New energy heat supply planning method, system, equipment and medium

Abstract

The invention provides a new energy heat supply planning method, system and device and a medium, and relates to the field of renewable energy consumption, and the method comprises the steps: obtaining new energy resources, air temperature and heat load data; matching a scene corresponding to the new energy resource, the air temperature and the thermal load data from a historical demand scene or a future prediction scene; and inputting the scene into a preset new energy heat supply model, and optimizing to obtain a new energy minimum installation scale. According to the method, the new energy heat supply model is established, the minimum development scale meeting the requirement is automatically generated, and index waste caused by scale exceeding is avoided. The new energy heat supply model achieves the degree of implementation of project economy evaluation, the whole model is more accurate and reliable, the method is widely applied to consultation evaluation of new energy index quota approved by the government and new energy scale construction by investment enterprises, and scientific reference is provided for government and enterprise decision making.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of renewable energy consumption, in particular to a new energy heating planning method, system, device and medium. BACKGROUND

[0002] In the field of renewable energy consumption, new energy heating system as a key technology path to improve energy utilization efficiency and promote clean energy consumption, its planning and operation optimization method is constantly evolving with technology iteration and policy guidance. At present, the electric boiler system with heat storage represented by wind power heating has become a research hotspot. The related optimization model integrates the demand response mechanism, takes the minimization of operation cost as the objective function, and realizes the coordinated optimization of electric boiler start-stop plan and heat storage device charging-discharging strategy under the constraints of meeting heating load and wind power output fluctuation. Further, for the multi-mode operation characteristics of electric boiler (such as continuous heating and intermittent heat storage), the existing research has constructed an optimization framework based on wind power consumption, which quantifies the coal saving benefit and carbon emission reduction potential under different operation modes, providing quantitative decision basis for system mode selection.

[0003] However, the existing technology still has three significant limitations: first, the economic evaluation system is out of touch with the actual investment decision. The current model mostly uses a single cost indicator as the optimization target, without introducing a complex investment decision model including the whole life cycle cost, time value of money, risk premium and other factors, resulting in deviation between the optimization results and actual decision-making processes such as project feasibility study and capital internal rate of return calculation, which makes it difficult to directly guide engineering practice. Second, the scale optimization logic lacks policy and market dimension constraints. The existing method focuses on technical parameter optimization, but does not establish a new energy scale back-propagation mechanism to ensure that the project has investment economic feasibility with the minimum new energy scale. There is a lack of optimization models constructed from the perspective of government approval of local new energy target quota and investment enterprises reporting new energy scale. Third, the lack of technology integration restricts the improvement of system energy efficiency. With the rapid penetration of heat pump technology in the heating field, the nonlinear characteristics of its coefficient of performance (COP) affected by environmental temperature, water source conditions, equipment selection and other factors have not been included in the multi-energy complementary optimization framework of existing new energy heating systems. This technical fragmentation leads to the inability of the model to accurately assess the operation efficiency of the heat pump, especially in the "electric heating coordination" scenario. Most of them only consider the electric boiler system, and lack of integration of heat pump model into the system optimization operation. The coefficient of performance (COP) of the heat pump is affected by many factors, and there is a lack of representation model. SUMMARY

[0004] The present application provides a new energy heating planning method, system, device and medium to solve the problem of ensuring the economic feasibility of new energy heating projects under the premise of obtaining the minimum new energy target quota approved by the government or the minimum new energy scale reported by the investment enterprise.

[0005] To achieve the above object, the technical scheme adopted by the present application is as follows: acquire new energy resources, temperature and heat load data; From the historical demand scenario or the future forecast scenario, match the scenario corresponding to the new energy resources, temperature and heat load data; input the scenario into a preset new energy heating model to obtain the minimum installed capacity of new energy.

[0006] In some embodiments, the process of constructing a new energy heating model is as follows: acquire new energy resources, temperature and heat load data of the new energy heating project, and evaluate the economic feasibility of the new energy heating project; construct an energy conversion path of wind power, photovoltaic, heat pump, heat storage and standby boiler; define a target function, a constraint condition and a boundary condition based on the energy conversion path; simulate dynamic operation through a simulation tool to obtain the minimum scale of the new energy heating project that meets the input and output boundary conditions.

[0007] In some embodiments, the target function is the minimum wind power installed capacity that the entire new energy heating project can have economic feasibility; The constraint condition includes power balance, energy balance, new energy utilization rate, new energy heating proportion as a technical constraint, and project operating period capital internal rate of return reaching a preset value as an economic constraint; The boundary condition is the new energy output coefficient at each time, the temperature at each time and the heat load at each time.

[0008] In some embodiments, the power balance is the balance of the output electric power of wind power and photovoltaic and the electric power for driving the heat pump and the abandoned electric power, and the balance of the sum of the heat output power of the heat pump, the heat storage energy charging and discharging heat power and the standby boiler heat power and the heat load power. The energy balance is the balance of the difference between the heat storage energy charging and discharging heat power and the amount of heat change in the heat storage energy per unit time.

[0009] In some embodiments, the construction process of the historical demand scenario is as follows: acquire historical new energy resources, temperature and heat load data, and perform correlation analysis on the historical new energy resources, temperature and heat load data to obtain a correlation matrix; dimension reduction is performed on the correlation matrix to obtain a feature set, and clustering analysis is performed on the feature set to obtain a plurality of clusters; select the sample closest to the cluster center from each cluster as the historical demand scenario.

[0010] In some embodiments, the construction process of the future prediction scene comprises: Obtain historical new energy resources, air temperature and heat load data, and preprocess them; Input the preprocessed data into a global climate model to obtain key parameters of future trends; Sample the probability distribution of the key parameters by the Monte Carlo method to obtain a multi-scenario data set.

[0011] In some embodiments, the process of constructing the energy conversion path of new energy, heat pumps, heat storage and standby boilers comprises: The new energy power generation equipment is connected to the heat pump through a cable; The heat pump is connected to the heat storage equipment and the heat station through a pipeline; The heat storage equipment is connected to the heat station through a pipeline; The standby boiler is connected to the heat station through a pipeline.

[0012] The present application provides a new energy heating planning system, comprising: An acquisition unit configured to acquire new energy resources, air temperature and heat load data; A matching unit configured to match a scenario corresponding to the new energy resources, air temperature and heat load data from a historical demand scenario or a future prediction scenario; An optimization unit configured to input the scenario into a preset new energy heating model to optimize to obtain a minimum installed capacity of new energy.

[0013] The present application provides a computer device, comprising: At least one processor; and a memory storing a computer program running on the processor, wherein the processor executes the program to perform the steps of the new energy heating planning method.

[0014] The present application provides a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to perform the steps of the new energy heating planning method.

[0015] Compared with the prior art, the present application has the following beneficial effects: The present application provides a new energy heating planning method, system, device and medium, which comprises: acquiring new energy resources, air temperature and heat load data; matching a scenario corresponding to the new energy resources, air temperature and heat load data from a historical demand scenario or a future prediction scenario; inputting the scenario into a preset new energy heating model to optimize to obtain a minimum installed capacity of new energy.

[0016] The present application establishes a new energy heat supply model to automatically generate the minimum development scale meeting the requirements, and avoid the index waste caused by the scale exceeding the standard. The new energy heat supply model reaches the implementable degree for the project economic evaluation, and the overall model is more accurate and reliable, and is widely applicable to the consultation and evaluation of government approval of new energy index quota and investment enterprise construction of new energy scale, and provides scientific reference for government and enterprise decision-making. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other embodiments can be obtained without creative labor on the basis of these drawings.

[0018] Figure 1 A flow chart of a new energy heat supply planning method provided by the present application is provided. Figure 2 A system module diagram of a new energy heat supply planning provided by the present application is provided. Figure 3 A structural schematic diagram of an embodiment of a computer device provided by the present application is provided. Figure 4 A structural schematic diagram of an embodiment of a computer readable storage medium provided by the present application is provided. Figure 5 An energy path diagram of a new energy heat supply planning method provided by the present application is provided. Figure 6 A flow chart of an embodiment of a new energy heat supply planning method provided by the present application is provided. DETAILED DESCRIPTION

[0019] The present application will be further described below in combination with the drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present application, and cannot limit the protection scope of the present application. It should be pointed out that the following detailed description is exemplary, and is intended to provide further description of the present application.

[0020] It should be noted that all the expressions of "first" and "second" in the embodiments of the present application are used to distinguish two same name different entities or different parameters, and "first" and "second" are only used for the convenience of description, and should not be understood as the limitation of the embodiments of the present application. The subsequent embodiments will not be described one by one.

[0021] The present application provides a new energy heat supply planning method, please refer to Figure 1 and Figure 6 , including: S1, acquiring new energy resource, temperature and heat load data; S2, matching the scene corresponding to the new energy resource, temperature and heat load data from the historical demand scene or the future prediction scene; S3, inputting the scene into a preset new energy heating model to obtain the minimum installed capacity of new energy.

[0022] The time series output curve of wind power and photovoltaic directly reflects the spatiotemporal distribution characteristics of new energy, the temperature data forms a key environmental constraint by affecting the heating efficiency (COP) of the heat pump, and the heat load data determines the terminal heating demand size that the system needs to meet. From the historical demand scene, the demand scene corresponding to the new energy resource, temperature and heat load data is matched, and a multi-dimensional association model is established through data mining technology to solve the time mismatch problem between new energy output and heat load demand. The future prediction scene can accurately reflect the future trend, and based on the meteorological model, the future prediction scene is generated to minimize the new energy scale as the target to optimize the future energy system configuration. The historical demand scene library usually contains multi-year meteorological data, energy prices, user behavior patterns and other complex information. The actual impact of extreme weather, equipment failure and other uncertain factors has been included in the historical scene, avoiding the deviation caused by relying on the model, and strengthening the model's response to risk scenarios. The future prediction scene usually includes the trend of meteorological data, the influence of renewable energy subsidies on the cost of new energy development, and the prediction of heat load data through industry planning and energy efficiency improvement. The future prediction scene covers the possible range of future changes while quantifying uncertainty, thereby increasing the richness of the data and ensuring the scientificity and practicality of the new energy heating model.

[0023] The future prediction scene quantitatively estimates the trend of wind and solar energy in a specific region over a period of time through meteorological data analysis and artificial intelligence algorithms, and outputs normalized wind power and photovoltaic power generation output coefficients.

[0024] The future prediction scene uses a numerical weather prediction (NWP) fusion long short-term memory network (LSTM) that combines physical modeling and AI. The physical model provides trend prediction to obtain the overall trend of future wind speed or illumination, and the LSTM corrects the local errors of the NWP.

[0025] The NWP data includes key meteorological elements such as wind speed, temperature, cloud cover, air pressure, humidity, etc. Combined with the micro-siting information of the power station, including terrain height, slope, vegetation coverage, photovoltaic panel inclination, etc. Different terrains have different effects on wind speed, vegetation coverage affects the roughness of the ground and thus the distribution of wind speed, and the inclination of the photovoltaic panel determines the efficiency of solar energy reception. By incorporating these geographical environmental parameters into the physical model, the distribution and variation of wind and solar energy in a specific area can be simulated more accurately. The available wind or solar energy is calculated. For wind energy, the wind power density is calculated based on the relationship between wind speed and wind power density; for solar energy, the theoretical output of photovoltaic power generation is calculated by combining the solar radiation model and the characteristic parameters of the photovoltaic panel.

[0026] LSTM can handle high-dimensional, nonlinear, and long-time series data, and is particularly suitable for capturing long-term dependencies such as seasonal changes and day-night alternations in complex environments such as mountains. By introducing a gating mechanism, LSTM can effectively solve the problem of gradient vanishing or gradient explosion that occurs when traditional recurrent neural networks process long-time series data. It remembers information over a long period of time and dynamically adjusts the flow of information based on current input and historical state, thereby better capturing long-term dependencies in the data.

[0027] The changes in wind and light resources in the future prediction scenario are influenced by a variety of factors and exhibit complex nonlinear characteristics. LSTM can perform complex nonlinear transformations on input data through its nonlinear activation function and multi-layer network structure, thereby establishing a nonlinear mapping relationship from historical meteorological data and power generation output data to future power generation output, and accurately predicting the fluctuations in wind and light resources.

[0028] The matched scenario is input into a preset new energy heating model to optimize the minimum installation scale of new energy. The preset model usually integrates multiple constraint conditions, simultaneously considering the operating characteristics of devices such as electric boilers, heat pumps, and heat storage devices, as well as external constraints such as grid dispatching rules and subsidy policies. After inputting the matched scenario, the model finds the minimum new energy installation that meets the following conditions through iterative calculation. Through scenario coverage analysis, the minimum installation scale takes into account both economy and safety, avoiding excessive investment or insufficient capacity; by dynamically optimizing the device combination, the capacity ratio of heat pumps and electric boilers is adjusted, further improving system energy efficiency.

[0029] In some embodiments, referring to Figure 1 and Figure 6 , the process of building a new energy heating model is as follows: Obtain new energy resources, air temperature, and heat load data for the new energy heating project, and evaluate the economic feasibility of the new energy heating project; Build the energy conversion path of wind power, photovoltaic, heat pump, heat storage and standby boiler; Define the objective function, constraint condition and boundary condition based on the energy conversion path; Simulate dynamic operation through simulation tools to get the minimum scale of new energy heating project that meets the input and output boundary conditions.

[0030] Establish a mixed integer linear programming optimization model to calculate the minimum new energy installed capacity that meets the heat load demand and economic feasibility, as well as the scale and operation mode of other components. Use programming language Matlab+Yalmip to build the programmatic description of this mixed integer linear programming optimization model, and then use Gurobi solver to solve it. The operation logic is to optimize the scale and operation mode of each part under the condition of meeting technical constraints and economic constraints, with the minimum new energy installed capacity as the objective function.

[0031] Obtain historical new energy resources, temperature and heat load data of new energy heating projects and evaluate their economic feasibility. Historical new energy resource data such as wind power and photovoltaic time series output curve can clearly show the fluctuation characteristics and time period distribution of new energy; temperature data directly affect the heat transfer of building envelope and heat pump heating efficiency, and then relate to heating system energy consumption; heat load data reflect the actual heat demand of user side. Together they form the core input of economic evaluation, quantifying the income level of the project under different subsidy policies and electricity price mechanism.

[0032] Build the energy conversion path of wind power, photovoltaic, heat pump, heat storage and standby boiler, which is essentially to establish the energy flow framework of multi-energy complementary system. New energy as the basic energy, its output is used to drive heat pump heating, supply to heat load, and the remaining heat energy is stored in heat storage device; when new energy output is insufficient, heat storage device releases heat, and if it still cannot meet the demand, standby boiler is started as a supplement.

[0033] Achieve the cascade utilization mode of new energy priority utilization, energy storage flexible regulation and traditional energy bottom-up guarantee. Through the efficient heating of heat pump, the unit heating energy consumption is significantly reduced; through the function of heat storage device, the time mismatch between new energy generation and heating demand is converted into internal regulation resources; through standby boiler, the risk of heating interruption caused by new energy fluctuation is avoided.

[0034] Simulate dynamic operation through simulation tools and get the minimum scale of new energy heating project that meets the input and output boundary conditions. The simulation tool integrates meteorological data, equipment characteristics, control strategy and other multi-dimensional parameters to simulate the continuous operation process of the system within 8760 hours in a year, accurately capturing the influence of extreme weather, equipment failure and other uncertain factors.

[0035] The simulation results show that when the new energy installed capacity decreases to a certain threshold, the standby boiler start-stop frequency increases sharply, leading to a sharp increase in operating costs, thus determining the threshold as the minimum size that meets the economic and reliable requirements. Not only does it provide a quantitative basis for project investment, but it also avoids the risk of frequent combustion caused by small scale or resource waste caused by large scale in static optimization through dynamic verification.

[0036] In some embodiments, referring to Figure 1 and Figure 6 , the objective function is the minimum new energy installed capacity that enables the entire new energy heating project to be economically feasible; The constraint conditions include power balance, energy balance, new energy utilization rate, and new energy heating proportion as technical constraints and project operating period capital internal rate of return reaching a preset value as economic constraints; The boundary conditions are the new energy output coefficient at each time, the air temperature at each time, and the heat load at each time.

[0037] Taking new energy heating as an example, new energy includes wind power and photovoltaic power. The energy source of wind power is the kinetic energy generated by atmospheric motion, which is intermittent and volatile. Wind speed is affected by many factors such as geographical latitude, topography, seasonal change, and day and night alternation, resulting in a sharp fluctuation of power generation over time. In coastal areas, wind energy resources are abundant during the summer typhoon period, but the power generation drops sharply in winter due to the weakening of the monsoon. In plateau areas, the diurnal temperature difference is large, and the wind speed at night is higher than that during the day, forming a unique power generation curve. Wind power has regional concentration, and high-quality wind farms are usually distributed along the coastline, mountain passes, or plateau open areas, where the wind speed gradient is large and the turbulence intensity is low, which is conducive to the efficient operation of wind turbines. However, the energy density of wind power is low, and the single machine capacity is limited by the length of the blade and the height of the tower, which requires large-scale cluster deployment to achieve stable power supply.

[0038] The energy source of photovoltaic power is solar radiation, which is closely related to the Earth's revolution, rotation, and atmospheric state. The most notable feature is the diurnal periodicity, with a single-peak curve in the daytime with the sun's elevation angle, and no power generation at night, which requires a storage system or complementation with other energy sources to achieve 24-hour power supply. Photovoltaic power has seasonal differences, with longer sunshine hours and higher radiation intensity in summer in the northern hemisphere, with power generation up to 2-3 times that in winter, which is particularly evident in high-latitude areas. Photovoltaic power has a wide but uneven distribution of resources. In arid areas such as deserts and gobi, the cloud cover is thin and the atmospheric transparency is high, while in rainy and humid areas, the sunshine duration is short and the radiation decays quickly, resulting in a significant reduction in power generation efficiency. Wind power and photovoltaic power complement each other in terms of resource characteristics: the peak output of wind power at night can fill the gap in photovoltaic power generation, while the peak output of photovoltaic power in the afternoon can alleviate the volatility of wind power.

[0039] The objective function is the minimum new energy installed capacity that enables the entire new energy heating project to be economically feasible: The constraints include technical and economic constraints, as follows: The wind power and photovoltaic power curve represents the wind power and photovoltaic power at each moment, which is the power source of new energy. The formula is: represents the wind power at the moment, with the unit of kW; represents the wind power coefficient at the moment; is the installed capacity of wind power. represents the photovoltaic power at the moment, with the unit of kW; represents the photovoltaic power coefficient at the moment; is the installed capacity of photovoltaic power. The power balance reflects the direction of the power generated from new energy, most of which is used to drive the heat pump, and a small part of the power that cannot be utilized becomes abandoned power. The formula is as follows: is the power used to drive the heat pump, with the unit of kW, represents the abandoned power of new energy, with the unit of kW.

[0040] The heat pump uses the power generated from new energy to drive heating, and through the gain effect of heat pump integration of low-temperature heat source, it realizes efficient electric heating conversion. The heat pump heating coefficient is related to many factors such as high and low temperature heat source temperature and circulating working medium. Here, the heat pump heating coefficient formula is fitted by referring to the actual data. The formula is as follows: represents the outlet heat power of the heat pump, with the unit of kW; is the heat pump heating coefficient; is the atmospheric temperature at the moment, with the unit of ℃; is the installed capacity of the heat pump, with the unit of kW.

[0041] As the main regulating component in the new energy heating system, the thermal storage needs to consider the actual process that charging and discharging cannot be performed at the same time and there is energy loss. In the constraint description, two 0-1 variables are used to represent the charging and discharging state. The formula is as follows: and is a 0-1 variable, representing the charging and discharging state judgment; and are the heat storage and discharging heat power of the thermal storage, with the unit of kW; is the upper limit of the heat exchange power of the thermal storage, with the unit of kW; represents the heat stored in the thermal storage at the moment, with the unit of kWh; and are the efficiencies of the heat storage and discharging of the thermal storage; is the heat power provided by the standby boiler at the moment, with the unit of kW; is the heat load at the moment, with the unit of kW.

[0042] In the development of new energy projects, it is necessary to ensure that the utilization rate of new energy reaches a certain proportion, which is determined according to the requirements of the project, and its constraint expression is as follows: is the utilization rate of new energy.

[0043] New energy heating projects need to ensure that the heat provided by new energy accounts for a certain proportion of the total heat supply, which is determined according to the requirements of the project, and its constraint expression is as follows: is the new energy heating proportion requirement.

[0044] The economic benefits of the project come from three parts, one is the heating revenue in the heating season, two is the new energy surplus electricity income in the heating season, and three is the new energy power generation income when there is no need for heating in the non-heating season.

[0045] In order to make the project economically feasible, a project investment decision model is adopted, with the project operation period set to 25 years, the capital ratio set to 20%, the loan period set to 15 years, the loan interest rate set to 3%, the value-added tax rate set to 13%, the sales tax and additional tax rate set to 8%, the income tax rate set to 25%, the depreciation period set to 15 years, the fixed asset residual value rate set to 5%, and the capital internal rate of return not less than 6.5%.

[0046] and are the heating and electricity prices, respectively, with the unit of yuan / kWh; and are the non-heating season wind power and photovoltaic output power, respectively, with the unit of kW; The unit scale construction cost of wind power, photovoltaic, heat pump, heat storage, and standby boiler, respectively, is in yuan / kW or yuan / kWh; The optimal scale of wind power, photovoltaic, heat pump, heat storage, and standby boiler, respectively, is in kW or kWh; The operation and maintenance cost of wind power, photovoltaic, heat pump, heat storage, and standby boiler, respectively, is in yuan / kW or yuan / kWh; The coal consumption cost required for a unit of heat provided by the standby boiler is in yuan / kWh; The capital internal rate of return is taken as 6.5%.

[0047] The boundary conditions need to give the local wind power output coefficient , the photovoltaic output coefficient , the hourly heat load , and the hourly atmospheric temperature .

[0048] The economic constraint equation is considered for sales revenue, operation cost, tax rate, depreciation, residual value, capital internal rate of return, and the economy of the scale of each component of the system.

[0049] The economic feasibility of the entire new energy heating project is set as the core, the minimum new energy installed capacity is taken as the objective function, the constraint conditions are constructed around the technical feasibility and economic rationality, and the key parameters such as new energy output, air temperature, and heat load are explicitly defined as boundary conditions, which provides a mathematical path for the precise planning of new energy heating projects.

[0050] The objective function focuses on the minimum new energy installed capacity, which solves the core contradiction of new energy heating project investment decision. The traditional planning method often takes meeting the maximum heat load demand or achieving 100% new energy supply as a single target, resulting in redundant installed capacity or uncontrolled cost. Defining the objective function as the minimum installed capacity under economic feasibility essentially finds the balance point between new energy utilization and investment return through mathematical optimization, so that the project realizes the unity between clean transformation and business sustainability.

[0051] The dual protection of power balance and energy balance in the technical constraint ensures the physical feasibility of the system operation. The power balance constraint requires the balance of electric-thermal conversion power, and the sum of heat pump heating power, storage device charging and discharging power, and standby boiler heat supplement power in any period of time to equal the user heat load demand, which prevents the risk of heating interruption caused by power gap. The energy balance constraint further stipulates that the net value of the charging and discharging power of the storage device matches the real-time change of its stored heat.

[0052] The preset value of the internal rate of return of the capital in the economic constraints converts the project profitability into a quantitative optimization index. In the optimization process, by adjusting the variables such as the new energy installed capacity, the heat pump size, the heat storage capacity and the configuration of the standby boiler, the discount rate when the sum of the net cash flow present value in the project operation period is zero is exactly the preset rate of return.

[0053] The dynamic parameterization of the new energy output coefficient, the air temperature and the heat load in the boundary conditions significantly improves the scene adaptability of the optimization results. The new energy output coefficient reflects the actual power generation capacity of wind power / photovoltaic affected by resource conditions; the air temperature indirectly affects the heat load demand and the heating efficiency by changing the building heat loss coefficient and the heat pump COP value; the temporal and spatial distribution and the day-night difference of the heat load reflect the volatility of heat demand, avoiding the simplification bias in static planning, and making the minimum installed capacity more practical.

[0054] In some embodiments, referring to Figure 1 and Figure 6 , the power balance is the balance between the output electric power of wind power and photovoltaic and the electric power driving the heat pump and the abandoned electric power, and the balance between the sum of the heat output power of the heat pump, the heat charging and discharging power of the heat storage and the heat power of the standby boiler and the heat load power; The energy balance is the balance between the difference of the heat charging and discharging power of the heat storage and the amount of heat change per unit time in the heat storage.

[0055] As fluctuating new energy, the output electric energy of wind power and photovoltaic has three directions in the system, one is converted into heat energy to supply users through the heat pump, two is the excess energy due to the capacity limitation of the heat pump or the low heat load, and three is a small amount of energy loss in the equipment conversion efficiency. Traditional modeling often ignores the explicit expression of abandoned electric energy, resulting in an overestimation of the system size. After including the abandoned electric energy in the balance equation, the proportion of energy waste in different periods is clearly quantified, avoiding the size deviation in the scale planning.

[0056] The dynamic constraint of power balance ensures the safe and stable operation of the system in the instantaneous power level. The output power of wind power and photovoltaic presents minute-level changes affected by wind speed and illumination, while the response of devices such as heat pumps and heat storage devices to power input has a time delay. The power balance forces the matching of instantaneous supply and demand, preventing device overload or power conflict, and significantly improving the flexibility of new energy consumption and the reliability of heat supply.

[0057] The energy balance determines the capacity of the heat storage and other devices from the total amount of energy, avoiding energy supply shortage and ensuring the reliability of the whole year heat supply.

[0058] In some embodiments, referring to Figure 1 and Figure 6 , the construction process of the historical demand scene is: Obtaining historical new energy resource, temperature and heat load data, performing correlation analysis on the historical new energy resource, temperature and heat load data to obtain a correlation matrix; Performing dimensionality reduction on the correlation matrix to obtain a feature set, and performing cluster analysis on the feature set to obtain a plurality of clusters; Selecting a sample closest to the centroid in each cluster as a historical demand scenario.

[0059] The construction of the historical demand scenario converts complex time series data of original new energy resources, temperature and heat load into a representative scenario set through a data-driven method.

[0060] Based on the correlation analysis of historical new energy resources, temperature and heat load data, a correlation matrix is constructed. The new energy resources are negatively correlated with the wind power output and the temperature. In winter, the wind speed is high but the temperature is low, and in summer, the opposite is true. The temperature and heat load are strongly positively correlated. The lower the temperature, the greater the heat loss of the building, and the higher the heat load demand. The linear or nonlinear relationship between these variables is quantified by calculating the Pearson correlation coefficient to form a matrix containing the correlation of all variables. The correlation matrix converts scattered original data into a structured correlation network through statistical methods, avoiding the bias of the independent assumption of variables in scenario generation and improving the physical reasonableness of the scenario.

[0061] The correlation matrix is processed by dimensionality reduction to extract a feature set, which solves the contradiction between high-dimensional data redundancy and computational complexity and provides a simplified and effective input for cluster analysis. The original data has a very high dimension, and direct clustering is easily disturbed by noise and has low computational efficiency. Through the principal component analysis dimensionality reduction method, the correlation matrix is mapped to a low-dimensional space, retaining the principal components with the largest variance in the data.

[0062] The feature set is analyzed by clustering to divide into a plurality of clusters. The similarity of the feature set divides the historical data into a plurality of groups, each group representing a typical demand mode. K-means clustering divides the feature set into 4 categories: the first category is severe cold high load-low wind power, the winter is extremely low temperature and low wind speed, the second category is moderate medium load-medium wind power, the spring and autumn transition season, the third category is cold high load-high wind power, the winter is regular low temperature and high wind speed, and the fourth category is hot low load-low wind power, summer. Each category of clustering corresponds to a specific energy supply and demand scenario, and the samples in the feature space are distributed compactly, reflecting the coordination characteristics of new energy resources, temperature and heat load under the scenario. Cluster analysis decomposes complex historical demand into a number of typical management modes through a data-driven approach, avoiding the subjectivity of manual scenario division and improving the coverage and representativeness of the scenario.

[0063] The sample closest to the centroid is selected from each cluster as a historical demand scenario, and the centroid is the average position of all samples in the feature space in the cluster, representing the central tendency of the scenario; and the sample closest to the centroid has both proximity to the average feature and actual occurrence, which avoids the interference of extreme outliers and retains the real volatility of the scenario. By selecting a representative sample from each class, the final set of historical demand scenarios is both concise and comprehensive, covering the main modes of historical demand, providing efficient input support for the scale planning, equipment selection and operation strategy of new energy heating projects.

[0064] The real-time feature vector is constructed through dimension matching, and the current new energy resource, air temperature and heat load data are converted into a unified format with the historical demand scenario. Real-time data usually exist in the form of discrete time points, and the features of the historical demand scenario are generated through dimension reduction clustering. Through standardization processing, the differences in dimension and variable range of the original data are eliminated, so that the real-time state and the historical scenario have direct comparability.

[0065] The similarity between the real-time vector and the historical demand scenario center vector is calculated using the Euclidean distance, and a similarity list is generated. The Euclidean distance measures the straight-line distance between two points in a multi-dimensional space, reflecting the distance relationship between the current state and each historical scenario. The advantage of the Euclidean distance is that it is easy to calculate and sensitive to outliers, which can effectively distinguish the similarity difference.

[0066] The historical demand scenario corresponding to the minimum similarity value is selected as the matching result, and the step determines the historical mode closest to the current running state through the nearest neighbor principle, providing a typical input for system optimization. The minimum similarity value means that the spatial distance between the real-time vector and the historical scenario center vector is the closest, i.e. the current state is most consistent with the feature distribution of the scenario. Mapping the complex and variable real-time state to a known typical mode avoids the subjectivity of manual judgment and improves the objectivity and efficiency of decision-making.

[0067] In some embodiments, referring to Figure 1 and Figure 6 , the construction process of the future prediction scenario includes: Obtain historical new energy resource, air temperature and heat load data and preprocess them; Input the preprocessed data into a global climate model to obtain key parameters of future trends; Sample the key parameters by the Monte Carlo method to obtain a multi-scenario data set.

[0068] Calibrate data from different sources to the same spatiotemporal resolution, calibrate satellite remote sensing light data and ground meteorological station data to provincial hourly data, and eliminate model errors caused by inconsistent scales.

[0069] Global climate model is based on physical equation to simulate global climate system, and can output key parameters in next decades, including temperature and wind speed, so as to avoid deviation of extrapolation depending on historical data, and large-scale parameters are converted into local variables through downscaling technology, so that local area prediction is realized.

[0070] The key parameters are sampled according to probability distribution, a large number of prediction scenarios are generated, extreme cases are covered, and the uncertainty range is quantified.

[0071] In some embodiments, referring to Figure 1 and Figure 5 , the process of constructing the energy conversion path of new energy, heat pump, heat storage and standby boiler includes: The new energy power generation equipment is connected with the heat pump through a cable; The heat pump is connected with the heat storage equipment and the heat station through a pipeline; The heat storage equipment is connected with the heat station through a pipeline; The standby boiler is connected with the heat station through a pipeline.

[0072] The 'new energy + heat pump + heat storage + standby boiler' mode is adopted, the heat pump is driven by new energy power to supply heat, the surplus heat is stored in the heat storage equipment, and the heat is supplemented when the new energy is insufficient, and in addition, the standby boiler is configured as a standby heat source.

[0073] The present application provides a new energy heating planning system, please refer to Figure 2 , comprising: The acquisition unit 100 is configured to acquire new energy resources, temperature and heat load data; The matching unit 200 is configured to match the scene corresponding to the new energy resources, temperature and heat load data from the historical demand scene or the future prediction scene; The optimization unit 300 is configured to input the scene into a preset new energy heating model, and optimize to obtain a minimum installed capacity of new energy.

[0074] The present application investigates the new energy resource characteristics, temperature conditions and heat load characteristics of the new energy heating project site. A mixed integer linear programming model of new energy heating is established, the minimum new energy installed capacity is taken as the objective function, the power balance, energy balance, new energy utilization rate and new energy heating proportion are taken as technical constraints, the internal rate of return of capital of project operation period reaches 6.5% as economic constraint, the new energy output characteristics, temperature and heat load are taken as boundary conditions, the actual investment decision model of project is taken as economic evaluation model, the project scale configuration and operation mode are optimized, and the economic feasibility of new energy heating project is ensured.

[0075] The economic evaluation of the present application is more accurate and reliable. After adopting the actual investment decision model of the project as the economic evaluation model, the economic evaluation of the project reaches the level of implementation, and the overall model is more accurate and reliable. It is widely applicable to government and enterprise consulting projects. After establishing the operation logic of "ensuring the investment economic feasibility of the project with the minimum new energy scale", the present application is widely applicable to the consulting evaluation of government approval of new energy target quotas and investment enterprises construction of new energy scale, and provides scientific reference for government and enterprise decision-making. The innovative heat pump technology is incorporated into the calculation model. In response to the encouragement and support policy of the state for heat pump technology, the heat pump is integrated into the overall optimization model, further expanding the representation dimension and calculation range of the heat pump heating technology path.

[0076] Based on the same inventive concept, according to another aspect of the present application, as shown in Figure 3 The embodiments of the present application also provide a computer device 30, wherein the computer device 30 comprises a processor 310 and a memory 320, the memory 320 stores a computer program 321 running on the processor, and the processor 310 executes the steps of the method as above when executing the program.

[0077] Based on the same inventive concept, according to another aspect of the present application, as shown in Figure 4 The embodiments of the present application also provide a computer readable storage medium 40, which stores a computer program 410 executed by a processor to execute the method as above.

[0078] The embodiments of the present application can also include a corresponding computer device. The computer device comprises a memory, at least one processor and a computer program stored in the memory and running on the processor, and the processor executes the program to execute any one of the above methods.

[0079] The memory is a non-volatile computer readable storage medium for storing non-volatile software programs, non-volatile computer programs and modules, such as program instructions / modules in the embodiments of the present application. The processor executes various function applications and data processing of the device by running the non-volatile software programs, instructions and modules stored in the memory, that is, implements the above method.

[0080] The memory can include a program storage area and a data storage area, where the program storage area stores an operating system, application programs required for at least one function, and the data storage area stores data created according to use of the device, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory such as at least one disk storage device, a flash memory device, or other non-volatile solid state memory device. In an embodiment, the memory includes memory that is remotely located with respect to the processor, which can be connected to the local module through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0081] Finally, it should be noted that those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by a computer program instructing relevant hardware, and the program is stored in a computer-readable storage medium. When the program is executed, it includes the processes of the above-mentioned embodiments. The storage medium of the program is a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), etc. The above-mentioned embodiments of the computer program can achieve the same or similar effects as any of the above-mentioned method embodiments.

[0082] Those of skill in the art would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein can be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans can implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present embodiments.

[0083] The above are exemplary embodiments disclosed by the present disclosure, but it should be noted that various changes and modifications can be made without departing from the scope of the embodiments disclosed by the present disclosure defined by the claims. The functions, steps and / or actions of the method claims in accordance with the embodiments disclosed herein need not be performed in any particular order. The above-mentioned embodiment numbers of the embodiments disclosed by the present disclosure are only for description and do not represent the advantages and disadvantages of the embodiments. In addition, although the elements of the embodiments disclosed by the present disclosure can be described or claimed in singular form, they can also be understood as plural unless explicitly limited to singular.

[0084] It should be understood that, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising", or "includes" and / or "including" when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0085] Those skilled in the art will understand that the above description is intended to be illustrative, and not restrictive, and that many other implementations of the present embodiments are possible within the spirit and scope of the present embodiments, as defined by the appended claims.

Claims

1. A method for planning new energy heating, characterized in that, include: Acquire data on new energy resources, temperature, and heat load; Match scenarios with the data on new energy resources, temperature, and heat load from historical demand scenarios or future forecast scenarios. The scenario is input into a preset new energy heating model, and the minimum installed capacity of new energy is obtained through optimization.

2. The method for planning new energy heating according to claim 1, characterized in that, The process of constructing the new energy heating model is as follows: Obtain data on new energy resources, temperature, and heat load for new energy heating projects, and assess the economic feasibility of these projects. Construct energy conversion pathways encompassing wind power, photovoltaics, heat pumps, thermal storage, and standby boilers; Define the objective function, constraints, and boundary conditions based on the energy conversion path; By simulating dynamic operation using simulation tools, the minimum scale of a new energy heating project that meets the input and output boundary conditions is obtained.

3. The method for planning new energy heating according to claim 2, characterized in that, The objective function is the minimum installed capacity of new energy that makes the entire new energy heating project economically feasible. The constraints include power balance, energy balance, new energy utilization rate, and new energy heating ratio as technical constraints, and the project's internal rate of return on equity reaching a preset value during the project's operation period as an economic constraint. The boundary conditions are the renewable energy output coefficient, the air temperature, and the heat load at each moment.

4. The method for planning new energy heating according to claim 3, characterized in that, The power balance refers to the balance between the output power of wind power and photovoltaic power and the power of driving heat pumps and the power of abandoned power, as well as the balance between the sum of the heat output power of heat pumps, the heat storage charging and discharging power and the standby boiler heat power and the heat load power. The energy balance refers to the balance between the difference in heat power during the charging and discharging of thermal energy storage and the change in heat per unit time in thermal energy storage.

5. The method for planning new energy heating according to claim 1, characterized in that, The process of constructing the historical demand scenario is as follows: Historical data on new energy resources, temperature, and heat load are acquired, and a correlation analysis is performed on the historical data on new energy resources, temperature, and heat load to obtain a correlation matrix. The correlation matrix is ​​dimensionality reduced to obtain a feature set, and cluster analysis is performed on the feature set to obtain several clusters; Select the sample closest to the centroid from each cluster as the historical demand scenario.

6. The method for planning new energy heating according to claim 1, characterized in that, The process of constructing future predicted scenarios includes: Acquire historical data on new energy resources, temperature, and heat load, and perform preprocessing. The preprocessed data is input into a global climate model to obtain key parameters for future trends. By sampling key parameters using the Monte Carlo method to obtain a multi-scenario dataset, a probability distribution was obtained.

7. The method for planning new energy heating according to claim 2, characterized in that, The process of constructing an energy conversion pathway that integrates new energy sources, heat pumps, thermal storage, and standby boilers includes: New energy power generation equipment is connected to the heat pump via cable; The heat pump connects the heat storage equipment and the heating station via pipes; The thermal storage equipment is connected to the heating station via pipelines; The standby boiler is connected to the heating station via pipelines.

8. A system for planning new energy heating, characterized in that, include: The acquisition unit is configured to acquire data on new energy resources, temperature, and heat load. The matching unit is configured to match the demand scenarios corresponding to the new energy resources, temperature and heat load data from historical demand scenarios or future predicted scenarios. The optimization unit is configured to input the demand scenario into a preset new energy heating model and optimize it to obtain the minimum installed capacity of new energy.

9. A computer device, comprising: At least one processor; The processor also includes a memory storing a computer program that runs on the processor, wherein the processor executes the program by performing the steps of a method for planning a new energy heating system as described in any one of claims 1 to 7.

10. A computer read storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it performs the steps of the method for planning a new energy heating system as described in any one of claims 1 to 7.

Images