A comprehensive energy carbon management multi-energy collaborative low-carbon planning method and system

Abstract

The application discloses a kind of integrated energy carbon management multi-energy collaborative low-carbon planning method and system, it is related to multi-energy collaborative management technical field, the technical problems that the existing technology exists are solved, carbon emission quota allocation is disjointed with multi-energy collaborative planning, and weather fluctuation influence is not considered, leading to the technical problem that the efficiency of multi-energy collaborative planning is lower;Including: generating the carbon emission proportion matrix corresponding to each period based on historical electricity consumption data;Obtain the remaining carbon emission quota, generate carbon emission quota sequence based on carbon emission proportion matrix and remaining carbon emission quota, obtain the weather data corresponding to collaborative management area;Based on weather data, the power estimation sequence corresponding to each first energy equipment is obtained by estimating the capacity of first energy equipment;Collaborative planning scheme is generated based on the power estimation sequence corresponding to each first energy equipment and carbon emission quota sequence;Realize the fine allocation of carbon emission quota in time dimension and the low-carbon collaborative planning of multi-energy power supply.

Description

Technical Field

[0001] This application belongs to the field of multi-energy collaborative management technology, specifically a comprehensive energy carbon management multi-energy collaborative low-carbon planning method and system. Background Technology

[0002] In integrated energy management scenarios, the collaborative management area is usually equipped with renewable energy power generation equipment, such as photovoltaic power generation equipment and wind power generation equipment, as well as conventional energy power generation equipment, such as gas power generation equipment and coal-fired power generation equipment. It is necessary to coordinate the power supply of various energy equipment according to the electricity demand.

[0003] Currently, multi-energy coordinated planning typically aims at balancing supply and demand. Under the premise of meeting electricity demand, it prioritizes the predicted power generation of renewable energy power generation equipment, supplementing any shortfall with conventional energy power generation equipment. However, this planning approach has a relatively crude control over carbon emissions, usually allocating carbon emission allowances to different time periods through total emission constraints or average allocation. Since the actual power generation of renewable energy power generation equipment is greatly affected by environmental fluctuations, accurate prediction is difficult. When the actual output of renewable energy power generation equipment deviates from the predicted value due to weather fluctuations, conventional energy power generation equipment is often temporarily activated to supplement power, resulting in additional carbon emissions. This failure to fully consider the impact of different time periods' electricity consumption structures, power supply structures, and weather conditions on energy planning makes it difficult to achieve low-carbon planning goals, and the accuracy of coordinated planning results is insufficient, leading to low overall efficiency. Therefore, a comprehensive energy carbon management multi-energy coordinated low-carbon planning method and system is needed. Summary of the Invention

[0004] This application provides a comprehensive energy carbon management method and system for multi-energy collaborative low-carbon planning. It solves the problems of existing technologies where carbon emission quota allocation is disconnected from multi-energy collaborative planning and does not consider the impact of weather fluctuations, resulting in low efficiency of multi-energy collaborative planning. This application uses a comprehensive energy carbon management method to generate a carbon emission ratio matrix based on historical electricity consumption data, generate a carbon emission quota sequence by combining the remaining carbon emission quota, and predict the capacity of the first energy equipment based on weather data, thereby generating a collaborative planning scheme. This achieves refined allocation of carbon emission quotas in the time dimension and low-carbon collaborative planning of multi-energy power supply.

[0005] To achieve the above objectives, this application adopts the following technical solution: Firstly, a comprehensive energy carbon management and multi-energy coordinated low-carbon planning method is provided, including: Acquire some historical electricity consumption data, and generate a carbon emission ratio matrix corresponding to each time period based on the historical electricity consumption data; obtain the remaining carbon emission credits, and generate a carbon emission credit sequence based on the carbon emission ratio matrix and the remaining carbon emission credits, wherein the carbon emission credit sequence includes the carbon emission credits for each time period. Acquire weather data corresponding to the collaborative management area; the weather data is obtained through weather monitoring towers or weather forecasts on the network; based on the weather data, the production capacity of the first energy equipment is estimated to obtain the power estimation sequence corresponding to each first energy equipment; the first energy equipment is a renewable energy power generation equipment, including photovoltaic power generation and wind power generation, etc., and the power estimation sequence is the estimated power generation of the corresponding first energy equipment in each time period within a future set time period; A collaborative planning scheme is generated based on the power forecast sequence and carbon emission quota sequence corresponding to each primary energy device. The collaborative planning scheme includes the power demand of each primary energy device and secondary energy device.

[0006] In conjunction with the first aspect above, in one possible implementation, generating the carbon emission ratio matrix for each time period based on historical electricity consumption data includes: Extract the periodic electricity consumption data within each electricity consumption cycle from the historical electricity consumption data. The electricity consumption cycle is a set time length, generally one day. Extract the electricity consumption for each time period in each period of the electricity consumption data. After normalizing the electricity consumption for each time period, the normalized value is the proportion of the electricity consumption for each time period to the electricity consumption for one electricity cycle; the electricity consumption is integrated into a time period electricity consumption sequence corresponding to the electricity cycle according to a set order; the time period electricity consumption sequence corresponding to each electricity cycle is generated in sequence; the average value corresponding to the element at the same position in each time period electricity consumption sequence is calculated, the average value is used as the feature value of that position, and a cycle electricity consumption feature matrix is ​​constructed based on these feature values; Extract the weather type corresponding to each period of electricity consumption data, and the power supply data for each time period within each period of electricity consumption data; the power supply data for each time period is the power supply of various types of energy devices in the corresponding time period; extract the power supply of each energy device in the power supply data for each time period; the energy devices include first energy devices and second energy devices; calculate the power supply ratio of each energy device corresponding to the power supply data for each time period based on the power supply of each energy device, and integrate the power supply ratios of each energy device into a time period power supply ratio sequence according to a set order; Obtain the power supply ratio sequence for each time period in the power consumption data of each cycle with the same weather type; calculate the average value of the elements at the same position in each time period power supply ratio sequence, use the average value as the feature value of that position, and construct the time period power supply ratio feature sequence for the time period corresponding to the weather type based on the feature value, generate the power supply ratio feature sequence for each time period corresponding to the weather type in sequence, integrate the power supply ratio feature sequences corresponding to each time period into the power supply feature matrix corresponding to the weather type; generate the power supply feature matrix corresponding to each weather type in sequence. Obtain the carbon emission factors corresponding to each energy device, and integrate the carbon emission factors into a carbon emission factor feature matrix in a set order; generate a carbon emission ratio matrix based on the periodic electricity consumption feature matrix, the power supply feature matrix and the carbon emission factor feature matrix, wherein the carbon emission ratio matrix contains the carbon emission ratio corresponding to each time period.

[0007] In conjunction with the first aspect above, in one possible implementation, generating the carbon emission ratio matrix based on the cyclic electricity consumption characteristic matrix, the power supply characteristic matrix, and the carbon emission factor characteristic matrix includes: Obtain the carbon emission factor feature matrix and the power supply feature matrix, and calculate the comprehensive carbon emission factor matrix corresponding to each time period based on each element in the carbon emission factor feature matrix and the power supply feature matrix; specifically, obtain the carbon emission factor feature matrix. and power supply characteristic matrix ;in, The carbon emission factor feature matrix is ​​numbered as follows The carbon emission factor corresponding to energy equipment; The first in the power supply characteristic matrix The time period corresponds to the number. The power supply ratio corresponding to energy equipment; the comprehensive carbon emission factor corresponding to each time period under each weather type is calculated using the formula: ; in, For the first The corresponding comprehensive carbon emission factor for each time period , The number of energy devices; and the various integrated carbon emission factors. Integrating into a comprehensive carbon emission factor matrix ; The process involves obtaining a cyclical electricity consumption characteristic matrix, calculating a carbon emission intensity matrix based on the cyclical electricity consumption characteristic matrix and the comprehensive carbon emission factor matrix, and then normalizing each carbon emission intensity in the carbon emission intensity matrix to obtain a carbon emission proportion matrix. Specifically, the cyclical electricity consumption characteristic matrix is ​​obtained. ;in, For the first The electricity consumption ratio corresponding to the time period; the carbon emission intensity matrix calculated based on the periodic electricity consumption characteristic matrix and the comprehensive carbon emission factor matrix includes: ; in, For carbon emission intensity matrix, Carbon emission intensity matrix The corresponding number in the middle Carbon emission intensity over a given period; The carbon emission proportion matrix is ​​obtained by normalizing each carbon emission intensity in the carbon emission intensity matrix, including: ; in, A carbon emission ratio matrix; Carbon emission ratio matrix The corresponding number in the middle Carbon emission ratio for a given period; , This refers to the number of time periods within an electricity consumption cycle.

[0008] In conjunction with the first aspect above, in one possible implementation, generating the carbon emission credit sequence based on the carbon emission proportion matrix and the remaining carbon emission credits includes: Obtain the remaining carbon emission allowance and the number of electricity cycles corresponding to the remaining carbon emission allowance; calculate the cycle carbon emission allowance corresponding to each electricity cycle; Obtain the weather type corresponding to the predicted electricity consumption cycle in the collaborative management area, obtain the carbon emission ratio matrix corresponding to the weather type, calculate the carbon emission quota for each period and the carbon emission ratio corresponding to each time period in the carbon emission ratio matrix to obtain the carbon emission quota for each time period, and integrate the carbon emission quotas corresponding to each time period into a carbon emission quota sequence according to a set order.

[0009] In conjunction with the first aspect above, in one possible implementation, the step of estimating the production capacity of the first energy equipment based on weather data to obtain a power prediction sequence corresponding to each first energy equipment includes: Extract several time-period weather parameters corresponding to each time period from the weather data corresponding to the collaborative management area. The weather parameters are weather parameters related to each first energy device. For example, when the first energy data includes photovoltaics, the time-period weather parameters include parameters related to photovoltaic power generation. The time periods in the weather data generally include each time period within the planned electricity consumption cycle. The planned electricity consumption cycle includes the remaining time period of the current electricity consumption cycle and the next electricity consumption cycle. Obtain weather parameters for several time periods corresponding to each first energy device, input the weather parameters for each time period into the power generation prediction model corresponding to the first energy device, obtain the power prediction value of the first energy device in the corresponding time period, integrate the power prediction values ​​according to the order of their corresponding time periods into a success rate prediction sequence; and generate the power prediction sequence corresponding to each first energy device in sequence.

[0010] In conjunction with the first aspect above, in one possible implementation, the generation of a collaborative planning scheme based on the power prediction sequence and carbon emission quota sequence corresponding to each first energy device includes: Obtain the electricity demand sequence; based on the electricity demand sequence, the power prediction sequence and carbon emission quota sequence corresponding to each primary energy device, generate available collaborative solutions for the primary and secondary energy devices; Acquire weather data for the collaborative management area and other areas within a defined range, and generate weather fluctuation indices for each time period based on the weather data; The final collaborative planning scheme is selected from all available collaborative schemes based on the weather fluctuation index.

[0011] In conjunction with the first aspect above, in one possible implementation, generating available collaborative schemes for the first and second energy devices based on the electricity demand sequence, the power estimation sequence corresponding to each first energy device, and the carbon emission quota sequence includes: A supply-demand balance constraint is constructed based on the electricity demand sequence and the power forecast sequence corresponding to each primary energy device; the supply-demand balance constraint is as follows: ; ; in, For the number The first energy device in the The required power supply for the corresponding time period; For the number The second energy device in the The required power supply for the corresponding time period; For the number The first energy device corresponds to the predicted power generation sequence in the first energy device Power estimates for the corresponding time period; The first in the electricity demand sequence Electricity demand corresponding to the time period; This is the number corresponding to the first energy device, and , The number of primary energy equipment; This is the number corresponding to the second energy device, and , The number of secondary energy facilities; ; This represents the length of each time period. By applying supply and demand balance constraints, combinations of estimated power generation from primary energy equipment and power demand from secondary energy equipment are obtained; these combinations are denoted as undetermined collaborative schemes; carbon emission quota constraints are constructed based on the carbon emission quota sequence; the carbon emission quota constraints are as follows: ; in, No. Among the pending collaborative solutions, the one numbered is... The first energy device in the The required power supply for the corresponding time period For the number The carbon emission factor corresponding to the first energy equipment; No. Among the pending collaborative solutions, the one numbered is... The second energy device in the The required power supply for the corresponding time period For the number The carbon emission factor corresponding to the second energy equipment; The first in the carbon emission credit series Carbon emission allowances corresponding to the time period; Several undetermined collaborative schemes that meet the carbon emission quota constraints are denoted as available collaborative schemes.

[0012] In conjunction with the first aspect above, in one possible implementation, generating a weather fluctuation index corresponding to each time period based on the weather data includes: Acquire weather data for each region within a set range; extract several time-period weather parameters from the weather data for each time period; normalize and integrate the several time-period weather parameters for each time period into a time-period weather feature vector for the region. The weather fluctuation index for each time period is obtained by substituting the weather feature vectors of the collaborative management area and the corresponding time period of each area into a set weather fluctuation index generation function; one expression of the weather fluctuation index generation function includes: ; in, For the first Weather fluctuation index corresponding to the time period; For collaborative management of the region The weather feature vector corresponding to the time period; Number The region The weather feature vector corresponding to the time period. Assign corresponding numbers to other areas within the collaborative management area, and , Set the total number of other areas within the collaborative management area; For collaborative management of the region The weather feature vector corresponding to the time period. Number the time period variable, and ; These are spatially discrete weighting coefficients. This is the time inertia weighting coefficient, and .

[0013] In conjunction with the first aspect above, in one possible implementation, the selection of the final collaborative planning scheme from various available collaborative schemes based on the weather fluctuation index includes: Obtain the weather fluctuation index corresponding to each time period, as well as the required power supply for each primary energy device and secondary energy device in each available collaborative solution during each time period; A collaborative planning objective function is constructed by using the weather fluctuation index corresponding to each time period, the required power supply of the first energy device, and the second energy device; the collaborative planning objective function is: ; in, For the number The combined carbon emissions corresponding to the available collaborative solutions; For the number The basic carbon emissions corresponding to the available collaborative solutions, that is, the carbon emissions generated by the normal execution of the available collaborative solutions; For the number The first penalty carbon emissions corresponding to the available synergistic solutions, The second penalty is for carbon emissions; One method for calculating the baseline carbon emissions includes: ; First penalty: carbon emissions One method of obtaining it includes: ; in, For the first Among the available collaborative solutions, the one numbered is... The second energy device in the The equivalent emergency supplementary power corresponding to the time period; Second penalty for carbon emissions One method of acquisition includes: ; in, For the number The corresponding second energy device is in Power conversion The carbon emissions corresponding to the additional power generation equipment consumption; For the number The corresponding second energy device is in Power conversion The carbon emissions corresponding to the additional power generation equipment consumption; This is the carbon emission function for state transitions.

[0014] Secondly, this application provides a comprehensive energy carbon management and multi-energy collaborative low-carbon planning system, comprising: a data acquisition module, a database, a data analysis module, and a collaborative control module; wherein, The data acquisition module is used to acquire weather data corresponding to the collaborative management area; The data analysis module includes a time-period quota generation unit, a power prediction unit, and a collaborative planning unit; The time-period quota generation unit obtains several historical electricity consumption data through a database connected to it, generates a carbon emission ratio matrix corresponding to each time period based on the historical electricity consumption data, obtains the remaining carbon emission quota, and generates a carbon emission quota sequence based on the carbon emission ratio matrix and the remaining carbon emission quota, the carbon emission quota sequence including the time-period carbon emission quota corresponding to each time period. The power estimation unit is used to acquire weather data corresponding to the collaborative management area; based on the weather data, it performs capacity estimation of the first energy equipment to obtain the power estimation sequence corresponding to each first energy equipment. The collaborative planning unit generates a collaborative planning scheme based on the power prediction sequence and carbon emission quota sequence corresponding to each first energy device. The collaborative planning scheme includes the required power supply of each first energy device and second energy device. The collaborative control module is used to control each of the first energy devices and the second energy devices based on a collaborative planning scheme. The first energy devices are renewable energy power generation devices, and the second energy devices are non-renewable energy power generation devices.

[0015] Beneficial effects: This application generates a carbon emission ratio matrix using historical electricity consumption data, allocates the remaining carbon emission allowance according to the carbon emission ratio of each time period, and generates a carbon emission allowance sequence. This ensures that the allocation of carbon emission allowances matches the electricity consumption and power supply structure of each time period, avoids the extensive allocation of carbon emission allowances in the time dimension, improves the precision of carbon emission allowance allocation, and enhances the overall efficiency of multi-energy collaborative planning.

[0016] This application estimates the capacity of the primary energy equipment based on weather data, obtains the power prediction sequence of each primary energy equipment, and generates a usable collaborative scheme under the constraints of supply and demand balance and carbon emission quota. This collaborative planning scheme can meet the electricity demand while controlling carbon emissions within the allocated quota.

[0017] This application introduces a weather fluctuation index to quantify the spatial dispersion and temporal inertia of weather in the collaborative management area. Based on the weather fluctuation index, a collaborative planning objective function is constructed that includes a base carbon emission, a first penalty carbon emission, and a second penalty carbon emission. The application incorporates the emergency supplementary carbon emissions that may be caused by weather fluctuations and the additional carbon emissions generated by equipment power state transitions into the scheme evaluation. The final collaborative planning scheme is selected with the goal of minimizing the overall carbon emissions, which reduces the adverse impact of weather fluctuations on the low-carbon planning objectives and improves the reliability of carbon emission control under weather fluctuation conditions in multi-energy collaborative planning.

[0018] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram illustrating the steps of the multi-energy synergistic low-carbon planning method in this application; Figure 2 This is a schematic diagram of the module connections of the multi-energy collaborative low-carbon planning system in this application. Detailed Implementation

[0021] The technical solutions of this application will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0022] Example 1: Please see Figure 1 This embodiment provides a comprehensive energy carbon management method for multi-energy coordinated low-carbon planning. This method is used to plan the power supply capacity of multiple types of energy devices within a coordinated management area, ensuring that the planning results meet electricity demand while also controlling carbon emissions. The coordinated management area refers to a specific geographical area requiring comprehensive energy carbon management, such as an industrial park, a commercial complex, or a residential community.

[0023] S100: Acquire historical electricity consumption data and generate a carbon emission ratio matrix for each time period based on the historical electricity consumption data. The historical electricity consumption data refers to the electricity-related data accumulated in the collaboratively managed area over several past electricity consumption cycles. The electricity consumption cycle is a set time length; for example, when an electricity consumption cycle is one day, it can be divided into 24 time periods, each corresponding to one hour; or it can be divided into 96 time periods, each corresponding to 15 minutes. The carbon emission ratio matrix is ​​used to characterize the proportion of carbon emissions in each time period within an electricity consumption cycle to the total carbon emissions of that cycle. The historical electricity consumption data includes information such as electricity consumption in each time period and power supply from various energy devices. By statistically analyzing and calculating this information, a carbon emission ratio matrix reflecting the carbon emission proportion characteristics of different time periods can be obtained.

[0024] S200, Obtain the remaining carbon emission allowances, and generate a carbon emission allowance sequence based on the carbon emission ratio matrix and the remaining carbon emission allowances. The carbon emission allowance sequence includes the carbon emission allowances for each time period. The remaining carbon emission allowances are the total amount of unused carbon emission quotas in the collaborative management area within the set planning period. The carbon emission allowance sequence is obtained by allocating the remaining carbon emission allowances according to the carbon emission ratio matrix for each time period. Each element in the sequence corresponds to the upper limit of carbon emissions allowed to be generated within the electricity consumption cycle for a given time period. By refining the carbon emission allowances to each time period, carbon emission constraints are shifted from the total amount to the time dimension, providing a time-specific carbon emission constraint basis for subsequent collaborative planning.

[0025] S300, acquire weather data corresponding to the collaborative management area; the weather data is obtained through weather monitoring towers or weather forecasts on the network; based on the weather data, the capacity of the first energy equipment is estimated to obtain the power estimation sequence corresponding to each first energy equipment; wherein, the first energy equipment is renewable energy power generation equipment, such as photovoltaic power generation equipment, wind power generation equipment, etc.; the weather data can be obtained through weather monitoring towers or through weather forecast services on the network; the weather data includes weather parameters related to the power generation capacity of the first energy equipment, such as solar irradiance, temperature, cloud cover, wind speed, wind direction, etc.; the power estimation sequence is a sequence formed by arranging the estimated power generation of each first energy equipment in the future set time period in chronological order; since the power generation capacity of the first energy equipment is greatly affected by weather conditions, capacity estimation based on weather data can provide output prediction data of renewable energy power generation side for subsequent collaborative planning.

[0026] S400: A collaborative planning scheme is generated based on the power forecast sequence and carbon emission quota sequence corresponding to each first energy device. The collaborative planning scheme includes the required power supply of each first energy device and each second energy device. The second energy device is a conventional energy power generation device, such as a gas-fired power generation device or a coal-fired power generation device. The power generation of the second energy device is highly dispatchable and can supplement the power supply when the output of the first energy device is insufficient. The collaborative planning scheme is used to determine the required power supply of each first energy device and each second energy device in each time period within the collaborative management area. When generating the collaborative planning scheme, the power forecast sequence provides the upper limit of the available output of the first energy device in each time period, and the carbon emission quota sequence provides the carbon emission constraints in each time period. The two work together to ensure that the collaborative planning scheme prioritizes the use of renewable energy power generation while controlling carbon emissions within the allocated quota.

[0027] This embodiment establishes a complete data link through the above four steps, from historical electricity consumption data to carbon emission quota sequences, from weather data to power prediction sequences, and then to collaborative planning schemes. The generation of carbon emission quota sequences is linked to historical electricity consumption data, enabling the time-period allocation of carbon emission quotas to reflect the electricity consumption and power supply structure characteristics of the collaborative management area itself. The generation of power prediction sequences is linked to weather data, enabling the output prediction of the primary energy equipment to reflect the impact of weather conditions. The generation of collaborative planning schemes is constrained by both carbon emission quota sequences and power prediction sequences, enabling the final planning results to achieve refined carbon emission control while meeting electricity demand.

[0028] Example 2: Based on Example 1, this example describes the specific implementation of generating the carbon emission ratio matrix for each time period based on historical electricity consumption data in step S100.

[0029] First, extract the periodic electricity consumption data within each electricity consumption cycle from the historical electricity consumption data. The electricity consumption cycle is a set time length, generally one day. Then, extract the electricity consumption for each time period within each period. Periodic electricity consumption data refers to the electricity-related data collected within a complete electricity consumption cycle. For example, with an electricity consumption cycle of one day and a time period of one hour, one period of electricity consumption data includes 24 hours of time-period electricity consumption. Historical electricity consumption data can come from electricity metering devices installed on various energy equipment within the collaborative management area, or from historical operation records exported from the energy management system. The number of electricity consumption cycles covered by the historical electricity consumption data can be set according to actual needs, such as the past 30 days, the past 90 days, or the past quarter. The more cycles, the more stable the statistical features, but the computational workload also increases accordingly.

[0030] Next, the electricity consumption for each time period is normalized, and the normalized value is the proportion of electricity consumption for each time period to the total electricity consumption of an electricity cycle. This is then integrated into a sequence of electricity consumption for each time period within the electricity cycle, following a predefined order. The normalization process involves calculating the proportion of electricity consumption for each time period to the total electricity consumption of an electricity cycle. For example, if the electricity consumption for the first time period in an electricity cycle is 100 kWh, and the total electricity consumption for that cycle is 2000 kWh, then the normalized value for the first time period is 0.05. The predefined order is typically the chronological order of the time periods, i.e., the first time period, the second time period, and so on up to the 24th time period. Thus, each electricity cycle corresponds to a sequence of electricity consumption for each time period, and the elements in this sequence reflect the proportion of electricity consumption for each time period within the total electricity consumption of that electricity cycle.

[0031] Then, the average value corresponding to the elements at the same position in the electricity consumption sequence of each time period is calculated. This average value is used as the feature value of that position, and a periodic electricity consumption feature matrix is ​​constructed based on these feature values. Elements at the same position refer to elements with the same time period number in the electricity consumption sequence of different electricity consumption cycles. For example, 30 electricity consumption cycles correspond to 30 time period electricity consumption sequences, each sequence having 24 elements. The first element of each of the 30 sequences is added together and divided by 30 to obtain the average electricity consumption ratio corresponding to the first time period. This process is repeated to obtain 24 average electricity consumption ratios. These 24 average electricity consumption ratios are arranged in chronological order according to the time periods, forming the periodic electricity consumption feature matrix. In an example where the electricity consumption cycle is one day and the time period is 24 hours, the periodic electricity consumption feature matrix is ​​a 24-dimensional vector, with each dimension corresponding to the average electricity consumption ratio of a time period. The periodic electricity consumption feature matrix reflects the typical distribution characteristics of electricity consumption in each time period in a statistical sense within the collaborative management area and is one of the foundations for subsequently calculating the carbon emission ratio matrix.

[0032] Simultaneously or subsequently, while constructing the periodic electricity consumption feature matrix, the weather type corresponding to each periodic electricity consumption data, and the time-period power supply data corresponding to each time period within each periodic electricity consumption data are extracted. The time-period power supply data refers to the power supply of various types of energy equipment during the corresponding time period. Among them, the weather type is used to distinguish the differences in power supply structure under different weather conditions. For example, it can be divided into sunny, cloudy, overcast, rainy, snowy, etc., or it can be divided according to finer granularity, such as sunny with few clouds, sunny with many clouds, etc. The weather type can be obtained from historical meteorological records, or it can be classified according to parameters such as cloud cover and precipitation in the weather data. The time-period power supply data refers to the actual power output of various types of energy equipment during the corresponding time period. For example, during a certain time period, the photovoltaic power generation equipment supplies 50 kWh, the wind power generation equipment supplies 30 kWh, and the gas power generation equipment supplies 120 kWh.

[0033] Extract the power supply of each energy device from the power supply data for each time period; the energy devices include first energy devices and second energy devices; calculate the power supply ratio of each energy device corresponding to the power supply data for each time period based on the power supply of each energy device, and integrate the power supply ratios of each energy device into a time period power supply ratio sequence according to a set order; wherein, the power supply ratio refers to the proportion of the power supply of a certain energy device to the total power supply of all energy devices in a certain time period; for example, if the power supply of photovoltaic power generation equipment, wind power generation equipment and gas power generation equipment is 50 kWh, 30 kWh and 120 kWh respectively in a certain time period, and the total power supply is 200 kWh, then the corresponding power supply ratios of the three are 0.25, 0.15 and 0.60 respectively; the set order can be first energy device first and second energy device last, or arranged according to the device number, as long as it remains consistent in subsequent calculations; the time period power supply ratio sequence reflects the proportion of various energy devices in the power supply structure in a certain time period.

[0034] Obtain the power supply ratio sequence for each time period in the electricity consumption data of each cycle with the same weather type; calculate the average value of the elements at the same position in each time period power supply ratio sequence, use the average value as the feature value of that position, and construct the time period power supply ratio feature sequence for the corresponding time period of the weather type based on the feature value, and generate the power supply ratio feature sequence for each time period corresponding to the weather type in sequence, and integrate the power supply ratio feature sequences corresponding to each time period into the power supply feature matrix corresponding to the weather type; generate the power supply feature matrix corresponding to each weather type in sequence; wherein, the elements at the same position refer to the power supply ratio corresponding to the same energy device number under the same time period number; for example, in all electricity consumption cycles with the weather type of sunny, extract the time period power supply ratio sequence for the first time period. The first element in these sequences is the power supply ratio of photovoltaic power generation equipment. Take the average value of these elements to obtain the average power supply ratio of photovoltaic power generation equipment in the first time period under the sunny weather type. Power supply ratio characteristic values ​​are calculated sequentially for all energy devices in the first time period to obtain the power supply ratio characteristic sequence for the first time period under the sunny weather type. The above process is repeated for the second to the 24th time periods, and the power supply ratio characteristic sequences of the 24 time periods are integrated to obtain the power supply characteristic matrix corresponding to the sunny weather type. In an example where the electricity consumption cycle is one day, the time period is 24 hours, and the number of energy devices is N, the power supply characteristic matrix is ​​a 24×N matrix, where each row corresponds to a time period and each column corresponds to an energy device. The same operation is performed sequentially for cloudy, overcast, and rainy weather types to obtain the power supply characteristic matrix corresponding to each weather type. The power supply characteristic matrix reflects the typical characteristics of the power supply structure in each time period under different weather types. Since the output of the first energy device is greatly affected by the weather, there are often significant differences in the power supply structure under different weather types. Therefore, constructing power supply characteristic matrices according to weather types can more accurately characterize these differences.

[0035] The carbon emission factors corresponding to each energy device are obtained, and these carbon emission factors are integrated into a carbon emission factor feature matrix according to a set order. The carbon emission factor refers to the carbon emissions generated per unit of electricity output by a particular energy device, expressed in kilograms of carbon dioxide per kilowatt-hour. The first energy device, as a renewable energy power generation device, typically has a low carbon emission factor; for example, the carbon emission factors of photovoltaic and wind power generation devices can be 0 or close to 0. The second energy device, as a conventional energy power generation device, typically has a high carbon emission factor; for example, the carbon emission factor of gas-fired power generation devices can be around 0.4 kilograms of carbon dioxide per kilowatt-hour, and that of coal-fired power generation devices can be around 0.8 kilograms of carbon dioxide per kilowatt-hour. The specific value of the carbon emission factor can be determined based on factors such as equipment type, fuel type, and equipment operating efficiency, or by referring to relevant standards or measured data. The order of elements in the carbon emission factor feature matrix is ​​consistent with the column order of energy devices in the power supply feature matrix. In the example where the number of energy devices is N, the carbon emission factor feature matrix is ​​an N-dimensional vector.

[0036] After completing the construction of the above three feature matrices, a carbon emission ratio matrix is ​​generated based on the periodic electricity consumption feature matrix, the power supply feature matrix, and the carbon emission factor feature matrix. The carbon emission ratio matrix contains the carbon emission ratio corresponding to each time period. Specifically, the carbon emission factor feature matrix and the power supply feature matrix are obtained. Based on each element in these matrices, the comprehensive carbon emission factor matrix for each time period is calculated. Each element in the comprehensive carbon emission factor matrix corresponds to a time period, representing the weighted average carbon emission level per unit of electricity generated by all energy devices within that time period. The calculation method is as follows: for a given time period, the power supply ratio of each energy device in the power supply feature matrix corresponding to that time period is multiplied by the carbon emission factor of the corresponding energy device in the carbon emission factor feature matrix, and then summed. For example, if the power supply ratios of photovoltaic power generation equipment, wind power generation equipment, and gas power generation equipment in a certain time period are 0.25, 0.15, and 0.60, respectively, corresponding to carbon emission factors of 0, 0, and 0.4 kg CO2 per kilowatt-hour, then the comprehensive carbon emission factor for that time period is 0.25×0 + 0.15×0 + 0.60×0.4 = 0.24 kg CO2 per kilowatt-hour. The comprehensive carbon emission factor matrix reflects the impact of differences in power supply structure in each time period on the carbon emission level per unit of electricity generated.

[0037] Specifically, obtain the carbon emission factor feature matrix. and power supply characteristic matrix ;in, The carbon emission factor feature matrix is ​​numbered as follows The carbon emission factor corresponding to energy equipment; The first in the power supply characteristic matrix The time period corresponds to the number. The power supply ratio corresponding to energy equipment; the comprehensive carbon emission factor corresponding to each time period under each weather type is calculated using the formula: ; in, For the first The corresponding comprehensive carbon emission factor for each time period , The number of energy devices; and the various integrated carbon emission factors. Integrating into a comprehensive carbon emission factor matrix ; A periodic electricity consumption characteristic matrix is ​​obtained, and a carbon emission intensity matrix is ​​calculated based on the periodic electricity consumption characteristic matrix and the comprehensive carbon emission factor matrix. Each element in the carbon emission intensity matrix corresponds to a time period, representing the relative amount of carbon emissions generated by electricity consumption during that time period under the influence of the comprehensive carbon emission factor. The calculation method is to multiply the average electricity consumption ratio corresponding to a certain time period in the periodic electricity consumption characteristic matrix by the comprehensive carbon emission factor corresponding to that time period. For example, if the average electricity consumption ratio is 0.05 and the comprehensive carbon emission factor is 0.24 kg of carbon dioxide per kilowatt-hour, then the carbon emission intensity of that time period is 0.05 × 0.24 = 0.012. The carbon emission intensity matrix reflects the impact of electricity consumption distribution and power supply structure on carbon emissions. In periods with high electricity consumption ratios and high comprehensive carbon emission factors, the carbon emission intensity is correspondingly larger.

[0038] The carbon emission intensity matrix is ​​obtained by normalizing each carbon emission intensity in the carbon emission intensity matrix. Specifically, obtain the periodic electricity consumption feature matrix. ;in, For the first The electricity consumption ratio corresponding to the time period; the carbon emission intensity matrix calculated based on the periodic electricity consumption characteristic matrix and the comprehensive carbon emission factor matrix includes: ; in, For carbon emission intensity matrix, Carbon emission intensity matrix The corresponding number in the middle Carbon emission intensity over a given period; The carbon emission proportion matrix is ​​obtained by normalizing each carbon emission intensity in the carbon emission intensity matrix, including: ; in, A carbon emission ratio matrix; Carbon emission ratio matrix The corresponding number in the middle Carbon emission ratio for a given period; , This refers to the number of time periods within an electricity consumption cycle.

[0039] It should be noted that the carbon emission ratio matrix is ​​related to weather type. Since the power supply characteristic matrix is ​​constructed separately according to weather type, the carbon emission ratio matrix calculated based on the power supply characteristic matrix corresponding to a certain weather type also corresponds to the same weather type. When generating the carbon emission credit sequence in the future, the corresponding carbon emission ratio matrix can be selected according to the weather type of the electricity consumption cycle to be predicted, so that the time period allocation of carbon emission credits matches the weather conditions.

[0040] This embodiment constructs a periodic electricity consumption characteristic matrix, a power supply characteristic matrix under different weather types, and a carbon emission factor characteristic matrix, respectively. It integrates the electricity consumption distribution characteristics, the power supply structure characteristics under different weather types, and the carbon emission factors of each energy device to generate a carbon emission ratio matrix that reflects the proportion of carbon emissions in each time period. Since the generation of the carbon emission ratio matrix considers both the electricity consumption structure and the power supply structure and distinguishes them according to weather type, it can more accurately reflect the typical distribution pattern of carbon emissions in the collaborative management area under different weather conditions in each time period, providing a reliable data foundation for the subsequent refined allocation of carbon emission quota sequences.

[0041] Example 3: Based on Example 2, this example describes the specific implementation of generating a carbon emission quota sequence based on the carbon emission ratio matrix and the remaining carbon emission quota in step S200.

[0042] Obtain the remaining carbon emission allowance and the number of electricity cycles corresponding to it; calculate the cycle carbon emission allowance for each electricity cycle; it is understood that the remaining carbon emission allowance is updated after each electricity cycle; the remaining carbon emission allowance is the total amount of unused carbon emission allowances in the collaborative management area within the set planning period, which can be one month, one quarter, or one year, with the specific duration determined according to the carbon emission allowance management cycle; the number of electricity cycles corresponding to the remaining carbon emission allowance refers to the number of remaining electricity cycles from the current moment until the end of the planning period; the cycle carbon emission allowance is obtained by dividing the remaining carbon emission allowance by the number of remaining electricity cycles, representing the carbon emission allowance obtainable per electricity cycle under the average allocation method; for example... For example, assuming the remaining carbon emission allowance is 100 tons and the remaining number of electricity cycles is 10, then the carbon emission allowance for each electricity cycle is 100 tons divided by 10, which is 10 tons. It should be noted that the remaining carbon emission allowance is updated after each electricity cycle. That is, when an electricity cycle ends, the actual carbon emissions generated during that cycle are counted and deducted from the remaining carbon emission allowance. At the same time, the number of remaining electricity cycles is reduced by one. The carbon emission allowance for the next electricity cycle is recalculated based on the updated remaining carbon emission allowance and the number of remaining electricity cycles. Through this rolling update mechanism, the periodic carbon emission allowance can reflect the actual consumption of carbon emission quotas and avoid the problem of inflated carbon emission allowances in subsequent electricity cycles due to excessive emissions in the early stages.

[0043] The process involves obtaining the weather type corresponding to the predicted electricity consumption cycle in the collaborative management area, obtaining the carbon emission ratio matrix corresponding to the weather type, calculating the carbon emission allowance for each period and the carbon emission ratio for each time period in the carbon emission ratio matrix, and integrating the carbon emission allowances for each time period into a carbon emission allowance sequence according to a set order. The predicted electricity consumption cycle refers to the electricity consumption cycle for which collaborative planning will be carried out, such as the next electricity consumption cycle that will begin after the current cycle ends. Weather types can be obtained from weather forecast data or categorized based on parameters such as cloud cover, precipitation, and solar irradiance from meteorological monitoring data. Since the carbon emission ratio matrix in Example 2 is constructed separately according to weather type, when generating the carbon emission allowance sequence, it is necessary to first determine the weather type corresponding to the predicted electricity consumption cycle and then obtain the carbon emission ratio matrix corresponding to that weather type, so that the time period allocation of the carbon emission allowance matches the weather conditions of the predicted electricity consumption cycle.

[0044] Specifically, for each time period within the predicted electricity consumption cycle, the carbon emission ratio corresponding to that time period in the carbon emission ratio matrix is ​​multiplied by the cycle carbon emission allowance to obtain the corresponding time period carbon emission allowance. For example, assuming the weather type corresponding to the predicted electricity consumption cycle is sunny, the carbon emission ratios for time periods 1 to 24 in the carbon emission ratio matrix for sunny days are 0.02, 0.01, 0.01, 0.01, 0.02, 0.04, 0.06, 0.08, 0.07, 0.05, 0.04, 0.04, 0.05, 0.06, 0.07, 0 The carbon emission allowances are calculated as follows: 0.08, 0.08, 0.08, 0.05, 0.03, 0.02, 0.01, 0.01, 0.01. The periodic carbon emission allowance is 10 tons. Therefore, the carbon emission allowance for the first period is 10 tons multiplied by 0.02, which is 0.2 tons. The carbon emission allowance for the second period is 10 tons multiplied by 0.01, which is 0.1 tons, and so on, resulting in 24 periods. These period carbon emission allowances are arranged chronologically, i.e., period 1, period 2, up to period 24, forming a carbon emission allowance sequence. The sum of the carbon emission allowances for all periods in the sequence equals the periodic carbon emission allowance, which is 10 tons.

[0045] Each element in the carbon emission quota sequence represents the theoretically permissible upper limit of carbon emissions for the collaborative management area within the corresponding time period. Since the carbon emission ratio matrix reflects both electricity consumption distribution characteristics and power supply structure characteristics, the time period allocation of the carbon emission quota sequence can be coordinated with the electricity consumption and power supply patterns of the collaborative management area itself. For example, in time periods with high electricity consumption and a high proportion of power supply from secondary energy equipment, the carbon emission ratio is correspondingly higher, and the carbon emission quota allocated to that time period is also larger. Conversely, in time periods with low electricity consumption and a high proportion of power supply from primary energy equipment, the carbon emission ratio is correspondingly lower, and the carbon emission quota allocated to that time period is also smaller. This allocation method avoids the constraint mismatch problem caused by evenly distributing carbon emission quotas across different time periods, making the carbon emission constraints more closely aligned with actual operating conditions in the time dimension.

[0046] When generating collaborative planning schemes, the carbon emission credit sequence will be used as a time-period carbon emission constraint. If the carbon emissions generated by each energy device operating at the planned power during a certain time period do not exceed the carbon emission credit for that time period, the planning scheme meets the carbon emission constraint for that time period. Otherwise, it is necessary to adjust the power allocation of each energy device or adjust the power allocation scheme for other time periods. Since the carbon emission credit sequence is related to weather type, when the weather type of the electricity consumption cycle to be predicted changes, the time period distribution of the carbon emission credit sequence will also be adjusted accordingly, so that the carbon emission constraint can adapt to the differences in power supply structure under different weather conditions.

[0047] Example 4: Based on Example 1, this example describes the specific implementation of step S300, which involves estimating the production capacity of the first energy equipment based on weather data to obtain the power estimation sequence corresponding to each first energy equipment.

[0048] Extract several time-period weather parameters from the weather data corresponding to each time period in the collaborative management area. The time-period weather parameters refer to the values ​​of weather elements related to the power generation capacity of the primary energy equipment during the corresponding time period. For photovoltaic power generation equipment, the time-period weather parameters may include solar irradiance, temperature, cloud cover, relative humidity, etc. For wind power generation equipment, the time-period weather parameters may include wind speed, wind direction, air pressure, etc. When multiple types of primary energy equipment are configured simultaneously in the collaborative management area, the corresponding weather parameters can be extracted separately for equipment with different power generation mechanisms. The time periods in the weather data generally include each time period within the planned electricity consumption cycle.

[0049] Obtain weather parameters for several time periods corresponding to each first energy device, input the weather parameters for each time period into the power generation prediction model corresponding to the first energy device, obtain the power prediction value of the first energy device in the corresponding time period, integrate the power prediction values ​​according to the order of their corresponding time periods into a success rate prediction sequence; and generate the power prediction sequence corresponding to each first energy device in sequence.

[0050] Among them, the power generation prediction model is used to output the power prediction value of the corresponding first energy device in the corresponding time period based on the input time period weather parameters; the power prediction value represents the estimated power output of the first energy device under the corresponding time period weather conditions; different power generation prediction models are corresponding to first energy devices with different power generation mechanisms; the following takes photovoltaic power generation equipment and wind power generation equipment as examples to give two optional power generation prediction models.

[0051] For photovoltaic (PV) power generation equipment, the estimated power output is mainly related to solar irradiance and PV module temperature. Higher solar irradiance means more solar radiation received by the PV equipment, resulting in higher output power. Conversely, the closer the PV module temperature is to the temperature under standard testing conditions, the higher the conversion efficiency and output power. One possible power estimation model for PV power generation equipment is: ; in, This is the estimated power output of the photovoltaic power generation equipment in time period t. This refers to the rated power of photovoltaic power generation equipment under standard test conditions. Let be the solar irradiance during time period t. The solar irradiance is the value under standard test conditions, for example, 1000 watts per square meter. The power temperature coefficient of photovoltaic power generation equipment. Let be the temperature of the photovoltaic module in time period t. The photovoltaic module temperature is the temperature under standard test conditions, for example, 25 degrees Celsius. The photovoltaic module temperature can be estimated from the ambient temperature and solar irradiance, for example, based on the ambient temperature and superimposed with the temperature rise caused by solar irradiance.

[0052] For wind power generation equipment, the power prediction value is mainly related to wind speed. When the wind speed is lower than the cut-in wind speed, the wind power generation equipment is insufficient to start; when the wind speed is between the cut-in wind speed and the rated wind speed, the output power increases with the increase of wind speed; when the wind speed is between the rated wind speed and the cut-out wind speed, the output power remains at the rated power; when the wind speed reaches or exceeds the cut-out wind speed, the wind power generation equipment is cut off and shut down to ensure operational safety. One optional power prediction model for wind power generation equipment is determined based on its power curve. When the average wind speed in time period t is between the cut-in wind speed and the rated wind speed, the wind power generation equipment has not yet reached its rated output, and the power prediction value increases with the increase of wind speed. At this time, the power prediction value is calculated according to the following formula: ; in, This is the estimated power output of the wind power generation equipment in time period t. Let be the average wind speed during time period t. The cut-in wind speed for wind power generation equipment. The rated wind speed for wind power generation equipment. The cut-off wind speed for wind power generation equipment. This represents the rated power of the wind power generation equipment. When the average wind speed is lower than the cut-in wind speed, the estimated power is 0; when the average wind speed is between the cut-in wind speed and the rated wind speed, the estimated power is calculated according to the above formula; when the average wind speed is between the rated wind speed and the cut-out wind speed, the estimated power is equal to the rated power; when the average wind speed reaches or exceeds the cut-out wind speed, the estimated power is 0.

[0053] It should be noted that the photovoltaic model based on solar irradiance and the wind turbine model based on power curves mentioned above are only optional implementations of the power generation prediction model. The power generation prediction model can also use a machine learning model trained based on historical operating data and historical weather data, such as a neural network model, support vector regression model, or random forest model, which takes weather parameters of each time period as input features and outputs the power prediction value of the corresponding time period. Alternatively, a combination of physical model and statistical correction term can be used. The power generation prediction model can be a pre-built and stored model, or it can be updated before each planning execution as needed. This embodiment does not limit which power generation prediction model to use.

[0054] After obtaining the power estimates for each time period, the power estimates are arranged in chronological order according to their corresponding time periods and integrated into a power estimate sequence corresponding to the first energy device. Then, the above process is performed on each first energy device in turn to obtain the power estimate sequence corresponding to each first energy device.

[0055] This embodiment extracts time-specific weather parameters related to the generation mechanism of each primary energy device and uses the corresponding power generation prediction model for each primary energy device to convert these weather parameters into power prediction values, thus obtaining the power prediction sequence for each primary energy device in each time period. Since the power generation capacity of photovoltaic and wind power generation devices is mainly affected by factors such as solar irradiance and wind speed, power prediction based on the corresponding weather parameters ensures that the power prediction values ​​reflect the available output level of the devices under the weather conditions of the corresponding time period. This provides a data foundation for determining the upper limit of the power supply required by the primary energy devices in subsequent collaborative planning.

[0056] Example 5: Based on Example 1, this example describes the specific implementation of generating a collaborative planning scheme based on the power prediction sequence and carbon emission quota sequence corresponding to each first energy device in step S400.

[0057] Obtain the electricity demand sequence; where the electricity demand sequence is a sequence formed by arranging the electricity demand corresponding to each time period within the predicted electricity consumption cycle in the collaborative management area in chronological order; the electricity demand sequence can be obtained in various ways, such as predicting based on historical electricity consumption data of the collaborative management area combined with electricity growth trends, estimating based on prior information such as production plans and equipment operation arrangements, or being directly provided by the energy management system; each element in the electricity demand sequence corresponds to a time period, representing the total demand of all electricity loads in the collaborative management area within that time period; the electricity demand sequence is one of the basic data for supply and demand balance calculations when generating available collaborative solutions.

[0058] Based on the electricity demand sequence, the power estimation sequence corresponding to each primary energy device, and the carbon emission quota sequence, available collaborative schemes for the primary and secondary energy devices are generated. An available collaborative scheme refers to a candidate planning scheme that simultaneously satisfies both supply-demand balance conditions and carbon emission quota constraints. Specifically, when generating available collaborative schemes, it is necessary to ensure that, on the one hand, the sum of the power demand of all primary and secondary energy devices in each time period can meet the electricity demand of that time period; on the other hand, it is necessary to ensure that the carbon emissions generated by each energy device operating at its planned power in each time period do not exceed the carbon emission quota for that time period. The power estimation sequence provides an upper limit reference for the power demand of the primary energy devices in each time period, meaning that the power demand of the primary energy devices cannot exceed the power estimation value for that corresponding time period. When the power estimation value of the primary energy devices is insufficient to meet the electricity demand, the shortfall is supplemented by the secondary energy devices. Since there can be multiple power allocation combinations between the primary and secondary energy devices, multiple available collaborative schemes can usually be obtained under the premise of satisfying the above dual constraints. The specific generation method of available collaborative schemes, including the specific expression of the supply-demand balance constraints and carbon emission quota constraints, will be explained in subsequent embodiments.

[0059] Weather data from the collaborative management area and other areas within a defined range are acquired, and a weather fluctuation index corresponding to each time period is generated based on the weather data. The defined range refers to a certain geographical area extending outward from the collaborative management area, such as an area extending tens to hundreds of kilometers outward from the boundary of the collaborative management area. The specific size of the range can be determined based on factors such as the spatial scale of the weather system, terrain conditions, and the availability of weather forecast data. Other areas refer to areas outside the collaborative management area within the defined range; weather data from these areas is used to compare with the weather data of the collaborative management area to reflect spatial differences in weather distribution. The weather fluctuation index is used to assess the impact of weather fluctuations on renewable energy output. The impact of weather fluctuations on power generation is significant. Since the power generation capacity of the first energy unit is greatly affected by weather conditions, when there are significant differences between the weather in the collaborative management area and the surrounding areas, or when the weather in the collaborative management area itself changes rapidly over time, the actual output of the first energy unit may deviate from the estimated value in the power prediction sequence. In this case, the second energy unit needs to urgently supplement its power to maintain supply and demand balance, and the resulting additional carbon emissions will affect the achievement of low-carbon planning goals. The weather fluctuation index quantifies the degree of weather variation in spatial and temporal dimensions, providing a basis for selecting a scheme with stronger adaptability to weather fluctuations from multiple available collaborative schemes. The specific generation method of the weather fluctuation index will be explained in subsequent embodiments.

[0060] Based on the weather fluctuation index, a final collaborative planning scheme is selected from various available collaborative schemes. This final collaborative planning scheme is chosen from multiple available schemes, ensuring good adaptability to weather fluctuations while meeting electricity demand and carbon emission quota constraints. Specifically, the selection of the final collaborative planning scheme aims to minimize overall carbon emissions. Overall carbon emissions include not only the basic carbon emissions generated by each energy device operating at its planned power, but also the penalty carbon emissions generated by the emergency power supplementation of the second energy device when the actual output of the first energy device is lower than the estimated value due to weather fluctuations, and the carbon emissions corresponding to the additional equipment consumption during the power state transition of the second energy device. By incorporating the weather fluctuation index into the calculation of overall carbon emissions, the final collaborative planning scheme can maintain a low carbon emission level even under weather fluctuation conditions. The specific selection method for the final collaborative planning scheme will be explained in subsequent embodiments.

[0061] This embodiment obtains the electricity demand sequence, generates available collaborative solutions under the dual constraints of supply and demand balance and carbon emission quotas, and then selects the final collaborative planning scheme based on the weather fluctuation index with the goal of minimizing the overall carbon emissions. This establishes a complete decision-making link from the power forecast sequence and carbon emission quota sequence to the final planning scheme. Since the generation of available collaborative solutions takes into account electricity demand, the upper limit of the output of the first energy equipment, and the carbon emission quota for each time period, and the selection of the final collaborative planning scheme further considers the additional carbon emissions that may be caused by weather fluctuations, the planning result can control carbon emissions within the allocated quota range while meeting electricity demand, and maintain a low carbon emission level under weather fluctuation conditions.

[0062] Example 6: Based on Example 5, this example describes the specific implementation of generating available collaborative schemes for the first and second energy devices based on the electricity demand sequence, the power estimation sequence corresponding to each first energy device, and the carbon emission quota sequence.

[0063] Supply-demand balance constraints are constructed based on the electricity demand sequence and the power forecast sequence corresponding to each primary energy device. These constraints ensure that the power supply of all energy devices in the collaborative management area can meet the electricity demand during each time period, while also ensuring that the power demand of the primary energy devices does not exceed the power forecast value for that time period. The supply-demand balance constraints are as follows: ; ; in, For the number The first energy device in the The required power supply for the corresponding time period; For the number The second energy device in the The required power supply for the corresponding time period; For the number The first energy device corresponds to the predicted power generation sequence in the first energy device Power estimates for the corresponding time period; The first in the electricity demand sequence Electricity demand corresponding to the time period; This is the number corresponding to the first energy device, and , The number of primary energy equipment; This is the number corresponding to the second energy device, and , The number of secondary energy facilities; ; Let be the length of each time period; specifically, the first formula represents the length of the time period in the first time period. Within a given time period, the sum of the power demand of all primary energy devices and the power demand of all secondary energy devices multiplied by the time period length equals the total electricity demand for that period. The second formula represents the electricity demand for each primary energy device during the period. The power demand for a given period cannot exceed the estimated power output of the first energy device for that period. Since the first energy device is a renewable energy power generation device, its actual output is limited by weather conditions. The estimated power output represents the maximum power that the device can output under the corresponding weather conditions. Therefore, the power demand for the first energy device is capped at the estimated power output. When the estimated power output of the first energy device is insufficient to meet the electricity demand, the shortfall is supplemented by the second energy device. The power demand for the second energy device is determined by the difference between the electricity demand and the power demand for the first energy device using the first formula.

[0064] By applying supply and demand balance constraints, several combinations of estimated power generation from the first energy source and the required power supply from the second energy source are obtained. These combinations are denoted as undetermined coordination schemes. Since there can be multiple power allocation combinations between the first and second energy sources, multiple undetermined coordination schemes can typically be obtained under the premise of satisfying the supply and demand balance constraints. Each undetermined coordination scheme includes the required power supply for each first energy source and each second energy source in each time period. The number of undetermined coordination schemes depends on the number of first energy sources, the number of second energy sources, and the difference between the electricity demand and the estimated power supply in each time period.

[0065] Carbon emission quota constraints are constructed based on the carbon emission quota sequence; these constraints are used to select schemes that meet the time-period carbon emission limits from the undetermined collaborative schemes. The carbon emission quota constraints are as follows: ; in, No. Among the pending collaborative solutions, the one numbered is... The first energy device in the The required power supply for the corresponding time period For the number The carbon emission factor corresponding to the first energy equipment; No. Among the pending collaborative solutions, the one numbered is... The second energy device in the The required power supply for the corresponding time period For the number The carbon emission factor corresponding to the second energy equipment; The first in the carbon emission credit series The carbon emission allowance corresponding to the time period; specifically, the carbon emission allowance constraint is expressed in the first... During the time period, the carbon emissions obtained by multiplying the demand power of all first energy devices by the time period length and then by the corresponding carbon emission factor, plus the carbon emissions obtained by multiplying the demand power of all second energy devices by the time period length and then by the corresponding carbon emission factor, shall not exceed the carbon emission quota corresponding to that time period. The carbon emission factor follows the definition in Example 2, that is, the carbon emissions generated by a certain energy device for each unit of electricity output. The carbon emission factor of the first energy device is usually lower, and the carbon emission factor of the second energy device is usually higher. Therefore, the carbon emission quota constraint actually imposes a stricter restriction on the power supply of the second energy device.

[0066] Several undetermined collaborative schemes that meet the carbon emission quota constraints are denoted as available collaborative schemes.

[0067] Available collaborative solutions are a subset of pending collaborative solutions, namely, solutions that simultaneously satisfy both supply and demand balance constraints and carbon emission quota constraints. If the carbon emissions generated by a pending collaborative solution exceed the corresponding carbon emission quota for any given period, that proposed collaborative solution is eliminated. After screening based on carbon emission quota constraints, the remaining pending collaborative solutions are the available collaborative solutions, used for subsequent selection of the final collaborative planning scheme based on the weather fluctuation index.

[0068] To more clearly illustrate the calculation process of supply and demand balance constraints and carbon emission quota constraints, a specific example is provided below. Assume the collaborative management area is equipped with two primary energy devices: one photovoltaic (PV) power generation unit and one wind power generation unit, and one secondary energy device: one gas-fired power generation unit. Taking a time period as an example, assume the period length is 1 hour, the electricity demand corresponding to this period in the electricity demand sequence is 200 kWh, the estimated power output of the PV power generation unit in this period is 60 kW, the estimated power output of the wind power generation unit in this period is 40 kW, the carbon emission factors of both the PV and wind power generation units are 0, the carbon emission factor of the gas-fired power generation unit is 0.4 kg CO2 per kWh, and the carbon emission quota corresponding to this period is 30 kg CO2.

[0069] Under supply and demand balance constraints, the required power output of photovoltaic (PV) power generation equipment should not exceed 60 kW, and the required power output of wind power generation equipment should not exceed 40 kW. Assuming both PV and wind power generation equipment operate at full capacity as projected, their combined power output would be 100 kWh. The remaining 100 kWh of electricity demand would be supplemented by gas-fired power generation equipment, which would also require 100 kW of power. In this case, the carbon emissions generated during this period would be the 100 kWh of power output from the gas-fired power generation equipment multiplied by a carbon emission factor of 0.4 kg CO2 per kWh, which equals 40 kg of CO2. Since 40 kg of CO2 exceeds the corresponding carbon emission allowance of 30 kg for this period, this combination does not meet the carbon emission allowance constraint and cannot be considered a usable synergistic solution.

[0070] If the power allocation is adjusted, for example, setting the required power supply for photovoltaic power generation equipment to 60 kW and the required power supply for wind power generation equipment to 30 kW, then the total power supply for both is 90 kWh, and the required power supply for gas-fired power generation equipment is 110 kW. The carbon emissions generated during this period would be 110 kWh multiplied by 0.4 kg of CO2 per kWh, which is 44 kg of CO2, still not meeting the carbon emission quota constraints. If further adjustments are made, setting the required power supply for photovoltaic power generation equipment to 50 kW and the required power supply for wind power generation equipment to 40 kW, the total power supply for both is still 90 kWh, and the required power supply for gas-fired power generation equipment is still 110 kW, with carbon emissions remaining at 44 kg of CO2. Therefore, in this example, since the carbon emission factor of the first energy device is 0, the carbon emissions are determined solely by the power supply from the gas-fired power generation device. The power supply from the gas-fired power generation device is determined by the difference between the electricity demand and the total power supply from the first energy device. Thus, carbon emissions can only fall below the carbon emission allowance when the total power supply from the first energy device reaches a certain level. For example, if both photovoltaic and wind power generation devices operate at full capacity as projected, resulting in a total power supply of 100 kWh, and the gas-fired power generation device also supplies 100 kWh, the carbon emissions would be 40 kg of carbon dioxide, still exceeding the allowance of 30 kg of carbon dioxide. In this case, if the carbon emission allowance for that period cannot be met, the power allocation scheme for other periods needs to be adjusted to ensure that the total carbon emissions over the entire electricity consumption cycle meet the constraints.

[0071] It should be noted that the power demand of each secondary energy device in each pending collaborative scheme should also meet the constraints of the corresponding device, such as the maximum upper limit constraint: ; in, for The maximum output limit corresponding to the second energy equipment; Slope constraints ; in, for The maximum ramp limit corresponding to the second energy equipment; In another embodiment, one method for generating a carbon emission allowance sequence includes: obtaining the periodic carbon emission allowance corresponding to the current electricity consumption cycle, and the carbon emissions already generated for each elapsed time period; calculating the periodic carbon emission allowance minus the carbon emissions already generated for each time period to obtain the remaining carbon emission allowance; obtaining the time period carbon emission ratios corresponding to each future time period within the current electricity consumption cycle in the carbon emission ratio matrix; normalizing these carbon emission ratios to obtain new phased time period carbon emission ratios; calculating the product of each phased time period carbon emission ratio and the remaining carbon emission allowance to obtain the phased time period carbon emission allowance corresponding to each time period; and integrating the phased time period carbon emission allowances corresponding to each time period into a carbon emission allowance sequence.

[0072] Example 7: Based on Example 5, this example describes the specific implementation method of generating weather fluctuation indices for each time period based on weather data.

[0073] Acquire weather data for each region within a defined range; each region within the defined range refers to the collection of regions formed after the range is divided into several sub-regions, and the collaborative management region itself can also participate in the calculation as one of the regions; weather data for each region can be obtained through ground meteorological observation stations, weather monitoring towers, meteorological satellite remote sensing data, or numerical weather prediction products, etc.; the method of region division can be determined according to actual needs, for example, it can be divided according to latitude and longitude grids, or according to administrative divisions or topographic features; the finer the region division, the more refined the characterization of spatial differences by the weather fluctuation index, but the data acquisition and calculation workload also increase accordingly.

[0074] Extract several time-period weather parameters corresponding to each time period from the weather data; time-period weather parameters refer to the values ​​of weather elements related to the power generation capacity of the first energy equipment in the corresponding time period; for example, for photovoltaic power generation equipment, time-period weather parameters may include solar irradiance, temperature, cloud cover, relative humidity, etc.; after normalizing the several time-period weather parameters corresponding to each time period, integrate them into the time-period weather feature vector corresponding to the region; the purpose of normalization is to eliminate the influence of differences in the dimensions and numerical ranges of different weather parameters on subsequent calculations; Substitute the weather feature vectors of the collaborative management area and the corresponding time period of each area into the set weather fluctuation index generation function to obtain the weather fluctuation index corresponding to each time period. The weather fluctuation index generation function is used to comprehensively quantify the degree of change in weather in the collaborative management area in both spatial and temporal dimensions. One expression of the weather fluctuation index generation function includes: ; in, For the first Weather fluctuation index corresponding to the time period; For collaborative management of the region The weather feature vector corresponding to the time period; Number The region The weather feature vector corresponding to the time period. Assign corresponding numbers to other areas within the collaborative management area, and , Set the total number of other areas within the collaborative management area; For collaborative management of the region The weather feature vector corresponding to the time period. Number the time period variable, and ; These are spatially discrete weighting coefficients. This is the time inertia weighting coefficient, and The larger the spatial dispersion weighting coefficient, the more the weather fluctuation index reflects the spatial differences in weather between the collaborative management area and surrounding areas; the larger the temporal inertia weighting coefficient, the more the weather fluctuation index reflects the degree of weather change within the collaborative management area itself over time; the spatial dispersion weighting coefficient... and time inertia weighting coefficient The specific values ​​are set by experts; in this embodiment... ; Specifically, the weather fluctuation index generation function consists of a weighted sum of two terms; the first term is the spatial dispersion factor, i.e. This reflects the degree of weather difference between the collaborative management area and the surrounding areas. When the weather characteristic vectors of the collaborative management area and the surrounding areas differ significantly, the spatial dispersion factor takes a large value, indicating that the collaborative management area is in an environment with uneven spatial weather distribution. The actual output of the first energy equipment may deviate from the estimated value in the power prediction sequence due to local weather changes. The second term is the time inertia factor, i.e. This reflects the degree of weather change in the collaborative management area over time. When the weather feature vector of the collaborative management area changes significantly between adjacent time periods, the time inertia factor takes a large value, indicating that the time inertia of the weather in the collaborative management area is weak, the weather condition is unstable, and the output of the primary energy equipment may fluctuate rapidly in the time dimension.

[0075] This embodiment constructs a time-period weather feature vector and substitutes the weather feature vectors of the collaborative management area and other areas within the set range into the weather fluctuation index generation function to quantify the degree of weather fluctuation from two dimensions: spatial discreteness and temporal inertia. Since the weather fluctuation index considers both the spatial differences in weather between the collaborative management area and surrounding areas, as well as the temporal changes in the weather within the collaborative management area itself, it can comprehensively reflect the potential impact of weather fluctuations on the output of the primary energy equipment. When selecting the final collaborative planning scheme based on the weather fluctuation index, periods with larger weather fluctuation indices indicate a higher risk of the actual output of the primary energy equipment deviating from the estimated power, a greater likelihood that the secondary energy equipment will need to urgently supplement its power, and a higher amount of additional carbon emissions. Therefore, these periods should be given a higher penalty weight in the scheme evaluation.

[0076] Example 8: Based on Examples 5 to 7, this example describes the specific implementation method of selecting the final collaborative planning scheme from various available collaborative schemes based on the weather fluctuation index.

[0077] Obtain the weather fluctuation index corresponding to each time period, and the required power supply for each first energy device and second energy device in each available collaborative scheme for each time period; wherein, the weather fluctuation index adopts the result generated in Example 7, and is used to characterize the degree of weather fluctuation in the collaborative management area in the spatial and temporal dimensions; each available collaborative scheme adopts the result obtained in Example 6, and each available collaborative scheme includes the required power supply for each first energy device and each second energy device in each time period; the required power supply refers to the output power planned to be undertaken by the corresponding energy device in the corresponding time period, the required power supply of the first energy device does not exceed the power estimate of its corresponding time period, and the required power supply of the second energy device is used to supplement the difference between the output of the first energy device and the power demand.

[0078] A collaborative planning objective function is constructed by using the weather fluctuation index corresponding to each time period, the required power supply of the first energy device, and the second energy device; the collaborative planning objective function is: ; in, For the number The combined carbon emissions corresponding to the available collaborative solutions; For the number The basic carbon emissions corresponding to the available collaborative solutions, that is, the carbon emissions generated by the normal execution of the available collaborative solutions; For the number The first penalty carbon emissions corresponding to the available synergistic solutions, The second penalty carbon emission is calculated as follows: Specifically, the comprehensive carbon emission is composed of three components. The basic carbon emission reflects the total carbon emissions generated by each energy device operating at its planned power under normal conditions. The first penalty carbon emission reflects the additional carbon emissions generated when the actual output of the first energy device is lower than the estimated power due to weather fluctuations, requiring the second energy device to urgently supplement its power. The second penalty carbon emission reflects the additional carbon emissions generated by the second energy device during power state transitions due to equipment start-up, shutdown, and rapid load adjustments. By adding these three carbon emission components, the collaborative planning objective function can comprehensively reflect the actual carbon emission level of the available collaborative scheme under weather fluctuation conditions.

[0079] One method for calculating basic carbon emissions includes: ; in, Let k be the base carbon emissions for the available synergistic scheme. The number of time periods within an electricity consumption cycle. Number the time period variable, and , The number of primary energy equipment, This is the number corresponding to the first energy device, and , For the kth available collaborative solution, the one numbered is... The required power supply of the first energy device in time period t. The time period length corresponds to each time period. For the number The carbon emission factor corresponding to the first energy equipment, For the number of second energy devices, This is the number corresponding to the second energy device, and , For the kth available collaborative solution, the one numbered is... The required power supply of the second energy device in time period t, For the number The carbon emission factor corresponding to the second energy equipment.

[0080] Specifically, the basic carbon emissions are calculated as follows: For each time period, the required power supply of each primary energy device is multiplied by the time period length and then by the corresponding carbon emission factor to obtain the carbon emissions of that primary energy device in that time period; the required power supply of each secondary energy device is multiplied by the time period length and then by the corresponding carbon emission factor to obtain the carbon emissions of that secondary energy device in that time period; all the above carbon emissions are summed to obtain the total carbon emissions for that time period; then the total carbon emissions for all time periods are summed to obtain the basic carbon emissions for the entire electricity consumption cycle; since the carbon emission factor of primary energy devices is usually lower and the carbon emission factor of secondary energy devices is usually higher, the basic carbon emissions are mainly determined by the power supply of secondary energy devices.

[0081] First penalty: carbon emissions One method of obtaining it includes: ; in, Let k be the first penalty carbon emission for the available collaborative scheme. The number of time periods within an electricity consumption cycle. For the number of second energy devices, For the first Among the available collaborative solutions, the one numbered is... The second energy device in the The equivalent emergency supplementary power corresponding to the time period; For the kth available collaborative solution, the one numbered is... The required power supply of the second energy device in time period t, The time period length corresponds to each time period. For the number The carbon emission factor corresponding to the second energy equipment.

[0082] Specifically, the calculation method for the first penalty carbon emission is as follows: For each time period, the equivalent emergency supplementary power of each secondary energy device is subtracted from its required power supply to obtain the emergency supplementary power increment of the secondary energy device in that time period. This increment is multiplied by the time period length and then by the corresponding carbon emission factor to obtain the additional carbon emissions generated by the secondary energy device due to emergency supplementation in that time period. The additional carbon emissions of all secondary energy devices in all time periods are summed to obtain the first penalty carbon emission. When weather fluctuations cause the actual output of the primary energy device to be lower than the power forecast, the secondary energy device needs to increase its output power beyond the original planned power to maintain supply and demand balance. The carbon emissions corresponding to this additional output power are the first penalty carbon emissions. The larger the weather fluctuation index, the higher the risk of the actual output of the primary energy device deviating from the power forecast, the greater the emergency supplementary power required by the secondary energy device, and the higher the first penalty carbon emissions.

[0083] Second penalty for carbon emissions One method of acquisition includes: ; in, Let k be the second penalty carbon emission for the available collaborative scheme. The number of time periods within an electricity consumption cycle. For the number of second energy devices, This is the number corresponding to the second energy device, and , Number the time period variable, and , For the kth available collaborative solution, the one numbered is... The equivalent emergency power supplement for the second energy device in time period t, For the kth available collaborative solution, the one numbered is... The equivalent emergency supplementary power of the second energy device in time period t-1, For the kth available collaborative solution, the one numbered is... The required power supply of the second energy device in time period t, For the kth available collaborative solution, the one numbered is... The required power supply for the second energy device in time period t-1 This refers to the carbon emission function for state transitions. The state transition carbon emission function corresponds to the carbon emissions generated during various operational state transitions of a device. Most typically, it represents the carbon emissions generated when a device starts up from a closed state to an open state. Setting up operational state transitions during operation also leads to similar additional carbon emissions; generally, the larger the span of the operational state transition, the greater the corresponding additional carbon emissions. Specific carbon emission functions can be set through expert experience. For example, when a device switches from state A to state B, the total energy consumption from the start of the switch until it is fully stable in state B is recorded. The product of this total energy consumption and the corresponding carbon emission factor is recorded as the transition carbon emission when the device switches from state A to state B. The state transition carbon emission function represents the mapping relationship between various state transitions of the corresponding device and the corresponding transition carbon emissions. For the number The corresponding second energy device is in Power conversion The carbon emissions corresponding to the additional power generation equipment consumption; For the number The corresponding second energy device is in Power conversion The carbon emissions corresponding to the additional power generated by the equipment consumption are calculated. Specifically, the state transition carbon emission function is used to calculate the carbon emissions corresponding to the additional equipment consumption during the power state transition of the equipment. When the power of the second energy equipment changes significantly, such as switching from a low-load state to a high-load state or starting from a shutdown state, the equipment itself will generate additional fuel consumption, heat loss, or mechanical loss. The carbon emissions corresponding to these additional consumptions are quantified by the state transition carbon emission function. The second penalty carbon emission is calculated by the difference between the state transition carbon emission corresponding to the equivalent emergency supplementary power sequence and the state transition carbon emission corresponding to the demand power supply sequence, reflecting the additional carbon emissions generated by the increased power adjustment of the second energy equipment due to weather fluctuations.

[0084] State transition carbon emission function Used to calculate the power of the second energy device Transform into The additional carbon emissions generated at that time. As a specific implementation of this embodiment, the function can take the following form: Linear form: ,in For equipment The carbon emission coefficient per unit power conversion was obtained by fitting historical operating data. Or piecewise linear form: Each parameter is obtained through calibration using equipment characteristic data; Or, in the form of a table lookup: ,in For equipment The carbon emission lookup table for power state transitions was obtained through actual measurement and calibration.

[0085] The aforementioned coefficients and lookup tables can be pre-acquired and stored for use by the target function. Those skilled in the art can select the appropriate form based on the device type and operating characteristics.

[0086] The second penalty carbon emission is obtained by calculating the difference between the state transition carbon emissions corresponding to the equivalent emergency power supplement sequence and the state transition carbon emissions corresponding to the demand power supply sequence.

[0087] The equivalent emergency supplementary power One method of obtaining the power includes: solving the objective function to obtain the equivalent emergency supplementary power of each secondary energy device in each time period; the objective function is: ; in, For the first Among the available collaborative solutions, the one numbered is... The second energy equipment is in The equivalent emergency supplementary power to be confirmed for the corresponding time period; the objective function includes at least the following constraints: Supply and demand equilibrium conditions: ; in, For the number The first of the available collaborative solutions The time period corresponds to the total equivalent emergency replenishment power; one method for obtaining the total equivalent emergency replenishment power includes: ; in, For the first Weather fluctuation index corresponding to the time period; For the number The required power supply of the first energy device in time period t. The number of primary energy equipment, For the number The required power supply of the second energy device in time period t, The number of secondary energy facilities; Specifically, the total equivalent emergency power replenishment is calculated as follows: multiply the weather fluctuation index by the proportion of the total power demand of the first energy device to the total power demand of all energy devices, and then multiply by the total power demand of the first energy device. This calculation method reflects the product of the degree of impact of weather fluctuations on the output of the first energy device and the proportion of the first energy device in the power supply structure. When the weather fluctuation index is large and the power supply ratio of the first energy device is high, the absolute amount by which the actual output of the first energy device deviates from the estimated power is large, and the total power required for emergency replenishment by the second energy device is correspondingly large.

[0088] The objective function also includes a maximum upper bound constraint and a ramp constraint. The maximum upper bound constraint is as follows: ; in, for The maximum output limit corresponding to the second energy equipment; Slope constraints ; in, for The maximum ramp limit corresponding to the second energy equipment.

[0089] This embodiment constructs a collaborative planning objective function that includes a base carbon emission, a first penalty carbon emission, and a second penalty carbon emission. It incorporates emergency supplementary carbon emissions caused by weather fluctuations and additional carbon emissions generated by equipment power state transitions into the calculation of comprehensive carbon emissions. The final collaborative planning scheme is selected with the goal of minimizing comprehensive carbon emissions. Since the calculation of comprehensive carbon emissions considers three dimensions simultaneously: normal execution carbon emissions, emergency supplementary carbon emissions, and state transition carbon emissions, and quantifies the impact of weather fluctuations into the calculation of emergency supplementary power through a weather fluctuation index, the final collaborative planning scheme can maintain a low carbon emission level under weather fluctuation conditions while meeting electricity demand and carbon emission quota constraints. This improves the reliability of carbon emission control under weather fluctuation conditions through multi-energy collaborative planning.

[0090] Example 9: Please see Figure 2 This embodiment provides a comprehensive energy carbon management multi-energy collaborative low-carbon planning system for executing the comprehensive energy carbon management multi-energy collaborative low-carbon planning method described in any of embodiments 1 to 8. The system can be deployed on an energy management platform within the collaborative management area or on a cloud server. It interacts with electricity metering devices, weather monitoring equipment, and control systems of various energy devices within the collaborative management area via a communication network. The system includes: a data acquisition module, a database, a data analysis module, and a collaborative control module. The data acquisition module is used to acquire weather data corresponding to the collaborative management area; The data analysis module includes a time-period quota generation unit, a power prediction unit, and a collaborative planning unit; The time-period quota generation unit obtains several historical electricity consumption data through a database connected to it, generates a carbon emission ratio matrix corresponding to each time period based on the historical electricity consumption data, obtains the remaining carbon emission quota, and generates a carbon emission quota sequence based on the carbon emission ratio matrix and the remaining carbon emission quota, the carbon emission quota sequence including the time-period carbon emission quota corresponding to each time period. The power estimation unit is used to acquire weather data corresponding to the collaborative management area; based on the weather data, it performs capacity estimation of the first energy equipment to obtain the power estimation sequence corresponding to each first energy equipment. The collaborative planning unit generates a collaborative planning scheme based on the power prediction sequence and carbon emission quota sequence corresponding to each first energy device. The collaborative planning scheme includes the required power supply of each first energy device and second energy device. The collaborative control module is used to control each of the first energy devices and the second energy devices based on a collaborative planning scheme. The first energy devices are renewable energy power generation devices, and the second energy devices are non-renewable energy power generation devices.

[0091] Some of the data in the above formula are calculated by removing the dimensions and taking their numerical values; the preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation.

[0092] The above embodiments are only used to illustrate the technical methods of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of this application without departing from the spirit and scope of the technical methods of this application.

Claims

1. A comprehensive energy carbon management and multi-energy coordinated low-carbon planning method, characterized in that, include: Acquire some historical electricity consumption data, and generate a carbon emission ratio matrix for each time period based on the historical electricity consumption data; Obtain the remaining carbon emission credits, and generate a carbon emission credit sequence based on the carbon emission ratio matrix and the remaining carbon emission credits. The carbon emission credit sequence includes the carbon emission credits for each time period. Acquire weather data corresponding to the collaborative management area; based on the weather data, estimate the capacity of the primary energy equipment to obtain the power prediction sequence for each primary energy equipment; Obtain the electricity demand sequence; based on the electricity demand sequence, the power prediction sequence and carbon emission quota sequence corresponding to each primary energy device, generate available collaborative solutions for the primary and secondary energy devices; The first energy device is a renewable energy power generation device, and the second energy device is a non-renewable energy power generation device; Acquire weather data for the collaborative management area and other areas within a defined range, and generate weather fluctuation indices for each time period based on the weather data; A collaborative planning objective function is constructed based on the weather fluctuation index and various available collaborative schemes, and the final collaborative planning scheme is selected. The collaborative planning scheme includes the power demand of each first energy device and second energy device.

2. The integrated energy carbon management and multi-energy synergistic low-carbon planning method according to claim 1, characterized in that, The process of generating a carbon emission ratio matrix for each time period based on historical electricity consumption data includes: Extract the periodic electricity consumption data for each electricity consumption cycle from the historical electricity consumption data; extract the time-period electricity consumption corresponding to each time period in the electricity consumption data of each cycle; After normalizing the electricity consumption for each time period, the electricity consumption for each time period is integrated into a time period electricity consumption sequence corresponding to the electricity consumption cycle in a set order; the time period electricity consumption sequence corresponding to each electricity consumption cycle is generated in sequence; the average value of the elements at the same position in each time period electricity consumption sequence is calculated, the average value is used as the feature value of that position, and a cycle electricity consumption feature matrix is ​​constructed based on these feature values; Extract the weather type corresponding to each period of electricity consumption data, and the power supply data for each time period within each period of electricity consumption data; extract the power supply amount corresponding to each energy device in each time period power supply data; the energy device includes a first energy device and a second energy device; calculate the power supply ratio of each energy device corresponding to the time period power supply data based on the power supply amount corresponding to each energy device, and integrate the power supply ratios corresponding to each energy device into a time period power supply ratio sequence according to a set order; Obtain the power supply ratio sequence for each time period in the power consumption data of each cycle with the same weather type; calculate the average value of the elements at the same position in each time period power supply ratio sequence, use the average value as the feature value of that position, and construct the time period power supply ratio feature sequence for the time period corresponding to the weather type based on the feature value, generate the power supply ratio feature sequence for each time period corresponding to the weather type in sequence, integrate the power supply ratio feature sequences corresponding to each time period into the power supply feature matrix corresponding to the weather type; generate the power supply feature matrix corresponding to each weather type in sequence. Obtain the carbon emission factors corresponding to each energy device, and integrate the carbon emission factors into a carbon emission factor feature matrix in a set order; generate a carbon emission ratio matrix based on the periodic electricity consumption feature matrix, the power supply feature matrix and the carbon emission factor feature matrix, wherein the carbon emission ratio matrix contains the carbon emission ratio corresponding to each time period.

3. The integrated energy carbon management and multi-energy synergistic low-carbon planning method according to claim 2, characterized in that, The generation of the carbon emission ratio matrix based on the cyclic electricity consumption characteristic matrix, the power supply characteristic matrix, and the carbon emission factor characteristic matrix includes: Obtain the carbon emission factor feature matrix and the power supply feature matrix, and calculate the comprehensive carbon emission factor matrix corresponding to each time period based on each element of the carbon emission factor feature matrix and the power supply feature matrix. Obtain the periodic electricity consumption characteristic matrix, and calculate the carbon emission intensity matrix based on the periodic electricity consumption characteristic matrix and the comprehensive carbon emission factor matrix; normalize each carbon emission intensity in the carbon emission intensity matrix to obtain the carbon emission ratio matrix.

4. The integrated energy carbon management and multi-energy synergistic low-carbon planning method according to claim 1, characterized in that, The generation of carbon emission quota sequences based on the carbon emission ratio matrix and remaining carbon emission quotas includes: Obtain the remaining carbon emission allowance and the number of electricity cycles corresponding to the remaining carbon emission allowance; calculate the cycle carbon emission allowance corresponding to each electricity cycle; Obtain the weather type corresponding to the predicted electricity consumption cycle in the collaborative management area, obtain the carbon emission ratio matrix corresponding to the weather type, calculate the carbon emission quota for each period and the carbon emission ratio corresponding to each time period in the carbon emission ratio matrix to obtain the carbon emission quota for each time period, and integrate the carbon emission quotas corresponding to each time period into a carbon emission quota sequence according to a set order.

5. The integrated energy carbon management and multi-energy synergistic low-carbon planning method according to claim 1, characterized in that, The process of forecasting the production capacity of the first energy equipment based on weather data yields a power forecast sequence for each first energy equipment, including: Extract weather parameters for several time periods from the weather data corresponding to each time period in the collaborative management area; Obtain weather parameters for several time periods corresponding to each first energy device, input the weather parameters for each time period into the power generation prediction model corresponding to the first energy device, obtain the power prediction value of the first energy device in the corresponding time period, integrate the power prediction values ​​according to the order of their corresponding time periods into a success rate prediction sequence; and generate the power prediction sequence corresponding to each first energy device in sequence.

6. The integrated energy carbon management and multi-energy synergistic low-carbon planning method according to claim 1, characterized in that, The process of generating available collaborative solutions for the first and second energy devices based on the electricity demand sequence, the power estimation sequence for each first energy device, and the carbon emission allowance sequence includes: A supply-demand balance constraint is constructed based on the electricity demand sequence and the power forecast sequence corresponding to each primary energy device; the supply-demand balance constraint is as follows: ； ； in, For the number The first energy device in the The required power supply for the corresponding time period; For the number The second energy device in the The required power supply for the corresponding time period; For the number The first energy device corresponds to the predicted power generation sequence in the first energy device Power estimates for the corresponding time period; The first in the electricity demand sequence Electricity demand corresponding to the time period; This is the number corresponding to the first energy device, and , The number of primary energy equipment; This is the number corresponding to the second energy device, and , The number of secondary energy facilities; ; This represents the length of each time period. By applying supply and demand balance constraints, combinations of estimated power generation from primary energy equipment and power demand from secondary energy equipment are obtained; these combinations are denoted as undetermined collaborative schemes; carbon emission quota constraints are constructed based on the carbon emission quota sequence; the carbon emission quota constraints are as follows: ； in, No. Among the pending collaborative solutions, the one numbered is... The first energy device in the The required power supply for the corresponding time period For the number The carbon emission factor corresponding to the first energy equipment; No. Among the pending collaborative solutions, the one numbered is... The second energy device in the The required power supply for the corresponding time period For the number The carbon emission factor corresponding to the second energy equipment; The first in the carbon emission credit series Carbon emission allowances corresponding to the time period; Several undetermined collaborative schemes that meet the carbon emission quota constraints are denoted as available collaborative schemes.

7. The integrated energy carbon management and multi-energy synergistic low-carbon planning method according to claim 1, characterized in that, Based on the aforementioned weather data, weather fluctuation indices are generated for each time period, including: Acquire weather data for each region within a set range; extract several time-period weather parameters from the weather data for each time period; normalize and integrate the several time-period weather parameters for each time period into a time-period weather feature vector for the region. The weather fluctuation index for each time period is obtained by substituting the weather feature vectors of the collaborative management area and the corresponding time period of each area into a set weather fluctuation index generation function; one expression of the weather fluctuation index generation function includes: ； in, For the first Weather fluctuation index corresponding to the time period; For collaborative management of the region The weather feature vector corresponding to the time period; Number The region The weather feature vector corresponding to the time period. Assign corresponding numbers to other areas within the collaborative management area, and , Set the total number of other areas within the collaborative management area; For collaborative management of the region The weather feature vector corresponding to the time period. Number the time period variable, and ; These are spatially discrete weighting coefficients. This is the time inertia weighting coefficient, and .

8. The integrated energy carbon management and multi-energy synergistic low-carbon planning method according to claim 1, characterized in that, The selection of the final collaborative planning scheme from various available collaborative schemes based on the weather fluctuation index includes: Obtain the weather fluctuation index corresponding to each time period, as well as the required power supply for each primary energy device and secondary energy device in each available collaborative solution during each time period; A collaborative planning objective function is constructed by using the weather fluctuation index corresponding to each time period, the required power supply of the first energy device, and the second energy device; the collaborative planning objective function is: ； in, For the number The combined carbon emissions corresponding to the available collaborative solutions; For the number The basic carbon emissions corresponding to the available collaborative solutions, that is, the carbon emissions generated by the normal execution of the available collaborative solutions; For the number The first penalty carbon emissions corresponding to the available synergistic solutions, The second penalty is for carbon emissions; One method for calculating the baseline carbon emissions includes: ； in, Let k be the base carbon emissions for the available synergistic scheme. The number of time periods within an electricity consumption cycle. Number the time period variable, and , The number of primary energy equipment, This is the number corresponding to the first energy device, and , For the kth available collaborative solution, the one numbered is... The required power supply of the first energy device in time period t. The time period length corresponds to each time period. For the number The carbon emission factor corresponding to the first energy equipment, For the number of second energy devices, This is the number corresponding to the second energy device, and , For the kth available collaborative solution, the one numbered is... The required power supply of the second energy device in time period t, For the number The carbon emission factor corresponding to the second energy equipment; First penalty: carbon emissions One method of obtaining it includes: ； in, Let k be the first penalty carbon emission for the available collaborative scheme. The number of time periods within an electricity consumption cycle. For the number of second energy devices, For the first Among the available collaborative solutions, the one numbered is... The second energy device in the The equivalent emergency supplementary power corresponding to the time period, wherein the equivalent emergency supplementary power is generated by the weather fluctuation factor; For the kth available collaborative solution, the one numbered is... The required power supply of the second energy device in time period t, The time period length corresponds to each time period. For the number The carbon emission factor corresponding to the second energy equipment; Second penalty for carbon emissions One method of acquisition includes: ； in, For the number The corresponding second energy device is in Power conversion The carbon emissions corresponding to the additional power generation equipment consumption; For the number The corresponding second energy device is in Power conversion The carbon emissions corresponding to the additional power generation equipment consumption; This is the carbon emission function for state transitions.

9. The integrated energy carbon management and multi-energy synergistic low-carbon planning method according to claim 8, characterized in that, One method for obtaining the equivalent emergency supplementary power includes: Solving the objective function yields the equivalent emergency supplementary power of each secondary energy device at each time period; the objective function is: ； in, For the first Among the available collaborative solutions, the one numbered is... The second energy equipment is in The equivalent emergency supplementary power to be confirmed for the corresponding time period; the objective function includes at least the following constraints: Supply and demand equilibrium conditions: ； in, For the number The first of the available collaborative solutions The time period corresponds to the total equivalent emergency replenishment power; one method for obtaining the total equivalent emergency replenishment power includes: ； in, For the first Weather fluctuation index corresponding to the time period; For the number The required power supply of the first energy device in time period t. The number of primary energy equipment, For the number The required power supply of the second energy device in time period t, The number of secondary energy facilities.

10. A comprehensive energy carbon management multi-energy collaborative low-carbon planning system, based on the comprehensive energy carbon management multi-energy collaborative low-carbon planning method according to any one of claims 1 to 9, characterized in that, include: The system comprises a data acquisition module, a database, a data analysis module, and a collaborative control module; among which, The data acquisition module is used to acquire weather data corresponding to the collaborative management area; The data analysis module includes a time-period quota generation unit, a power prediction unit, and a collaborative planning unit; The time-period quota generation unit obtains several historical electricity consumption data through a database connected to it, generates a carbon emission ratio matrix corresponding to each time period based on the historical electricity consumption data, obtains the remaining carbon emission quota, and generates a carbon emission quota sequence based on the carbon emission ratio matrix and the remaining carbon emission quota, the carbon emission quota sequence including the time-period carbon emission quota corresponding to each time period. The power estimation unit is used to acquire weather data corresponding to the collaborative management area; based on the weather data, it performs capacity estimation of the first energy equipment to obtain the power estimation sequence corresponding to each first energy equipment. The collaborative planning unit obtains the electricity demand sequence; based on the electricity demand sequence, the power estimation sequence corresponding to each first energy device, and the carbon emission quota sequence, it generates available collaborative schemes corresponding to the first energy device and the second energy device; the first energy device is a renewable energy power generation device, and the second energy device is a non-renewable energy power generation device; Acquire weather data for the collaborative management area and other areas within a defined range, and generate weather fluctuation indices for each time period based on the weather data; Based on the weather fluctuation index and various available collaborative schemes, a collaborative planning objective function is constructed, and the final collaborative planning scheme is selected. The collaborative planning scheme includes the power demand of each first energy device and second energy device. The collaborative control module is used to control each of the first energy devices and the second energy devices based on a collaborative planning scheme. The first energy devices are renewable energy power generation devices, and the second energy devices are non-renewable energy power generation devices.

Images