbon park construction

Abstract

The invention discloses a park energy supply planning method and system for zero-carbon park construction, and relates to the technical field of energy management, and the method comprises the steps: traversing an energy consumption node list, predicting a power demand in combination with the expected output of a target time zone, and generating a power demand list; matching business portraits, indexing mode carbon emissions of samples with the same portraits to form a predicted carbon emission list, and combining the predicted carbon emission list with a carbon quota list; traversing photovoltaic energy supply nodes, and predicting energy supply; a plurality of energy supply planning schemes are generated on the basis of energy supply prediction by taking predicted electricity demand as a constraint, and each scheme is provided with a carbon emission identifier; and finally, screening a minimum carbon emission scheme according to the carbon emission identifier, the carbon quota and the predicted carbon emission, and sending the minimum carbon emission scheme to an energy supply management end. Therefore, the technical effects of improving the planning fineness and improving the carbon reduction level are achieved.

Description

Technical Field

[0001] The present invention relates to the field of energy management technology, and in particular to a park energy supply planning method and system for zero-carbon park construction. Background Art

[0002] Park energy supply planning is crucial to achieving low-carbon and efficient operation of the park. Existing park energy supply planning methods mainly focus on the basic balance between energy supply and demand, usually considering the power demand of various energy-consuming nodes in the park and the source of energy supply, such as traditional power grid power supply and new energy power generation, but lack of refined management of energy supply and demand in the park.

[0003] The existing energy supply planning method generally gives priority to supplying green energy and then considers external energy supply. It does not fully consider the carbon emissions of various energy consumption nodes within the park and the carbon quota restrictions. Due to the lack of detailed analysis and optimization of the carbon emissions of energy supply within the park, the refinement of the energy supply planning of the entire park is insufficient, and it is impossible to effectively achieve the low-carbon and efficient operation of the park energy supply system, and it is difficult to meet the current strict requirements for energy utilization efficiency and carbon emission control in the construction of zero-carbon parks. There are technical problems such as insufficient planning refinement that affect the carbon reduction effect. Summary of the invention

[0004] The present invention provides a park energy supply planning method and system for the construction of a zero-carbon park, so as to solve the technical problems in the prior art of insufficient planning refinement and affecting the carbon reduction effect, and achieve the technical effects of improving planning refinement and improving the carbon reduction level.

[0005] In a first aspect, the present invention provides a park energy supply planning method for zero-carbon park construction, which includes: Traverse the list of energy-consuming nodes, make a power consumption forecast based on the expected output in the target time zone, and obtain a list of predicted power requirements.

[0006] The business portrait list of the energy consumption node list is traversed, combined with the predicted power demand list, the majority carbon emissions of the same portrait samples are indexed online, and set as the predicted carbon emissions list, and the energy consumption node list has a carbon quota list.

[0007] Traverse the photovoltaic energy supply node list to predict the energy supply in the target time zone and obtain the predicted energy supply list.

[0008] The predicted power demand list is used as the energy supply constraint, and based on the predicted energy supply list, an energy supply plan configuration module is initialized to obtain several energy supply planning plans, and any energy supply planning plan has an energy supply carbon emission identifier.

[0009] Based on the energy supply carbon emission identifier, the carbon quota list and the predicted carbon emission list, the plurality of energy supply planning schemes are sorted for minimum carbon emission, and the selected scheme for the park energy supply planning is obtained and sent to the energy supply management terminal.

[0010] In a second aspect, the present invention further provides a park energy supply planning system for zero-carbon park construction, wherein the system comprises: The electricity consumption prediction module is used to traverse the list of energy-consuming nodes, make electricity consumption predictions based on the expected output in the target time zone, and obtain a list of predicted electricity demand.

[0011] The carbon emission prediction module is used to traverse the business portrait list of the energy consumption node list, combine the predicted power demand list, index the majority carbon emission of the same portrait sample online, and set it as the predicted carbon emission list. The energy consumption node list has a carbon quota list.

[0012] The photovoltaic energy supply prediction module is used to traverse the photovoltaic energy supply node list to perform energy supply prediction in the target time zone and obtain a predicted energy supply list.

[0013] The energy supply planning module is used to use the predicted power demand list as the energy supply constraint, initialize through the energy supply plan configuration module based on the predicted power supply list, and obtain several energy supply planning plans, any of which has an energy supply carbon emission mark.

[0014] The carbon emission sorting module is used to sort the several energy supply planning schemes according to the minimum carbon emission based on the energy supply carbon emission identification, the carbon quota list and the predicted carbon emission list, obtain the selected scheme of the park energy supply planning and send it to the energy supply management terminal.

[0015] The present invention discloses a park energy supply planning method and system for zero-carbon park construction, including: traversing the energy consumption node list, combining the expected output in the target time zone to predict the electricity consumption, and obtaining a predicted power demand list; traversing the business portrait list of the energy consumption node list, combining the predicted power demand list, networking and indexing the mode carbon emissions of the same portrait samples, setting it as a predicted carbon emission list, and the energy consumption node list has a carbon quota list; traversing the photovoltaic energy supply node list to predict the energy supply in the target time zone, and obtaining a predicted power supply list; taking the predicted power demand list as the energy supply constraint, based on the predicted power supply list The table is initialized through the energy supply plan configuration module to obtain several energy supply planning schemes, and any energy supply planning scheme has an energy supply carbon emission mark; based on the energy supply carbon emission mark, the carbon quota list and the predicted carbon emission list, the several energy supply planning schemes are sorted by the minimum carbon emission, and the selected park energy supply planning scheme is obtained and sent to the energy supply management end. The park energy supply planning method and system for zero-carbon park construction disclosed in the present invention solve the technical problems of insufficient planning refinement and affecting the carbon reduction effect, and achieve the technical effects of improving the planning refinement and improving the carbon reduction level. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of a park energy supply planning method for zero-carbon park construction according to the present invention; Figure 2 This is a structural schematic diagram of a park energy supply planning system for zero-carbon park construction according to the present invention.

[0017] Explanation of the reference numerals: electricity consumption prediction module 11 , carbon emission prediction module 12 , photovoltaic energy supply prediction module 13 , energy supply planning module 14 , carbon emission sorting module 15 . DETAILED DESCRIPTION

[0018] The above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods of the specification to better understand the above technical solution. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments used only to explain the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, it should be noted that, for the convenience of description, only the parts related to the present invention are shown in the drawings, rather than all of them.

[0019] Embodiment 1:

[0020] Figure 1 The present invention is a flow chart of a park energy supply planning method for zero-carbon park construction, which includes: S100: Traverse the list of energy consumption nodes, make a power consumption forecast based on the expected output in the target time zone, and obtain a forecast power demand list.

[0021] Specifically, the predicted electricity demand list is used to quantitatively reflect the expected electricity demand of multiple energy consumption nodes under the expected output in the target time zone, so as to provide basic data support for subsequent energy supply planning; among them, the energy consumption node list refers to the collection of all energy-consuming nodes in the park, including various production equipment, lighting systems, air-conditioning systems, etc.; the target time zone refers to a specific time period, such as a peak electricity consumption period in a day or a specific production cycle period; the expected output refers to the production output that the park expects to achieve within the target time zone.

[0022] Through the above steps, the power demand of the park in the target time zone can be more accurately understood, which helps to improve the accuracy of the forecast, make the subsequent energy supply plan more in line with the actual needs of the park, and reduce energy waste.

[0023] In some embodiments, the power consumption forecast is performed in combination with the expected output in the target time zone to obtain a forecast power demand list, including: Obtain the first energy consuming node in the energy consuming node list; obtain the production equipment position number set of the first energy consuming node, cluster the production equipment position number set according to the service life of the equipment and based on the service life deviation threshold, and obtain the production equipment position number clustering result; traverse the production equipment position number clustering result, select any one production equipment to perform unit output power demand statistics in the past six months, and obtain a unit output power demand identifier; perform power consumption forecast based on the production volume allocation information of the target time zone uploaded by the first energy consuming node and the unit output power demand identifier, obtain a first predicted power demand, and add it to the predicted power demand list.

[0024] Specifically, service life refers to the length of time that production equipment has been in use from the beginning of its use to the current time, which is used to reflect the usage status and aging degree of the equipment, and has a certain impact on the energy consumption level of the equipment; the service life deviation threshold is a series of reference values ​​used to judge the similarity of the service life of production equipment. By comparing with this threshold, production equipment with similar service life can be grouped.

[0025] Specifically, first, the first energy-consuming node is obtained from the energy-consuming node list, and then, the position number set of all production equipment in the energy-consuming node is obtained, and a cluster analysis is performed on multiple production equipment position numbers according to the service life of each production equipment and a preset service life deviation threshold, so that the production equipment position numbers with similar service years are divided into multiple groups to form a number of production equipment position number clustering results; then, representative equipment in each cluster is selected, and the amount of electricity required to produce each unit of product in the last six months is counted as the unit output power requirement identifier of the production equipment of the cluster (service life category); finally, according to the production volume allocation information in the target time zone uploaded by the energy-consuming node, combined with the above-obtained unit output power requirement identifier, a power consumption forecast calculation is performed to obtain the first predicted power requirement of the energy-consuming node in the target time zone, and this result is added to the predicted power requirement list, wherein the value of the unit output power requirement identifier is equal to the product of the production volume allocation information and the value of the unit output power requirement identifier.

[0026] For example, taking a chemical park as an example, it is assumed that there is a production workshop in the park as the first energy consumption node, which contains multiple production equipment numbers, such as reactor A, reactor B, centrifuge C, etc. After clustering according to the service life of these equipment and the service life deviation threshold (for example, 1 year), reactors A and B are clustered together, and centrifuge C is an independent category. Statistics show that the unit output power demand of the reactor group in the past six months is 20kWh / ton of product, and the unit output power demand of the centrifuge group is 15kWh / ton of product. If the production volume allocation information of the workshop in the target time zone shows that the reactor plans to produce 100 tons of products and the centrifuge plans to process 80 tons of products, then the predicted power demand is (100 tons × 20kWh / ton) + (80 tons × 15kWh / ton) = 2000kWh + 1200kWh = 3200kWh, where reactor A corresponds to 1000kWh, reactor B corresponds to 1000kWh, and centrifuge C corresponds to 1200kWh.

[0027] Exemplarily, the predicted power demand list is expressed as: Table 1 Example of predicted power demand list Energy consumption nodes Position No. 1 Position No. 2 Position No. 3 …… Position No.n Node 1 1000kWh 1000kWh 1200kWh …… …… …… …… …… …… …… …… Node m …… …… …… …… …… Through the above steps, the cluster analysis of the service life of production equipment in the energy-consuming nodes and the statistics of the power demand per unit output have achieved a refined prediction of the power demand of each energy-consuming node in the target time zone, providing more accurate and detailed basic data for the subsequent energy supply plan configuration, which helps to improve the accuracy and rationality of the entire energy supply planning and ensure the stability and efficiency of the park's energy supply system.

[0028] In some implementations, the service life deviation threshold corresponds to a production equipment model one by one, and the configuration steps include: According to the production equipment model, statistics are generated on the service life sequence and the unit output power requirement sequence, wherein the unit output power requirement is equal to the mode value of the power requirement of at least 500 unit output records corresponding to the service life; the service life sequence and the unit output power requirement statistical value sequence are processed by a service life deviation threshold configuration model, and the service life deviation threshold is output; wherein the service life deviation threshold configuration model is generated by multiple groups of data based on machine learning training, and any one of the multiple groups of data includes: a service life record sequence, a unit output power requirement record sequence and a label identifying the service life deviation threshold.

[0029] Specifically, due to differences in design, manufacturing process, use environment, etc., the service life of different types of production equipment has different impacts on energy consumption. Therefore, it is necessary to configure corresponding service life deviation thresholds for production equipment models; among which, the service life sequence refers to a data sequence formed by counting the service life of all equipment of a certain production equipment model.

[0030] Specifically, the service life deviation threshold configuration model is a model based on machine learning, which is used to give the corresponding service life deviation threshold according to the service life sequence and the unit output electricity demand statistical value sequence; the model is trained and generated through multiple groups of data, each group of data includes a service life record sequence, a unit output electricity demand record sequence and a label identifying the service life deviation threshold, and by learning the relationship between these data, the service life deviation threshold corresponding to the production equipment model can be accurately output.

[0031] Specifically, firstly, according to the production equipment model, the service life sequence and unit output power demand sequence are collected. For the unit output power demand sequence, it is necessary to collect the power demand of at least 500 unit output records of the corresponding service life, and take the mode value as the unit output power demand under the service life and store it in the unit output power demand sequence, so as to reduce the impact of abnormal data on the results; then, the service life sequence and the unit output power demand statistical value sequence are input into the pre-trained service life deviation threshold configuration model, and the output result is the service life deviation threshold, which can accurately reflect the impact of the service life of this model of equipment on energy consumption, and provides a reliable basis for subsequent clustering analysis and power demand prediction.

[0032] Specifically, the service life deviation threshold configuration model is a machine learning model, and the training data of the service life deviation threshold configuration model includes multiple groups of service life record sequences, unit output power demand record sequences and labels identifying the service life deviation thresholds that are associated and stored, wherein the service life record sequences and unit output power demand record sequences are training input data, and the label identifying the service life deviation threshold is the expected output of the training; exemplarily, in the service life deviation threshold configuration model, the mean square error (MSE) is selected as the loss function, and the convergence conditions include the loss function value being less than a preset threshold, the loss function value changing less than a threshold in several consecutive iterations, and the training reaching a preset maximum number of iterations, etc. For example, when the loss function value is less than 0.01 or the loss function value changes less than 0.001 in 10 consecutive iterations, it is considered to have converged.

[0033] Through the above steps, the service life deviation threshold is accurately configured, and the production equipment can be clustered more reasonably, so that the equipment in the same cluster has higher similarity in service life and energy consumption characteristics, thereby improving the accuracy of the unit output power requirement labeling, and further improving the refinement of the energy supply planning of the entire park.

[0034] In some implementations, the process of identifying the label identifying the service life deviation threshold includes: A service life record sequence and a unit output power demand record sequence are obtained to construct a fluctuation curve of unit output power demand with service life; the length of the flat segment of the fluctuation curve is extracted, wherein the variance of the unit output power demand in the flat segment is less than or equal to the flat variance threshold, and the deviation of any unit output power demand in the flat segment from the mean of the unit output power demand in the flat segment is less than or equal to the unit output power demand deviation threshold; the length of the shortest flat segment is extracted and stored as a label identifying the service life deviation threshold.

[0035] Specifically, the service life record sequence is a data set of the service life of production equipment arranged in a certain order, reflecting the usage time of different equipment; the unit output power demand record sequence is a data set of the unit output power demand corresponding to each service life record; the fluctuation curve is a curve drawn with the service life as the horizontal axis and the unit output power demand as the vertical axis, which is used to intuitively show the changing trend of the unit output power demand with the service life.

[0036] Specifically, a flat segment refers to an interval on the fluctuation curve where the change in unit electricity demand is relatively small, and the length of the flat segment refers to the length of the service life corresponding to the flat segment; wherein, the flat segment is defined and identified by a flat variance threshold, and when the variance of the unit electricity demand in a segment of the fluctuation curve is less than or equal to the threshold, and the deviation of the unit electricity demand at any point in the segment from the mean unit electricity demand in the segment is less than the unit electricity demand deviation threshold, the segment is considered to be flat.

[0037] Specifically, after extracting all the flat segments that meet the conditions in the fluctuation curve, find the shortest flat segment and store its corresponding length of time as a label that identifies the service life deviation threshold. The shortest flat segment corresponds to the service life range with relatively stable power demand per unit output, which helps to provide a more accurate basis for production equipment clustering.

[0038] S200: traverse the business portrait list of the energy consumption node list, combine it with the predicted power demand list, index the majority carbon emissions of the same portrait samples online, and set it as a predicted carbon emissions list. The energy consumption node list has a carbon quota list.

[0039] Specifically, each energy-consuming node has a corresponding business portrait list, which contains various business characteristics and attribute information of the energy-consuming node. For example, in an industrial park, the business portrait of an energy-consuming node is "a large manufacturing factory that mainly produces metal products, and its production equipment includes stamping machines, welding machines, etc."; among them, samples with the same portrait refer to other nodes with the same business, scale, and power demand as the energy-consuming node.

[0040] Specifically, the energy consumption node list has a carbon quota list, which is a collection of carbon emission quotas owned by each energy consumption node in the park, representing the restriction on the carbon emission of the park.

[0041] Specifically, first, traverse the business portrait list in the energy-consuming node list, combine it with the predicted power demand list, and use the network index to find the same portrait samples that are similar to the current energy-consuming node business portrait; then, extract the mode carbon emissions from multiple same-portrait samples and set it as a value in the predicted carbon emissions list, so as to provide a reference for carbon emissions for subsequent energy supply plan configuration, so that the energy supply plan not only meets the electricity demand of the park, but also takes into account the limitations of carbon emissions, thereby realizing the low-carbonization of the park's energy supply.

[0042] For example, in an industrial park, the business profile of an energy-consuming node is "a large manufacturing factory that mainly produces metal products, and its production equipment includes stamping machines, welding machines, etc." Through online indexing, samples with the same profile similar to the business profile are found. The mode carbon emissions of these samples are 100 tons / month. In the predicted carbon emissions list, the predicted carbon emissions value of the energy-consuming node is 100 tons / month.

[0043] S300: Traversing the photovoltaic energy supply node list to perform energy supply forecasting in the target time zone, and obtaining a forecast energy supply list.

[0044] Specifically, the photovoltaic energy supply node list refers to the collection of all nodes in the park that are equipped with photovoltaic power generation equipment. These nodes can use solar energy to generate electricity and provide clean energy for the park. Energy supply forecasting refers to the process of estimating the amount of electricity that photovoltaic energy supply nodes can generate in the target time zone by collecting and analyzing various relevant data. The forecast energy supply list reflects the forecast energy supply data and is used to provide a reference for subsequent energy supply planning.

[0045] In some embodiments, traversing the photovoltaic energy supply node list to perform energy supply prediction for the target time zone and obtaining a predicted energy supply list includes: The photovoltaic energy supply node includes a first photovoltaic energy supply node, which collects meteorological characteristic time series information of the target time zone; taking the meteorological characteristic time series information as a dynamic constraint and the photovoltaic deployment scale as a static constraint, collecting the mode value of multiple energy storage record values ​​of multiple sample energy supply nodes that meet the dynamic constraint and the static constraint, storing them as a first predicted energy supply and adding them into the predicted energy supply list; wherein, a meteorological characteristic similarity comparison function is constructed: Sim\left ( {A, B} \right )=\sum ^{Y}_{i=1} \left [ {{w}_{i}\sum ^{Q}_{j=1} {\frac {2{x}_{ijA}*{x}_{ijB}+c} {{{x}_{ijA}}^{2}+{{x}_{ijB}}^{2}+c}}} \right ] ; in, Characterizes any two meteorological characteristic time series information of the same duration and meteorological characteristics time series information The similarity of meteorological characteristics, Characterization No. Attributes of meteorological elements The characteristic value at the moment, Characterization No. Attributes of meteorological elements The characteristic value at the moment, Representing the duration constraint, The total number of representation attributes, Characterization The impact weight of attribute meteorological factors on photovoltaic energy storage, Based on the Delphi method weighting, when the meteorological characteristic similarity between the meteorological characteristic record time series information of the sample energy supply node and the meteorological characteristic time series information is greater than or equal to the similarity threshold, it is considered to meet the dynamic constraint.

[0046] Specifically, meteorological characteristic time series information refers to the data sequence of various meteorological-related elements changing over time in the target time zone, including light intensity, temperature, wind speed, etc. The meteorological characteristic time series information is used as a dynamic constraint condition for photovoltaic energy supply, and coordinated with the static constraints based on the photovoltaic deployment scale, so as to extract the mode value of multiple energy storage record values ​​of multiple sample energy supply nodes as the typical value of photovoltaic production capacity corresponding to the meteorological conditions and photovoltaic deployment scale, and output it as the first predicted energy supply, which is stored in the predicted energy supply list.

[0047] Specifically, the meteorological feature similarity comparison function is used to determine whether the sample energy supply node meets the dynamic constraints. The duration constraint refers to the time length limit of the meteorological feature time series information, ensuring that the two compared time series information are consistent in the time dimension. The total number of attributes indicates the number of types of meteorological elements contained in the meteorological feature time series information; the impact weight refers to the importance of each meteorological element in the photovoltaic energy storage process. The Delphi method is used to collect and organize the opinions and judgments of experts on a certain issue to form a relatively accurate weight distribution.

[0048] Specifically, in the meteorological feature similarity comparison function, the introduction of the constant term c is intended to avoid the problem of the denominator being zero in the calculation process and ensure the stability and numerical accuracy of the similarity calculation; specifically, when the two eigenvalues ​​are and When both are zero, the denominator is also zero, which makes the calculation impossible. By adding a constant to the denominator This can effectively avoid this situation; in addition, the constant The introduction of can also enhance the robustness of the model, reduce the impact of numerical errors on the calculation results, and ensure the stability and accuracy of the similarity calculation.

[0049] S400: Taking the predicted power demand list as the energy supply constraint, initializing through the energy supply plan configuration module based on the predicted power supply list, and obtaining a plurality of energy supply planning plans, any of which has an energy supply carbon emission identifier.

[0050] Specifically, the energy supply scheme configuration module is used to initialize based on the predicted power demand list and the predicted power supply list, formulate a detailed energy allocation and supply plan, and output it as several energy supply planning schemes. Among them, the energy supply carbon emission mark refers to the carbon emission mark corresponding to each energy supply planning scheme, which is used to measure the carbon emissions generated after the implementation of the scheme.

[0051] In some embodiments, the predicted power demand list is used as the energy supply constraint, and based on the predicted power supply list, initialization is performed through the energy supply scheme configuration module to obtain several energy supply planning schemes, and any energy supply planning scheme has an energy supply carbon emission identifier, including: The predicted power demand list includes the predicted power demand of the first energy consumption node to the predicted power demand of the Mth energy consumption node; the predicted power supply list includes the predicted power supply of the first energy supply node to the predicted power supply of the Zth energy consumption node; based on the first energy supply node, traverse the first energy consumption node to the Mth energy consumption node to perform unit power transmission historical loss ratio statistics, which is set as the first energy supply loss ratio set; until based on the Zth energy supply node, traverse the first energy consumption node to the Mth energy consumption node to perform unit power transmission historical loss ratio statistics, which is set as the Zth energy supply loss ratio set; give priority to the predicted power supply of the first energy supply node to the predicted power supply of the Zth energy consumption node, analyze the actual power supply delivered to the predicted power demand of the first energy consumption node to the predicted power demand of the Mth energy consumption node based on the first energy supply loss ratio set to the Zth energy supply loss ratio set, when the predicted After all the energy supply lists are scheduled, if the actual energy supply fails to meet the predicted energy demand list, the large power grid is used for supplementary power supply until the energy supply meets the predicted energy demand list to obtain a first energy supply planning scheme; based on the first energy supply node, traverse the first energy consumption node until the Mth energy consumption node to perform historical average carbon emissions statistics per unit of electricity transmission, which is set as the first energy supply carbon emissions set; until based on the Zth energy supply node, traverse the first energy consumption node until the Mth energy consumption node to perform historical average carbon emissions statistics per unit of electricity transmission, which is set as the Zth energy supply carbon emissions set; based on the statistics of the historical average carbon emissions per unit of electricity transmission by the large power grid, obtain the large power grid power transmission carbon emissions identifier; add the first energy supply planning scheme to the several energy supply planning schemes, add the first energy supply carbon emissions set to the Zth energy supply carbon emissions set, and add the large power grid power transmission carbon emissions identifier to the energy supply carbon emissions identifier.

[0052] Specifically, the predicted power demand list and the predicted power supply list respectively contain the power demand of each energy-consuming node and the predicted power supply of the energy supply node in the park. Among them, the energy-consuming nodes and energy supply nodes are classifications of different functional areas in the park. The former are the main electricity users and the latter are the main energy suppliers.

[0053] Specifically, the historical loss ratio of unit electricity transmission is determined based on historical data. It is the proportion of the actual available electricity reduction due to loss during the transmission process of each unit electricity, which reflects the transmission efficiency; the historical carbon emissions per unit electricity transmission refers to the carbon emissions generated during the transmission process of each unit electricity, which is used to evaluate the environmental impact of the energy supply process.

[0054] Specifically, first, for each energy supply node, calculate the historical loss ratio of the unit power transmitted to each energy consumption node, and summarize it into a loss ratio set. For example, for the first energy supply node, calculate the average historical loss ratio of the unit power transmitted from the first energy consumption node to the Mth energy consumption node to form the first energy supply loss ratio set; similarly, form the Zth energy supply loss ratio set for the Zth energy supply node; then, according to the predicted supply amount, prioritize the energy supply nodes in the park to supply energy to the energy consumption nodes, and calculate the actual supply amount that can reach the energy consumption nodes based on the loss ratio set, that is, first perform energy allocation within the park; if the energy supply in the park is insufficient, use the large power grid to supplement it until the requirements of the predicted power demand list are met, thereby forming the first energy supply planning scheme.

[0055] Furthermore, the historical average carbon emissions per unit of electricity delivered by each energy supply node to each energy consumption node are calculated and summarized into a carbon emissions set. For example, the first energy supply node forms the first energy supply carbon emissions set, and the Zth energy supply node forms the Zth energy supply carbon emissions set; at the same time, the carbon emissions identification of the unit electricity delivered by the large power grid is counted, and finally, the first energy supply planning scheme and its corresponding carbon emissions set and the large power grid carbon emissions identification are added to the energy supply planning scheme pool. Through the above method steps, multiple energy supply planning schemes can be generated, each with a clear carbon emissions identification, which provides a basis for subsequent scheme selection.

[0056] S500: Based on the energy supply carbon emission identifier, the carbon quota list and the predicted carbon emission list, the plurality of energy supply planning schemes are sorted for minimum carbon emission, and a selected scheme for the park energy supply planning is obtained and sent to the energy supply management terminal.

[0057] Specifically, all generated energy supply planning schemes are evaluated according to the energy supply carbon emission identification, carbon quota list and predicted carbon emission list, so as to select the scheme with the lowest carbon emission as the final energy supply planning scheme. Among them, the energy supply management end refers to the management platform of the park energy supply system, which is used to receive and execute energy supply planning schemes to ensure the stable operation of the park energy supply system.

[0058] Through the minimum carbon emission sorting, it is ensured that the energy supply plan of the park can reduce carbon emissions as much as possible while meeting energy needs, avoid overspending on carbon quotas, and comply with the low-carbon development goals of the park.

[0059] In some embodiments, based on the energy supply carbon emission identifier, the carbon quota list and the predicted carbon emission list, the plurality of energy supply planning schemes are sorted by minimum carbon emission to obtain a selected scheme for the energy supply planning of the park, including: According to the first energy supply planning scheme of the several energy supply planning schemes, extract the first energy supply node energy of the first energy consumption node until the S-th energy supply node energy; based on the energy supply carbon emission identifier, multiply and add the energy supply of the first energy supply node until the S-th energy supply node to obtain the energy supply carbon emission of the first energy consumption node; add the energy supply carbon emission of the first energy consumption node and the predicted carbon emission of the first energy consumption node to obtain the summed carbon emission of the first energy consumption node; until the summed carbon emission of the M-th energy consumption node is obtained; when any one of the summed carbon emission of the first energy consumption node until the summed carbon emission of the M-th energy consumption node is greater than the corresponding carbon quota in the carbon quota list, delete the first energy supply planning scheme; repeat the cycle to obtain the minimum carbon emission scheme of the retained energy supply planning schemes, and set it as the selected scheme for the park energy supply planning.

[0060] Specifically, first, the first energy supply energy of the first energy consumption node to the S energy supply node is obtained respectively, and then, the energy supply carbon emission identifier of each node is used as the weighted weight, and the weighted summation of the energy supply of the first energy supply node to the S energy supply node is performed to obtain the energy supply carbon emission of the first energy consumption node; then, the sum of the energy supply carbon emission of the first energy consumption node and the predicted carbon emission of the first energy consumption node is taken as the summed carbon emission of the first energy consumption node.

[0061] For example, there are two energy consumption nodes in the park: energy consumption node A and energy consumption node B. Each energy consumption node has two optional energy supply nodes: energy supply node 1 and energy supply node 2. Among them, energy supply node 1 generates 0.5 tons of CO per unit of energy supply. 2 , Energy supply node 2 generates 0.3 tons of CO per unit of energy supply 2 ; The carbon quota list shows that energy consumption node A has a quota of 50 tons of CO 2 , energy consumption node B quota 40 tons CO 2 ; The predicted carbon emissions list shows that energy consumption node A is estimated to emit 10 tons of CO 2 ; Energy consumption node B is estimated to emit 15 tons of CO 2 ; In the energy supply planning scheme, Scheme 1 is that energy-consuming node A obtains 60 units of energy supply from energy supply node 1, and energy-consuming node B obtains 70 units of energy supply from energy supply node 2; Scheme 2 is that energy-consuming node A obtains 80 units of energy supply from energy supply node 2, and energy-consuming node B obtains 50 units of energy supply from energy supply node 1.

[0062] For scenario 1: Energy consumption node A’s energy supply carbon emissions: 60 units × 0.5 tons / unit = 30 tons CO 2 .

[0063] Total carbon emissions of energy consumption node A: 30 tons + 10 tons = 40 tons CO 2 .

[0064] Energy consumption node B’s energy supply carbon emissions: 70 units × 0.3 tons / unit = 21 tons CO 2 .

[0065] Total carbon emissions of energy consumption node B: 21 tons + 15 tons = 36 tons CO 2 .

[0066] Compare total carbon emissions to carbon allowances: Energy consumption node A: 40 tons ≤ 50 tons (compliant); Energy consumption node B: 36 tons ≤ 40 tons (compliant).

[0067] For scenario 2: Energy consumption node A’s energy supply carbon emissions: 80 units × 0.3 tons / unit = 24 tons CO 2 .

[0068] Total carbon emissions of energy consumption node A: 24 tons + 10 tons = 34 tons CO 2 .

[0069] Energy consumption node B’s energy supply carbon emissions: 50 units × 0.5 tons / unit = 25 tons CO 2 .

[0070] Total carbon emissions of energy consumption node B: 25 tons + 15 tons = 40 tons CO 2 .

[0071] Compare total carbon emissions to carbon allowances: Energy consumption node A: 34 tons ≤ 50 tons (compliant); Energy consumption node B: 40 tons ≤ 40 tons (compliant).

[0072] Therefore, Option 2 has a lower total carbon emission, complies with all carbon quota restrictions, and performs better in the minimum carbon emission selection, and was eventually selected as the selected option for the park's energy supply planning.

[0073] The above method steps can accurately evaluate the actual carbon emissions of each energy supply planning scheme by calculating the energy supply carbon emissions and the summed carbon emissions of each energy consumption node, and avoid carbon emissions exceeding the standard due to rough estimates; through minimum carbon emissions sorting, the energy supply planning scheme with the lowest total carbon emissions and meeting the carbon quota constraints is selected to ensure that the park minimizes carbon emissions while meeting energy needs.

[0074] In summary, the park energy supply planning method for zero-carbon park construction provided by the present invention has the following technical effects: By traversing the list of energy-consuming nodes and combining the expected output in the target time zone to predict electricity consumption, a predicted electricity demand list is obtained; the business portrait list of the energy-consuming node list is traversed, combined with the predicted electricity demand list, the majority carbon emissions of the same portrait samples are indexed online and set as the predicted carbon emissions list, and the energy-consuming node list has a carbon quota list; the photovoltaic energy supply node list is traversed to predict the energy supply in the target time zone and obtain a predicted energy supply list; with the predicted electricity demand list as the energy supply constraint, based on the predicted energy supply list, the energy supply scheme configuration module is initialized to obtain several energy supply planning schemes, and any energy supply planning scheme has an energy supply carbon emission identifier; based on the energy supply carbon emission identifier, the carbon quota list and the predicted carbon emission list, the minimum carbon emission is sorted for several energy supply planning schemes, and the selected scheme for the energy supply planning of the park is obtained and sent to the energy supply management end, thereby achieving the technical effect of improving the planning precision and improving the carbon reduction level.

[0075] Embodiment 2: Figure 2 This is a schematic diagram of the structure of a park energy supply planning system for zero-carbon park construction in the present invention. For example, Figure 1 The flow chart of a park energy supply planning method for zero-carbon park construction in the present invention can be shown as follows: Figure 2 The structure shown is implemented.

[0076] Based on the same concept as the park energy supply planning method for zero-carbon park construction in the embodiment, the present invention also provides a park energy supply planning system for zero-carbon park construction, including: The power consumption prediction module 11 is used to traverse the energy consumption node list, make power consumption prediction based on the expected output in the target time zone, and obtain a predicted power demand list.

[0077] The carbon emission prediction module 12 is used to traverse the business portrait list of the energy consumption node list, combine the predicted power demand list, index the majority carbon emission of the same portrait sample online, and set it as the predicted carbon emission list. The energy consumption node list has a carbon quota list.

[0078] The photovoltaic energy supply prediction module 13 is used to traverse the photovoltaic energy supply node list to perform energy supply prediction in the target time zone and obtain a predicted energy supply list.

[0079] The energy supply planning module 14 is used to use the predicted power demand list as the energy supply constraint, initialize through the energy supply plan configuration module based on the predicted power supply list, and obtain several energy supply planning plans, any of which has an energy supply carbon emission mark.

[0080] The carbon emission sorting module 15 is used to sort the several energy supply planning schemes according to the minimum carbon emission based on the energy supply carbon emission identification, the carbon quota list and the predicted carbon emission list, obtain the selected scheme of the park energy supply planning and send it to the energy supply management terminal.

[0081] In some embodiments, the power consumption prediction module 11 includes: The first energy consumption node acquisition unit is used to obtain the first energy consumption node in the energy consumption node list.

[0082] The production equipment position number clustering unit is used to obtain the production equipment position number set of the first energy consuming node, cluster the production equipment position number set according to the service life of the equipment and based on the service life deviation threshold, to obtain the production equipment position number clustering result.

[0083] The unit output power requirement statistics unit is used to traverse the production equipment position number clustering results, select any production equipment to perform unit output power requirement statistics in the past six months, and obtain the unit output power requirement identifier.

[0084] The first predicted power demand calculation unit is used to make a power consumption forecast based on the production distribution information of the target time zone uploaded by the first energy consuming node and the unit production power demand identifier, obtain a first predicted power demand, and add it to the predicted power demand list.

[0085] In some implementations, the production equipment bit number clustering unit in the power consumption prediction module 11 includes: The service life and power demand sequence statistics unit is used to count the service life sequence and the unit output power demand sequence according to the production equipment model, wherein the unit output power demand is equal to the mode value of the power demand of at least 500 unit output records collected for the corresponding service life.

[0086] The service life deviation threshold output unit is used to process the service life sequence and the unit output power demand statistical value sequence through the service life deviation threshold configuration model, and output the service life deviation threshold.

[0087] Among them, the service life deviation threshold configuration model is generated through multiple groups of data based on machine learning training, and any group of the multiple groups of data includes: a service life record sequence, a unit output power demand record sequence and a label identifying the service life deviation threshold.

[0088] In some implementations, the power consumption prediction module 11 further includes: The fluctuation curve construction unit is used to obtain a service life record sequence and a unit output power demand record sequence, and to construct a fluctuation curve of the unit output power demand with the service life.

[0089] The flat segment length extraction unit is used to extract the flat segment length of the fluctuation curve, wherein the unit output power demand variance of the flat segment is less than or equal to the flat variance threshold, and the deviation of any unit output power demand of the flat segment from the average unit output power demand of the flat segment is less than or equal to the unit output power demand deviation threshold.

[0090] The service life deviation threshold label generation unit is used to extract the length of the shortest flat segment and store it as the label identifying the service life deviation threshold.

[0091] In some embodiments, the photovoltaic energy supply prediction module 13 includes: The first photovoltaic energy supply node meteorological characteristic collection unit is used to collect meteorological characteristic time series information of the target time zone.

[0092] The first predicted energy supply calculation unit is used to use the meteorological characteristic time series information as a dynamic constraint and the photovoltaic deployment scale as a static constraint, collect the mode values ​​of multiple energy storage record values ​​of multiple sample energy supply nodes that meet the dynamic constraint and the static constraint, store them as the first predicted energy supply and add them into the predicted energy supply list.

[0093] Among them, the meteorological characteristics similarity comparison function is constructed: Sim\left ( {A, B} \right )=\sum ^{Y}_{i=1} \left [ {{w}_{i}\sum ^{Q}_{j=1} {\frac {2{x}_{ijA}*{x}_{ijB}+c} {{{x}_{ijA}}^{2}+{{x}_{ijB}}^{2}+c}}} \right ] ; in, Characterizes any two meteorological characteristic time series information of the same duration and meteorological characteristics time series information The similarity of meteorological characteristics, Characterization No. Attributes of meteorological elements The moment characteristic value, Characterization No. Attributes of meteorological elements The characteristic value at the moment, Representing the duration constraint, The total number of representation attributes, Characterization The impact weight of attribute meteorological factors on photovoltaic energy storage, Empowerment based on the Delphi method.

[0094] When the meteorological characteristic similarity between the meteorological characteristic record time series information of the sample energy supply node and the meteorological characteristic time series information is greater than or equal to the similarity threshold, it is deemed that the dynamic constraint is met.

[0095] In some embodiments, the energy supply planning module 14 includes: The energy supply loss ratio set acquisition unit is used to perform historical unit power transmission loss ratio statistics based on the first energy supply node, traverse the first energy consumption node until the Mth energy consumption node, and set it as the first energy supply loss ratio set. Until based on the Zth energy supply node, traverse the first energy consumption node until the Mth energy consumption node, and set it as the Zth energy supply loss ratio set.

[0096] The first energy supply planning scheme generating unit is used for giving priority to scheduling the predicted energy supply of the first energy supply node to the predicted energy supply of the Zth energy consumption node, analyzing the actual energy supply delivered to the predicted energy demand of the first energy consumption node to the predicted energy demand of the Mth energy consumption node based on the first energy supply loss ratio set to the Zth energy supply loss ratio set, and when the predicted energy supply list is fully scheduled, the actual energy supply fails to meet the predicted energy demand list, and a large power grid is used for supplementary power supply until the energy supply meets the predicted energy demand list to obtain a first energy supply planning scheme.

[0097] The energy supply carbon emission set acquisition unit is used to perform historical carbon emission statistics per unit of electricity transmission based on the first energy supply node, traverse the first energy consumption node until the Mth energy consumption node, and set it as the first energy supply carbon emission set. Until based on the Zth energy supply node, traverse the first energy consumption node until the Mth energy consumption node to perform historical carbon emission statistics per unit of electricity transmission, and set it as the Zth energy supply carbon emission set.

[0098] The large power grid power transmission carbon emission identification acquisition unit is used to obtain the large power grid power transmission carbon emission identification based on the large power grid statistical unit electricity transmission historical carbon emission average statistics.

[0099] The energy supply planning scheme and carbon emission identification integration unit is used to add the first energy supply planning scheme into the several energy supply planning schemes, and add the first energy supply carbon emission set to the Zth energy supply carbon emission set, and the large power grid power transmission carbon emission identification into the energy supply carbon emission identification.

[0100] In some embodiments, the carbon emission sorting module 15 includes: The energy supply planning scheme extraction unit is used to extract the first energy supply node energy of the first energy consumption node until the Sth energy supply node energy according to the first energy supply planning scheme of the plurality of energy supply planning schemes.

[0101] The energy supply carbon emission calculation unit is used to obtain the energy supply carbon emission of the first energy consumption node by performing product addition calculation based on the energy supply carbon emission identifier and the energy supply of the first energy supply node to the Sth energy supply node.

[0102] The summed carbon emission calculation unit is used to add the energy supply carbon emission of the first energy consumption node and the predicted carbon emission of the first energy consumption node to obtain the summed carbon emission of the first energy consumption node.

[0103] The carbon emission comparison and scheme deletion unit is used to obtain the summed carbon emission of the Mth energy consumption node. When any one of the summed carbon emission of the first energy consumption node and the summed carbon emission of the Mth energy consumption node is greater than the corresponding carbon quota in the carbon quota list, the first energy supply planning scheme is deleted.

[0104] The minimum carbon emission scheme determination unit is used to repeat the cycle to obtain the minimum carbon emission scheme of the retained energy supply planning scheme, and set it as the selected scheme for the energy supply planning of the park.

[0105] It should be understood that the embodiments mentioned in this specification focus on their differences from other embodiments. The specific embodiments in the aforementioned embodiment one are also applicable to a park energy supply planning system for zero-carbon park construction described in embodiment two. For the sake of brevity of the specification, they will not be further elaborated here.

[0106] It should be understood that the embodiments disclosed in the present invention and the above description can enable those skilled in the art to use the present invention to implement the present invention. At the same time, the present invention is not limited to the above-mentioned embodiments. It should be understood that those skilled in the art can still modify the technical solutions recorded in the above-mentioned embodiments, or replace some of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A park energy supply planning method for zero-carbon park construction, characterized in that: include: Traverse the list of energy-consuming nodes, make a power consumption forecast based on the expected output in the target time zone, and obtain a list of predicted power requirements; Traversing the business portrait list of the energy consumption node list, combining the predicted power demand list, indexing the majority carbon emissions of the same portrait samples online, and setting it as the predicted carbon emissions list, the energy consumption node list has a carbon quota list; Traverse the photovoltaic energy supply node list to predict the energy supply in the target time zone and obtain the predicted energy supply list; Taking the predicted power demand list as the energy supply constraint, initializing through the energy supply plan configuration module based on the predicted power supply list, obtaining a plurality of energy supply planning schemes, any of which has an energy supply carbon emission identifier; Based on the energy supply carbon emission identifier, the carbon quota list and the predicted carbon emission list, the plurality of energy supply planning schemes are sorted for minimum carbon emission, and the selected scheme for the park energy supply planning is obtained and sent to the energy supply management terminal.

2. The method according to claim 1, characterized in that Traverse the list of energy-consuming nodes, make a power consumption forecast based on the expected output in the target time zone, and obtain a list of predicted power requirements, including: Obtain the first energy-consuming node in the energy-consuming node list; Obtaining a set of production equipment bit numbers of the first energy consuming node, clustering the set of production equipment bit numbers according to the service life of the equipment and based on a service life deviation threshold, to obtain a production equipment bit number clustering result; Traverse the clustering results of the production equipment position numbers, select any production equipment to perform unit production power demand statistics in the past six months, and obtain a unit production power demand identifier; According to the production distribution information of the target time zone uploaded by the first energy consuming node, the power consumption is predicted in combination with the unit output power demand identifier to obtain a first predicted power demand, which is added to the predicted power demand list.

3. The method according to claim 2, characterized in that The service life deviation threshold corresponds to the production equipment model one by one, and the configuration steps include: According to the production equipment model, a service life sequence and a unit output power requirement sequence are counted, wherein the unit output power requirement is equal to the mode value of the power requirement of at least 500 unit output records collected for the corresponding service life; Processing the service life sequence and the unit output power demand statistical value sequence through a service life deviation threshold configuration model, and outputting the service life deviation threshold; Among them, the service life deviation threshold configuration model is generated through multiple groups of data based on machine learning training, and any group of the multiple groups of data includes: a service life record sequence, a unit output power demand record sequence and a label identifying the service life deviation threshold.

4. The method according to claim 3, characterized in that The identification process of the label identifying the service life deviation threshold includes: Obtain service life record sequence and unit output power requirement record sequence, and construct a fluctuation curve of unit output power requirement with service life; Extracting the length of the flat segment of the fluctuation curve, wherein the variance of the unit output power demand of the flat segment is less than or equal to the flat variance threshold, and the deviation of any unit output power demand of the flat segment from the mean unit output power demand of the flat segment is less than or equal to the unit output power demand deviation threshold; The length of the shortest flat segment is extracted and stored as a label identifying the service life deviation threshold.

5. The method according to claim 1, characterized in that Traverse the photovoltaic energy supply node list to predict the energy supply in the target time zone and obtain the predicted energy supply list, including: The photovoltaic energy supply node includes a first photovoltaic energy supply node, which collects meteorological characteristic time series information of the target time zone; Taking the meteorological characteristic time series information as a dynamic constraint and the photovoltaic deployment scale as a static constraint, collecting the mode values ​​of multiple energy storage record values ​​of multiple sample energy supply nodes that meet the dynamic constraint and the static constraint, storing them as a first predicted energy supply and adding them into the predicted energy supply list; Among them, the meteorological characteristics similarity comparison function is constructed: Sim\left ( {A,B} \right )=\sum ^{Y}_{i=1} \left [ {{w}_{i}\sum ^{Q}_{j=1} {\frac {2{x}_{ijA}*{x}_{ijB}+c} {{{x}_{ijA}}^{2}+{{x}_{ijB}}^{2}+c}}} \right ] 4 in, Characterizes any two meteorological characteristic time series information of the same duration and meteorological characteristics time series information The similarity of meteorological characteristics, Characterization No. Attributes of meteorological elements The characteristic value at the moment, Characterization No. Attributes of meteorological elements The characteristic value at the moment, Representing the duration constraint, The total number of representation attributes, Characterization The impact weight of attribute meteorological factors on photovoltaic energy storage, Empowerment based on the Delphi method; When the meteorological characteristic similarity between the meteorological characteristic record time series information of the sample energy supply node and the meteorological characteristic time series information is greater than or equal to the similarity threshold, it is deemed that the dynamic constraint is met.

6. The method according to claim 1, characterized in that The predicted power demand list is used as the energy supply constraint. Based on the predicted power supply list, the energy supply scheme configuration module is initialized to obtain several energy supply planning schemes. Any energy supply planning scheme has an energy supply carbon emission identifier, including: The predicted power demand list includes the predicted power demand of the first energy consumption node to the predicted power demand of the Mth energy consumption node; The predicted energy supply list includes the predicted energy supply of the first energy supply node to the predicted energy supply of the Zth energy consumption node; Based on the first energy supply node, traverse the first energy consumption node until the Mth energy consumption node to perform statistics on the average value of the historical loss ratio of unit power transmission, and set it as the first energy supply loss ratio set; Until based on the Zth energy supply node, traverse the first energy consumption node until the Mth energy consumption node to perform unit power transmission historical loss ratio average statistics, which is set as the Zth energy supply loss ratio set; Prioritize scheduling the predicted energy supply of the first energy supply node to the predicted energy supply of the Zth energy consumption node, analyze the actual energy supply delivered to the predicted power demand of the first energy consumption node to the predicted power demand of the Mth energy consumption node based on the first energy supply loss ratio set to the Zth energy supply loss ratio set, and when the predicted energy supply list is fully scheduled, the actual energy supply does not meet the predicted power demand list, use the large power grid for supplementary power supply until the energy supply meets the predicted power demand list to obtain a first energy supply planning scheme; Based on the first energy supply node, traverse the first energy consumption node until the Mth energy consumption node to perform historical carbon emission statistics per unit of electricity transmission, which is set as the first energy supply carbon emission set; Until based on the Zth energy supply node, traverse the first energy consumption node until the Mth energy consumption node to perform historical carbon emission statistics per unit of electricity transmission, which is set as the Zth energy supply carbon emission set; Based on the historical average carbon emissions per unit of electricity transmission in the large power grid, the carbon emissions mark of power transmission in the large power grid is obtained; The first energy supply planning scheme is added into the several energy supply planning schemes, the first energy supply carbon emission set is connected to the Zth energy supply carbon emission set, and the large power grid power transmission carbon emission identifier is added into the energy supply carbon emission identifier.

7. The method according to claim 1, characterized in that Based on the energy supply carbon emission identifier, the carbon quota list and the predicted carbon emission list, the plurality of energy supply planning schemes are sorted by minimum carbon emission to obtain a selected scheme for the energy supply planning of the park, including: According to a first energy supply planning scheme of the plurality of energy supply planning schemes, extracting a first energy supply node supply energy of a first energy consumption node until an Sth energy supply node supply energy; Based on the energy supply carbon emission identifier, multiply and add the energy supply of the first energy supply node to the energy supply of the Sth energy supply node to obtain the energy supply carbon emission of the first energy consumption node; Adding the energy supply carbon emission of the first energy consumption node and the predicted carbon emission of the first energy consumption node to obtain the summed carbon emission of the first energy consumption node; Until the sum of carbon emissions of the Mth energy consumption node is obtained; When any one of the sum of carbon emissions of the first energy consumption nodes up to the sum of carbon emissions of the Mth energy consumption node is greater than the corresponding carbon quota in the carbon quota list, the first energy supply planning scheme is deleted; The cycle is repeated to obtain the minimum carbon emission plan of the retained energy supply planning plan, which is set as the selected plan for the energy supply planning of the park.

8. A park energy supply planning system for zero-carbon park construction, characterized in that: The system is used to execute a park energy supply planning method for zero-carbon park construction according to any one of claims 1 to 7, and the system includes: The power consumption prediction module is used to traverse the list of energy-consuming nodes, make power consumption predictions based on the expected output in the target time zone, and obtain a list of predicted power requirements; A carbon emission prediction module is used to traverse the business portrait list of the energy consumption node list, combine the predicted power demand list, network index the majority carbon emission of the same portrait sample, and set it as the predicted carbon emission list. The energy consumption node list has a carbon quota list; The photovoltaic energy supply prediction module is used to traverse the photovoltaic energy supply node list to perform energy supply prediction for the target time zone and obtain a predicted energy supply list; An energy supply planning module is used to use the predicted power demand list as an energy supply constraint, initialize through an energy supply scheme configuration module based on the predicted power supply list, and obtain a plurality of energy supply planning schemes, any of which has an energy supply carbon emission identifier; The carbon emission sorting module is used to sort the several energy supply planning schemes according to the minimum carbon emission based on the energy supply carbon emission identification, the carbon quota list and the predicted carbon emission list, obtain the selected scheme of the park energy supply planning and send it to the energy supply management terminal.

Images