CN111968005A - Regional energy system potential evaluation method and system for realizing same - Google Patents

Abstract

The invention relates to a potential evaluation method of a regional energy system and a system for realizing the method. The method comprises the following steps: receiving an input target area; receiving one or more regions partitioned into a target region; receiving input regional energy (refrigeration/heating) demand and construction feasibility fraction distribution proportion; if a grid division tool is used, extracting pre-calculated energy demand and construction feasibility scores of the region from a database; if a lasso tool is used, extracting energy use requirements and construction related data of the region and national design specification data from the database, extracting a building energy requirement and construction feasibility evaluation model matched with the target region from an algorithm library, and respectively calculating energy requirements and construction feasibility scores of the region by using the model based on the data; and carrying out weighted average on the energy demand and the construction feasibility score based on the score distribution proportion to obtain and output the engineering potential score of the area.

Description

Regional energy system potential evaluation method and system for realizing same

Technical Field

The present invention relates to the field of regional energy, and in particular to a method of assessing the potential of building a regional cooling/heating system at a plurality of regions of a target area, a method of optimizing the boundaries of regions suitable for building a regional cooling/heating system, as well as a system for implementing these methods and a computer readable medium storing a computer program capable of executing the method.

Background

In recent years, regional energy is regarded as a verified energy solution, and due to the advantages (such as improvement of energy utilization efficiency, reduction of fossil energy consumption, reduction of carbon dioxide emission, and the like) of the regional energy, people are more and more favored, and a regional energy system is deployed and used in more and more cities around the world.

Broadly, regional energy is defined as: "various forms and various grades of energy required by people for production and life are reasonably, integrally and energy-efficiently produced, distributed, utilized and dissipated in a certain specific area". In a narrow sense, regional energy is defined as: the system comprises comprehensive integration of regional heating, regional cooling, regional power supply and an energy system for solving regional energy requirements. The area referred to herein may be a block divided by an administrative division, various parks, or a single building group. ". Among them, the district cooling/heating system serving particularly for cooling and heating of buildings is continuously emerging, developing and improving in various cities all over the world. A district cooling/heating system generally includes a cooling/heating station constituted by a cooling system for producing chilled water/a heating system for producing hot water, a pipe network for supplying cooling/heating to a service object such as a building, and a heat exchange device.

When planning a regional energy system for a region with a large area (e.g., a county, a city, a province, or even a country), it is important for all stakeholders to quickly and efficiently screen out the region (i.e., the region with a large potential) where the regional energy system is suitable for construction. Generally, they need to quickly complete the screening of potential sites for large numbers of regional energy systems on an urban scale during the initial stages of project development. However, the relevant data available at this stage is very small and the amount and range of screening is very large (usually on a city scale).

To address the above issues, one common solution in the prior art is to perform qualitative analysis based on interview, raw statistical data, reports, and other relevant data. In the scheme, an investigation team needs to investigate each detail in the area, interview for many times to obtain original statistical data, and then give qualitative judgment based on personal experience. The traditional engineering method needs a lot of manpower, material resources and time, the larger the area of the region is, the more time is consumed, the higher the cost is, and the evaluation result depends on personal experience and judgment to a great extent, and the evaluation standard in the investigation team is difficult to subdivide and quantify, so that the high-quality reference opinion is difficult to provide for potential site selection suitable for building the regional energy system. Therefore, the main disadvantage of this method is that it is not suitable for rapid and accurate assessment of large areas.

Secondly, because the data relied on by the method is non-public data obtained by a research team through on-site research of a target area, when the target area changes, the research team needs to research again and collect new data to evaluate the potential of the regional energy system of the new target area. Therefore, another disadvantage of the above method is that it cannot be easily extended to other areas.

Thirdly, the method has no intuitive and convenient interactive means for helping the user to understand the analysis result, so that the user cannot quickly understand and make a decision.

Therefore, there is a need to develop a new potential evaluation tool for regional energy systems.

Disclosure of Invention

The invention aims to solve the technical problem of helping a user quickly and reliably screen out potential areas which have higher engineering potential and are suitable for building regional energy systems (particularly regional refrigeration/heating systems) aiming at regions with larger areas.

To this end, embodiments of the present application provide a method of assessing the potential of building a district cooling/heating system at a target area, the method comprising the steps of: A) receiving a target area input by a user; B) receiving one or more areas divided into a target area by a user; C) receiving a refrigeration/heating demand fraction and a construction feasibility fraction distribution ratio input by a user; D) if the user uses the automatic meshing tool when the target region is divided in step B, extracting pre-calculated cooling/heating demand scores and construction feasibility scores of the one or more regions from a pre-established database for the target region using a pre-established index; E) if the lasso tool is used when the user divides the target region in the step B, extracting energy use requirements and construction related data of the one or more regions and national design specification data from the database by using a pre-established index, extracting a building refrigeration/heat supply requirement evaluation model and a construction feasibility evaluation model matched with the target region from an algorithm library established in advance for the target region, and respectively calculating refrigeration/heat supply requirement scores and construction feasibility scores of the one or more regions by using the models based on the data; F) and C, performing weighted average calculation on the refrigeration/heating demand fraction and the construction feasibility fraction obtained in the step D or E based on the distribution ratio of the refrigeration/heating demand fraction and the construction feasibility fraction received in the step C to obtain the engineering potential fraction of the construction area refrigeration/heating system of the one or more areas, and displaying the engineering potential fraction of the one or more areas to users.

In the present application, the term "region" refers to a block, a collection of blocks, and even the country itself, which is divided from the territory of a country according to a certain standard (e.g., a geographic standard, an economic standard, an administrative division standard, etc.), and the block may be, for example, an administrative division such as a country, a town, a city, a county, a province, a district, a union, a state, etc., a division of a north China area, a east China area, a Central China area, a south China area, etc., or an economic division such as a northeast China economic division, an east economic division, a middle economic division, a west economic division, etc. It should be understood that the above list is not exhaustive and that other possibilities exist.

In the present application, the term "potential" is used to characterize whether a certain area is suitable for building a district cooling/heating system, the greater the potential, the more suitable it is for building, specifically including but not limited to engineering potential, profitability potential and energy saving and emission reduction potential. In the embodiment of the invention, the engineering potential of a certain area is evaluated from two dimensions of the refrigerating/heating requirement of the area and the construction feasibility of constructing a refrigerating/heating system in the area; assessing the profitability potential of a region based on the cost of constructing and operating the regional refrigeration/heating system assembly in the region; and evaluating the energy saving and emission reduction potential of a certain area based on the reduction degree of the urban heat island effect by the regional refrigeration/heating system of the area (only applicable to the regional refrigeration system) and the reduction amount of the caused carbon emission.

In the above evaluation method, since the target area is divided into grids of different sizes in advance, and the refrigeration/heating demand score and the construction feasibility score corresponding to the area represented by each grid are calculated in advance and stored in the database, when a user selects one of preset gears representing the grid size to divide the grid into the target area and requests to calculate the engineering potential score of the area represented by each grid at the gear, the required engineering potential score can be obtained by performing weighted average calculation on the refrigeration/heating demand score and the construction feasibility score directly retrieved from the database based on the distribution ratio of the refrigeration/heating demand score and the construction feasibility score input by the user. Meanwhile, intermediate data required by calculation under lasso division is stored in the database, and various models (used for replacing an evaluation method depending on personal experience) required by calculation under lasso division are stored in the algorithm library in advance, so that when a user utilizes a lasso tool to define one or more regions in a target region and requests to calculate the engineering potential score of each region, the corresponding models only need to be extracted from the algorithm library, and the engineering potential score of each region can be quickly and accurately calculated according to the required intermediate data extracted from the database. The method greatly saves the time for a user to wait for the calculation result, improves the reliability of the calculation result, and can help the user quickly and reliably screen out the potential area which has higher engineering potential and is suitable for building the regional refrigeration/heating system aiming at the region with larger area, thereby meeting the requirements of the user (such as colleges and universities and construction units) paying attention to the engineering potential.

In addition, the method establishes a quantitative and standardized scoring system, and enables users to intuitively feel the engineering potential difference of different areas through the difference of scores. Moreover, the method simplifies the input of the user, the user only needs to input the distribution ratio of the refrigeration/heating demand fraction and the construction feasibility fraction after selecting the target area, the area to be evaluated is selected by an automatic meshing tool or a lasso tool, and the rest is automatically finished by the system. Both aspects are rendered user friendly without relevant professional background.

In some embodiments of the present invention, the above method further comprises the steps of: G1) if an automatic meshing tool is used when the user divides the target region in the step B, extracting the pre-evaluated profit potential of the one or more regions from the database by using a pre-established index; H1) if the lasso tool is used when the user divides the target region in step B, extracting a cooling/heating load curve, energy cost data, procurement costs and operating efficiency curves of equipment constituting a regional cooling/heating system for each of the one or more regions from the database using a pre-established index, and calculating a profit potential of the one or more regions based on the data; I1) and displaying the profit potential of the one or more areas to the user.

According to the scheme, the profit potential result under grid division and the intermediate data required by calculating the profit potential under lasso division are stored in the database in advance, so that a user can be helped to quickly and reliably screen out a potential region which has high profit potential and is suitable for building a regional refrigeration/heating system in the region aiming at the region with a large area, and the demand of a user (such as an investor) paying attention to the profit potential is met.

According to some embodiments of the invention, the profitability potential is characterized by a final cost consisting of investment costs and operating costs for building the district cooling/heating system in said one or more zones.

In some embodiments of the present invention, the above method further comprises the steps of: G2) if the user uses an automatic grid division tool when dividing the target region in the step B, extracting the pre-evaluated energy-saving and emission-reduction potential of the one or more regions from the database by using a pre-established index; H2) if the lasso tool is used when the user divides the target region in the step B, extracting a cooling/heating load curve of each building in the one or more regions, a working efficiency curve of equipment forming a regional cooling/heating system and climate data of a typical design day from the database by using a pre-established index, and calculating the energy saving and emission reduction potential of the one or more regions based on the data; I2) and displaying the energy conservation and emission reduction potential of the one or more areas to a user.

According to the scheme, the energy-saving and emission-reducing potential results under grid division and the intermediate data required by calculating the energy-saving and emission-reducing potential under lasso division are stored in the database in advance, so that a user can be helped to quickly and reliably screen out a potential region which has higher energy-saving and emission-reducing potential and is suitable for building a regional refrigeration/heating system in the region aiming at the region with larger area, and the requirement of the user (such as a government) paying attention to the energy-saving and emission-reducing potential is met.

According to some embodiments of the invention, the energy saving and emission reduction potential is characterized by an amount of carbon emission reduction caused by the construction of a district cooling system and/or a degree of mitigation of urban heat island effects in the one or more districts or by an amount of carbon emission reduction caused by the construction of a district heating system in the one or more districts.

According to some embodiments of the invention, the energy usage requirements and construction related data for the one or more regions comprises satellite maps, point of interest data, climate data, building footprint, building height, building category, water location, and greenfield location within the one or more regions; the national design specification data of the one or more regions includes cooling/heating related design criteria, cooling/heating load calculation related parameters applicable to the one or more regions.

Since these data are public data that can be easily acquired from the internet, data obtained by processing the public data with a mathematical formula, or data estimated by machine learning of the public data, the above-described evaluation method can be applied to any region in the world, and has no regional limitation and good extensibility.

According to some embodiments of the invention, the database is built by: determining the boundary of a target area and dividing the target area into a plurality of areas with the same size according to different gears representing the size of a grid by using an automatic grid dividing tool; collecting public raw data in a target region from the Internet, wherein the public raw data comprises a satellite map, interest point data, annual climate data, cooling/heating related design standards and cooling/heating load calculation related parameters; deducing the water body position and the greening position in the area covered by each satellite map from the collected green band, infrared band and near infrared band data in the satellite map by using the normalized vegetation index and the water index, and storing the water body position and the greening position in the database; dividing an area represented by each grid under each gear aiming at the automatic grid by using a construction feasibility evaluation model called from the algorithm library, calculating a corresponding construction feasibility score based on a satellite map of the area, and storing the construction feasibility score into the database; using a building geometric model which is extracted from the algorithm library and consists of a building floor area presumption model and a building height presumption model, presuming the building floor area and the building height of each building in the coverage area of each satellite map from the collected red, green and blue wave band data in the satellite map, and storing the building floor area and the building height into the database; estimating the building type of each building according to the socioeconomic characteristics of the interior and the periphery of each building in the target area extracted from the collected interest point data and the building occupation area and the building height of each building by using the building type estimation model extracted from the algorithm library, and storing the building type in the database; calculating the refrigerating/heating degree days of the target area from the collected annual climate data and storing the refrigerating/heating degree days in the database; calculating a cooling/heating load curve of each building based on the building floor area, the building height, the building type, the cooling/heating degree days of the target area, the cooling/heating related design standard and the cooling/heating load calculation related parameters of each building in the target area by using the building cooling/heating demand evaluation model extracted from the algorithm library, and storing the cooling/heating load curve into the database; and calculating a corresponding refrigeration/heating demand fraction for the area represented by each grid under each gear by using the building refrigeration/heating demand evaluation model of each building, and storing the refrigeration/heating demand fraction into the database.

The database building method gives priority to the response rate of the meshing tool and the lasso tool when calling data. By storing the display data of the grid dividing tool and the intermediate data of the lasso tool, the space requirement is reduced, and meanwhile, the calculation times during calling are reduced, so that the database is overall more portable and efficient.

According to some embodiments of the invention, the public raw data further comprises energy cost data for the target region, the method further comprising the steps of: calculating an operation expenditure of each building based on the collected energy cost data and the calculated cooling/heating load curve of each building, and storing the operation expenditure in the database; collecting the cost of equipment for constructing a regional refrigeration/heating system and the working efficiency curve of the equipment, which are available in a target region, and storing the cost and working efficiency curve into the database; calculating a capital expenditure for building a district cooling/heating system at each of the zones under each of the gears for the automatic meshing based on the cost and operating efficiency curves of the equipment and storing the capital expenditure to the database; based on the operational and capital expenditures, a final cost of building a district cooling/heating system at each gear for that district is calculated for each district under automatic meshing and stored to the database.

In some embodiments of the invention, the method further comprises the steps of: collecting a working efficiency curve of equipment which is purchased in a target area and used for building a regional refrigeration/heating system, and storing the working efficiency curve into the database; collecting climate data for a typical design day for a target area and storing the climate data in the database; and calculating the reduction amount of carbon emission and/or the reduction degree of urban heat island effect caused by building a regional cooling/heating system in each region (only applicable to the regional cooling system) aiming at each region under each gear of automatic grid division based on the working efficiency curve of the equipment and the climate data of the typical design day of the target region, and storing the reduction amount of carbon emission and/or the reduction degree of urban heat island effect in the database.

According to some embodiments of the present invention, calculating a cooling/heating demand score for a region using a building cooling/heating demand assessment model matched to a target region comprises the steps of: extracting a cooling/heating load curve of each building in the area from the database by using a pre-established index, and calculating typical design day time-by-time total cooling/heating load requirements of all buildings in the area; calculating the energy efficiency ratio of a refrigeration/heating system, the utilization rate of a refrigeration/heating unit and the total refrigeration/heating demand amount of the typical design day based on the typical design day hourly total refrigeration/heating load demand; standardizing the energy efficiency ratio of the refrigeration/heating system, the utilization rate of the refrigeration/heating unit and the total refrigeration/heating demand of a typical design day into fractions which are fully divided into N, calculating the average value of the fractions, and taking the average value as the refrigeration/heating demand fraction of the area. Preferably, N is an integer multiple of 10.

Because the energy efficiency ratio of the refrigeration/heating system reflects the operation efficiency of the regional refrigeration/heating station, the utilization rate of the refrigeration/heating unit reflects the return condition of investment equipment, and the typical design daily refrigeration/heating demand total amount of a region reflects the potential energy demand total amount (potential cold sale/heat profit) of the region, the three indexes more accurately reflect the efficiency and the investment economy of the regional refrigeration/heating system based on the potential regional energy demand curve attribute, and the system efficiency and the investment economy are most concerned by various stakeholders when evaluating the energy demand potential of the regional energy system. The scores obtained by averaging the three indexes after standardization can well represent the refrigeration/heating demand of one area, and users without relevant background knowledge can easily understand the scores of different areas to be visually compared.

According to some embodiments of the present invention, the construction feasibility assessment model matched with the target region calculates the construction feasibility score of the one or more regions based on the satellite map of the region.

According to some embodiments of the present invention, a construction feasibility assessment model matched with a target region is obtained by: preparing a satellite map data set of the region scale of the region with the same type as the target region; randomly selecting two satellite images from the satellite image data set to be compared with an expert, selecting a satellite image which represents a region more suitable for building a regional refrigeration/heating system from the two satellite images by the expert, and repeating the step until the preset times are reached; calculating construction feasibility scores of the areas represented by each satellite image according to the comparison result of experts; calculating the volume ratio, the building category ratio, the vegetation coverage rate, the water body coverage rate and the road width of the area represented by each satellite map; carrying out nonlinear fitting modeling on the volume ratio, the building category ratio, the vegetation coverage, the water body coverage and the relation between the road width and the construction feasibility fraction of the corresponding area of the area represented by the satellite map to obtain an initial evaluation model; training an initial evaluation model by using a first preset number of satellite images, enabling the initial evaluation model to learn the volume ratio, the building category ratio, the vegetation coverage, the water body coverage and the relation between the road width and the construction feasibility score of the corresponding area of each satellite image, and automatically adjusting the parameters of the model; and carrying out construction feasibility evaluation on a second preset number of satellite images which are not learned by the adjusted evaluation model, comparing the construction feasibility score of the area represented by each satellite image with the construction feasibility score of the same satellite image obtained based on the evaluation of an industry expert to verify the accuracy of the evaluation model, repeating the training step if the accuracy does not reach an expected value, and storing the adjusted evaluation model into the algorithm library as a construction feasibility evaluation model matched with a target area if the accuracy does not reach the expected value.

The trained and verified construction feasibility evaluation model can accurately and quickly give the construction feasibility score of an area based on a satellite map (which is public data) of the area.

According to some embodiments of the invention, the building footprint inference model is a deep learning model obtained by: preparing a satellite map training set containing building occupation position labels and red, green and blue wave bands; designing a coder decoder structure (such as a residual error network) to perform semantic segmentation on the satellite image; designing a loss function based on the building boundary and the building floor space shape to represent the difference between the existing model and an ideal state; acquiring a deep learning model to be trained, selecting a satellite map from a training set, training the deep learning model to predict the building floor area of a building contained in the satellite map, calculating a loss function, adjusting each parameter of the deep learning model through negative feedback, and repeating the step until the loss function can not be reduced any more; and taking the deep learning model obtained when the loss function can not be reduced any more as a building floor area conjecture model, and storing the model into the algorithm library.

According to some embodiments of the invention, the building height inference model is a deep learning model obtained by: preparing a digital surface model containing height information and a satellite map training set of red, green and blue wave bands; designing a coder decoder structure (such as a refining network), and converting input satellite map data into data containing predicted height; designing a loss function based on the building height to represent the difference between the existing model and the ideal state; acquiring a deep learning model to be trained, selecting a satellite map from a training set, training the deep learning model to predict the building height of a building contained in the satellite map, calculating a loss function, adjusting each parameter of the deep learning model through negative feedback, and repeating the step until the loss function can not be reduced any more; and taking a deep learning model obtained when the loss function can not be reduced any more as a building height presumption model, and storing the model into the algorithm library.

The deep learning model for estimating the building floor area and height can realize very high calculation precision and granularity.

Embodiments of the present invention also provide a method of optimizing the boundaries of a zone suitable for building a district cooling/heating system, the method comprising the steps of: a) receiving a target area input by a user; b) receiving one or more target areas selected by a user in a target area; c) receiving a refrigeration/heating demand fraction and a construction feasibility fraction distribution ratio input by a user; d) performing a method of assessing the potential of building a district cooling/heating system at a target site as described above to obtain a project potential score for the one or more target districts; e) fine-tuning the boundaries of the one or more target regions by automatically adding or subtracting sub-regions, resulting in new one or more target regions; f) repeating step d, and calculating the engineering potential scores of the new one or more target areas; g) comparing the engineering potential score of the new one or more target regions to the engineering potential score of the one or more target regions before adjustment; h) and if the engineering potential score of the new one or more target areas is larger than the engineering potential score of the one or more target areas before adjustment, repeating the steps e, f and g, and otherwise, displaying the boundary of the new one or more target areas before the last adjustment as an optimized boundary to the user.

The method identifies the boundary of the area with higher engineering potential score by performing automatic iteration on the boundary of the target area which is preliminarily selected by the user and is suitable for building the regional refrigeration/heating system, thereby helping the user to quickly and accurately screen out the site of the regional refrigeration/heating system.

Embodiments of the present invention also provide a computer readable medium having stored thereon a computer program executable by a processor to implement a method as described above, and a database and a library of algorithms for use in a method as described above.

Embodiments of the present invention also provide a system comprising a memory having stored thereon a computer program executable by the processor to implement the method as described above, and a database and algorithm library for use in the method as described above, and a processor.

Advantageously, the system further comprises a human-machine interface for receiving input from a user and presenting output from the system to the user. For example, the human-computer interaction interface can be arranged on a touch screen of a mobile terminal (such as a mobile phone and a tablet computer), so that a user can easily and conveniently perform potential site selection screening work at any time and any place. The human-machine interface may also be provided on a conventional computer display or any other suitable device.

Advantageously, the memory and processor are located in a cloud server (e.g. the Alice cloud). The method is realized by utilizing the more portable cloud server and developing the webpage application program which can calculate all the work on the cloud, so that the time cost and the labor cost which are consumed for building the local server are greatly reduced, and the method can help a user to complete the screening of the potential site selection of the regional refrigeration/heating system in a large area (such as a city) quickly and efficiently at very low cost.

Drawings

The present invention will be described in further detail below with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are solely for purposes of illustration and are not intended as a definition of the limits of the invention. The order of the various steps shown in the figures is merely exemplary, and they may be performed in an order different than that shown.

Fig. 1 is a flow chart of a method of assessing the potential of building a district cooling/heating system in one or more regions of a target district according to an embodiment of the present invention.

Fig. 2 is a method of optimizing the boundaries of a zone suitable for building a zone cooling/heating system according to an embodiment of the present invention.

Fig. 3a to 3c respectively show examples of boundaries obtained by using an automatic meshing tool, a lasso meshing tool, and a boundary automatic growing tool according to an embodiment of the present invention.

Fig. 4 is a flow chart illustrating steps for building a database for a target region according to an embodiment of the present invention.

FIG. 5 is a flow chart illustrating steps for building an algorithm library for a target region according to an embodiment of the present invention.

FIG. 6 shows public data used by the evaluation method according to an embodiment of the invention.

Fig. 7 is a data pipeline diagram for building a database for a target region according to an embodiment of the present invention.

FIG. 8 is a diagram of a data pipeline when a database and an algorithm library are invoked according to an embodiment of the present invention.

FIG. 9 is a flowchart illustrating steps for building a geometric model of a building according to an embodiment of the invention.

FIG. 10 is a flowchart illustrating steps for building a building category inference model according to an embodiment of the present invention.

Fig. 11 is a schematic diagram of a model for calculating a cooling load of a building according to an embodiment of the present invention.

Fig. 12 is a flowchart showing steps of building a construction feasibility evaluation model according to an embodiment of the present invention.

Figure 13 is a flow chart illustrating steps for calculating the final cost of building and operating a district cooling/heating system in a district according to an embodiment of the present invention.

Figure 14 is a flow chart showing steps for calculating the extent to which a refrigeration system can be slowed down in an area to an urban heat island effect in accordance with an embodiment of the present invention.

Fig. 15 is a flowchart illustrating steps for calculating the amount of carbon emissions reduction caused by building a district cooling/heating system in a district according to an embodiment of the present invention.

FIG. 16 is a schematic block diagram of a computer system implementing the above-described method according to an embodiment of the present invention.

Detailed Description

Embodiments of the present invention provide a method and system for assessing the potential for building a district cooling/heating system in one or more regions of a target area. Fig. 1 shows a flow chart of the method 100, and fig. 16 shows a schematic block diagram of a system 50 for implementing the method. In this embodiment, the target area is a city, such as Shanghai, it being understood that the target area may be any other geographical area that is artificially divided by certain criteria. The method 100 enables a user to know the engineering potential size, optional profit potential and energy saving and emission reduction potential size for building the regional refrigeration/heating system in different regions of a target region within a short time (several seconds), thereby quickly and accurately screening one or more high-potential candidate regions of the target region suitable for building the regional refrigeration/heating system, and providing important guidance for site selection decisions of project investors and planners of the regional refrigeration/heating system. As described in the summary section, in the present application, the engineering potential is evaluated from two dimensions, cooling/heating demand and construction feasibility, and the profitability potential of a region is evaluated based on the total cost of constructing and operating the cooling/heating system of the region in the region; and evaluating the energy saving and emission reduction potential of a certain area based on the reduction degree of the urban heat island effect by the regional refrigeration/heating system of the area (only applicable to the regional refrigeration system) and the reduction amount of the caused carbon emission.

The evaluation method 100 is described in detail below with reference to fig. 1.

The method 100 begins at step 101, and then in step 102, a target region of interest (e.g., Shanghai) input by a user at a front end of the system 50 (which may be in the form of a web-based application or software or a mobile-device application-based human-machine interface, for example) is received, and in response to the input, the system presents a map of the target region to the user at the front end.

Then, it is determined in step 103 whether the user intends to use the lasso tool (i.e. a tool that allows the user to freely define any enclosed area 14 having a regular or irregular polygonal shape in the target area, see fig. 3b), and in step 109, an allocation ratio between the regional energy demand (cooling/heating demand in this embodiment) and the fraction of the construction feasibility of the regional energy item (regional cooling/heating system in this embodiment) inputted by the user at the front end of the system is received. Alternatively, the user may embody the respective importance of the energy demand and the construction feasibility by dragging the importance slider or inputting the importance score, and the system calculates the distribution ratio.

If the determination in step 103 is negative, then the process goes to steps 105 and 106, and receives one or more boundaries that are input by the user using the automatic meshing tool, and these boundaries define one or more areas 12 (see fig. 3a), where the automatic meshing tool allows the user to divide the target area into a plurality of grids (i.e., areas) with the same size and the same regular shape (such as a square or a rectangle) according to a certain gear, the system can preset several gears, different gears represent different grid sizes (in different gears, the target area is divided into tens, hundreds, thousands or even tens of thousands of areas with the same size), and a certain gear can be set as a default gear (i.e., a gear that is the default gear of the system when the user does not select).

Next, in step 120, the pre-calculated cooling/heating demand score and construction feasibility score of the one or more zones are extracted from the database 20 previously established for the target area using the pre-established index. Subsequently, in step 122, based on the distribution ratios of the cooling/heating demand and the construction feasibility scores received in step 109, a weighted average calculation is performed on the cooling/heating demand scores and the construction feasibility scores obtained in step 120 to obtain engineering potential scores of the construction area cooling/heating systems of the one or more areas, and the engineering potential scores are returned to the front end in step 123 to be displayed to the user in an intuitively understandable form, for example, the engineering potential score levels of the one or more areas can be presented in a color gradient on a map of the target area, which allows the user to quickly and efficiently screen out areas with high engineering potential and perform further evaluation and investigation on the areas with high engineering potential. It should be appreciated that in addition to the engineering potential score, the system may also return to the front end other characteristic information that may be of interest to the user of each area. The evaluation method 100 then ends at step 124.

Optionally, the method 100 may further extract the pre-evaluated profit potential and energy saving and emission reduction potential of the one or more regions from the database 20 by using the pre-established index in step 117, and return the two potentials to the front end to be displayed to the user in step 123.

When a user uses the preset gears of the system to automatically divide the grids of a target area, the system calculates the refrigeration/heating demand fraction, the construction feasibility fraction, the profit potential and the energy-saving and emission-reducing potential of the area represented by the grids in advance for all the grids in each gear and stores the calculated fractions in the database, so that when the user requests to check the engineering potential fractions of all the areas in a certain gear, only the weighted average calculation of the last step needs to be performed, and when the user requests to check the profit potential and/or the energy-saving and emission-reducing potential of all the areas in a certain gear, only the calculation needs to be directly called out from the database, and therefore the user can receive the result fed back by the system in a very short time. In one example, when the user selects to divide shanghai into a plurality of square grids with a side length of 4 kilometers, the engineering potential scores of the areas represented by the grids can be seen after one second or two seconds.

If the determination in step 103 is yes, then proceed to step 104, where in step 104, one or more boundaries input by the user using the lasso tool are received, the boundaries defining one or more regions. Next, in step 107, energy usage demand and construction related data, national design code data, energy cost data within the one or more regions are extracted from the database 20 using the pre-established index. Next, a building energy model (in this embodiment, specifically, a building cooling/heating demand evaluation model) and a construction feasibility evaluation model matching the target region are extracted from the algorithm library 30 established in advance for the target region in steps 110 and 111, respectively, and an energy demand (in this embodiment, specifically, a cooling/heating demand) score and a construction feasibility score of the one or more regions are calculated using the models based on the energy usage demand and construction-related data and the national design specification data, respectively. Subsequently, in step 112, the cooling/heating demand score and the construction feasibility score calculated in steps 110, 111 are weighted-averaged based on the distribution ratios of the cooling/heating demand and construction feasibility scores received in step 109 to derive a project potential score for the construction zone cooling/heating system of the one or more zones, and the project potential score is returned to the head-end in step 118 for presentation to the user in an intuitively understandable manner. Subsequently, the method 100 ends the evaluation in step 119.

In this embodiment, the energy usage requirements and construction related data for the one or more regions includes satellite maps, point of interest data, climate data, building footprint, building height, building category, water location, and greenfield location within the one or more regions; the national design specification data of the one or more regions comprises design standards related to cooling/heating (such as the relevant standards specified in the Chinese national standard GB 50736-2012) and cooling/heating load calculation related parameters (such as the relevant parameters specified in the Chinese national standard GB 50736-2012) applicable to the one or more regions; the energy cost data for the one or more regions includes electricity and gas costs for the region. Generally, all of the above data is public and available on the internet for any target region, and therefore, the method of assessing engineering potential can be applied to any region worldwide.

Alternatively, the method 100 may further extract a cooling/heating load curve, energy cost data, procurement costs and operating efficiency curves of equipment constituting the district cooling/heating systems from the database 20 using the pre-established index in step 108, then calculate final costs consisting of investment costs and operating costs for constructing the district cooling/heating systems in the one or more districts based on the data in step 113, estimate a profit potential for constructing the district cooling/heating systems in the one or more districts based on the final costs in step 115, and return the profit potential to the front end in step 118 for presentation to the user.

Optionally, the method 100 may further extract a cooling/heating load curve of each building in the one or more zones, an operating efficiency curve of equipment constituting the zone cooling/heating system, typical design day climate data from the database 20 using the pre-established index in step 108, then calculate a carbon emission reduction amount and/or a reduction degree of the urban heat island effect caused by building the zone cooling system in the one or more zones or a carbon emission reduction amount caused by building the zone heating system in the one or more zones based on these data in step 114, evaluate an energy saving and emission reduction potential of the cooling/heating system in the one or more zone building zones based on the carbon emission reduction amount and/or the reduction degree of the urban heat island effect in step 116, and return the energy saving and emission reduction potential to the front end in step 118, and displaying to the user.

In the case that the user uses the lasso tool, the one or more regions are user-defined, but not preset by the system, so that the refrigeration/heating demand fraction and the construction feasibility fraction, the profitability potential and the energy saving and emission reduction potential corresponding to the regions cannot be stored in the database in advance, and on-site calculation is required, so that the time required for feeding back the result to the user is slightly longer than that in the case of grid division. However, the calculation process is also quite fast, since the intermediate data required for the calculation are stored in advance in the database. The user's wait time is related to the size and number of zones he or she has selected using the lasso tool. In one example, the user customizes an area of 9 square kilometers with the lasso tool and waits approximately 1 second to see the engineering potential score for the system to return to the front end.

From the above description, it can be seen that the method according to the embodiment of the present invention can meet different user requirements. A typical application of the method is that a user first roughly screens an area with a large area (such as a city) by using a meshing tool to find out several potential areas with high potential scores, and then, in order to further understand the potentials of the areas, the user selects meshing with different gears and different cooling/heating demands and construction feasibility score distribution ratios for each area, and compares the potentials of the areas on different scales. After the above operation is performed on each potential region, the user can select several candidate regions. Since the candidate area is a regular polygon (usually a square or a rectangle) automatically mesh-divided, its boundary does not necessarily conform to the user's desire. In this case, the user may use the lasso tool to self-define the appropriate boundaries. Through a previous comparison of the potential at different scales, the user is generally able to quickly find a suitable road as a new boundary. By performing steps 104, 107, 110, 111, 112 and/or 104, 108, 113, 115 and/or 104, 108, 114, 116 of the above method, the user can know the engineering potential size and/or the profitability size and/or the energy saving and emission reduction potential size of the area defined by the customized new boundary and other related characteristic information, which can provide important references for the location decision of project investors, planners, constructors and approvers of the area cooling/heating system.

There is another user need to optimize the boundary of the approximate target region selected by the user so as to obtain the region with the maximum potential. FIG. 2 illustrates an optimization method 200 that can optimize the engineering potential of a region, according to an embodiment of the invention. The method begins at step 201, and then at step 202, the coverage of an optimization area is identified, and then at step 203, one or more target areas to be optimized are received as input by a user. In step 204, the engineering potential score for the one or more target areas is calculated by performing the relevant steps in the above-described assessment method 100. Subsequently, in step 205, the boundaries of the one or more target areas are fine-tuned by automatically adding or subtracting sub-areas (e.g., adding or subtracting buildings or blocks) to obtain new one or more target areas, and an engineering potential score is calculated for the new one or more target areas by performing the relevant steps in the evaluation method 100. In step 206, the engineering potential scores of the new one or more target regions are compared with the engineering potential scores of the one or more target regions before fine tuning, if the former is greater than the latter, step 205 is repeated, otherwise, step 207 is proceeded, and the boundary before the last fine tuning of the new one or more target regions is displayed to the user as the optimized boundary. The boundary optimization method 200 then ends at step 208.

In the boundary optimization method 200, the system can dynamically evaluate the engineering potential increase or decrease of the area per adding or subtracting building or block so as to optimize the boundary of the area with greater engineering potential on the basis of the target area initially selected by the user, namely, the dynamic growth of the boundary is realized. Fig. 3c schematically shows the area 16 defined by the boundary of such a dynamic growth.

Fig. 4 shows a process of establishing the database 20 used in the above-described evaluation method 100. The library construction method 300 begins at step 301. Subsequently, in step 302, a target area (for example, Shanghai) for which a database is to be built is selected and the target area is divided into a plurality of regions of the same size by using an automatic meshing tool according to different gears representing the size of the mesh. Next, in steps 303, 308, 310, 314, respectively, satellite map data, point of interest data, energy related national design specification data (including cooling/heating related design criteria, and cooling/heating load calculation related parameters), and annual climate data within the target region are collected from the internet. As shown in fig. 5, these data are public data that are publicly available on the internet. Because the method does not depend on a special database (usually private) of a specific region, the database building method according to the embodiment of the invention is not limited by the region, has wide adaptability and can be easily popularized to other regions in the world. It should be understood that there are many data disclosed on the internet, and the data used in the method of the present invention is carefully selected by the inventor, and can be obtained for general areas, and after being processed, the data can more accurately characterize the energy demand situation of each building in the target area and the construction feasibility of regional energy projects.

In step 304, the water body position and the greening position in the area covered by each satellite map are estimated from the collected green band, infrared band and near infrared band data in the satellite map by using the normalized vegetation index and water index, and are stored in the database 20. In step 305, a construction feasibility evaluation model is extracted from the algorithm library 30, and an area represented by each grid in each gear is divided for the automatic grid using the model, a corresponding construction feasibility score is calculated based on a satellite map of the area, and the construction feasibility score is stored in the database 20, followed by ending in step 306.

In step 307, a building geometry model is extracted from the algorithm library 30, and from the red, green and blue band data in the satellite maps collected in step 303, building geometry information (building footprint and building height) of each building in the area covered by each satellite map is inferred using the model, and the building geometry information is stored in the database 20.

In step 309, a building category presumption model is extracted from the algorithm library 30, and the model is used to presume the building category of each building and store the building category in the database 20 according to the socioeconomic characteristics of the interior and periphery of each building in the target region extracted from the point-of-interest data collected in step 308, and the building occupied area and building height of each building presumed in step 307. A point of interest (POI) is a term in a geographic information system, and generally refers to all geographic objects that can be abstracted as points, especially some geographic entities closely related to people's lives, such as schools, banks, restaurants, gas stations, hospitals, supermarkets, and the like. The main purpose of the interest points is to describe the addresses of the things or events, so that the description capability and the query capability of the positions of the things or events can be greatly enhanced, and the accuracy and the speed of geographic positioning are improved. In embodiments of the present invention, points of interest may be used to preliminarily determine building categories for a building, including, but not limited to, office buildings, hospitals, schools, malls, supermarkets, restaurants, hotels, entertainment venues, industrial venues, and the like.

In step 315, based on the annual climate data of the target area collected in step 314, the cooling/heating degree day number of the target area is calculated and stored in the database 20.

In step 311, a building cooling/heating demand evaluation model for each building in the target area is extracted from the algorithm library 30, and a cooling/heating load curve for each building is calculated by using the model based on the building floor area, the building height, the building type, the cooling/heating degree day number, the cooling/heating related design standard, and the cooling/heating load calculation related parameter of each building in the target area, and stored in the database 20.

In step 312, a corresponding cooling/heating demand score is calculated for the area represented by each grid in each gear for the automatic grid division using the building cooling/heating demand evaluation model for each building in the target area, and the cooling/heating demand score is stored in the database 20. Subsequently, the method 300 ends in step 313.

Optionally, the method 300 may also collect energy cost data, such as electricity and gas cost charging criteria, within the target region in step 316; calculating an operation expenditure of the cooling/heating system in the region operation region for the region represented by each grid in each gear for the automatic meshing based on the energy cost data and the cooling/heating load curve of each building calculated in step 311 in step 317; in step 318, collecting the cost of the equipment for constructing the district cooling/heating system and the operation efficiency curve of the equipment, which are available in the target district, and storing the cost and operation efficiency curve in the database 20; in step 319, calculating capital expenditures for building a district cooling/heating system for the region represented by each grid at each gear for the automatic meshing based on the cost and operating efficiency curves of the plant; in step 320, calculating the final cost of building and operating the district cooling/heating system in the district represented by each grid in each gear for the automatic meshing based on the operating and capital expenditures, and storing the final cost in the database 20; the method then ends in step 321.

Optionally, the method 300 may also collect climate data for a typical design day for the target region in step 322 and store the climate data to the database 20; calculating an amount of carbon emission reduction caused by building the district cooling/heating system in the district for each of the zones represented by each of the grids under each of the gears by the automatic meshing, based on the operating efficiency curve of the equipment for building the district cooling/heating system, which is available in the target district, collected in step 318, and the climate data of the typical design day collected in step 322, and storing the amount of carbon emission reduction in the database 20; the method 300 then ends in step 324.

Optionally, the method 300 may further calculate a degree of mitigation of the urban heat island effect by the area building district refrigeration system for the area represented by each grid at each gear based on the operating efficiency curves of the equipment available for construction of the district refrigeration system for the target area collected in step 318 and the typical design day climate data collected in step 322, and store the degree of mitigation of the urban heat island effect to the database 20; the method 300 then ends in step 326.

A method 400 of building an algorithm library for a target region according to an embodiment of the present invention is described below with reference to fig. 5.

The method 400 begins at step 401, and then at step 402, collects satellite map data and corresponding elevation and footprint annotation data for the target area, and at step 406, builds a building geometry model based on these data, and stores the building geometry model to the algorithm repository 30. Building geometry data (e.g., floor area and height) and corresponding building category information for each building in the target area are collected at step 403, and a building category model is built based on the data and information and stored to the algorithm library 30 at step 407. Energy-related national design code data for the target region is collected in step 404, and a building energy demand (cooling/heating demand in this embodiment) evaluation model is built based on the data in step 408 and stored in the algorithm library 30. Satellite map data of the target region and data for comparison in construction feasibility by corresponding experts are collected in step 405, a construction feasibility evaluation model is established based on the data in step 409, and the construction feasibility evaluation model is stored in the algorithm library 30. The method 400 then ends at step 410.

FIG. 7 is a data pipeline diagram corresponding to the library construction method 300. How this data pipe implements the above method is briefly described below:

step 1: and after the database interface acquires the data collection and analysis request of the target area, the task is distributed to the engine.

Step 2: the engine subdivides the request according to different data types and sends the request to a schedule waiting response.

And 3, step 3: and the schedule organizes the request list and sends the first task request in the list to the engine.

And 4, step 4: the engine acquires a task request from the schedule and sends a data capture request to the crawler script of the corresponding data type.

And 5, step 5: the crawler script captures data from the internet, performs geographic coordinate conversion, data screening and simplification processing on the data, and returns the data, log information and the like to the engine.

And 6, step 6: after receiving the data capture result, the engine submits a characteristic analysis request to the algorithm library according to the data type, and simultaneously reports the data capture result to the library interface. In the embodiment of the invention, the algorithm in the algorithm library can particularly calculate the refrigerating/heating degree days according to the temperature historical data of the target region about one year and the use habits of local equipment; the building occupation area and the building height of each building in the area covered by each satellite image can be estimated from the collected satellite image data by using a machine deep learning model; the vegetation coverage position/water body coverage position in the coverage area of each satellite map can be respectively estimated through the near infrared band and the red light band/green light band by utilizing the collected satellite map data; the building category can be inferred through machine learning using building footprint and building height data inferred from satellite map data in combination with POI data. These calculated or inferred results are hereinafter collectively referred to as feature data.

And 7, step 7: and after the feature data is calculated, the algorithm library returns the feature data and the analysis result to the engine.

And 8, step 8: the engine arranges the analyzed data into table data to be stored in the server, and simultaneously reports the result to the timetable and the library interface to wait for response.

Step 9: and repeating the steps 3 to 8 until the schedule is empty.

FIG. 8 is a data pipeline diagram corresponding to the evaluation method 100. How this data pipe implements the above method is briefly described below:

step 1: the user selects one or more regions in the target area at the front end via a meshing or lassoing tool. After the front end analyzes the area selected by the user, the front end converts the area into an Http request and sends the Http request to the server to start waiting for a response. The server receives the user request from the front end, and sends the request to the library interface to start waiting for response.

Step 2: the library interface parses out the specific number and location of regions within the request, sending it to the engine.

And 3, step 3: the engine considers the area and location of the regions and determines whether each region is suitable for operation (the larger the area of the selected region, the longer the time it takes to compute).

And 4, step 4: and the timetable adds the new request table into the existing task request table, if no task request is operated at present, the new task request is sent to the engine from the request table, and otherwise, the engine is waited to finish the task response.

And 5, step 5: the engine retrieves the building data and the related feature data within the boundary from the database by a search algorithm using a pre-established index according to the region targeted by the task request.

And 6, step 6: and the engine sends the data called out from the database to the algorithm library and waits for a regional energy characteristic analysis request.

And 7, step 7: after the feature data calculation is completed, the algorithm library returns the potential score and other feature data that may be of interest to the user to the engine.

And 8, step 8: the engine judges whether all the requests sent by all the library interfaces are finished, and if the requests are finished, the engine integrates and returns all the task request results to the library interfaces and informs the schedule that the current task is finished. If all tasks are not finished, the schedule is informed to send a next task request, and the steps 4 to 8 are repeated until all tasks are finished.

Step 9: after the analysis is completed, the library interface arranges the data sent by the engine into a data format transmitted by commonly used internet files such as json files and the like and transmits the data format to the front end through an Http request. And the front end displays the potential score and other characteristic data possibly interested by the user to the user according to the interface style after receiving the Http response.

Fig. 9 illustrates a modeling process 500 for the building geometry model referred to in the above library construction method 300, wherein the building geometry model is composed of a building footprint inference model and a building height inference model, both of which are deep learning models. The process starts at step 501, and then in step 502, a satellite map training set containing building floor space position labels and red, green and blue bands is prepared for a building floor space presumption model, and a digital surface model containing height information and a satellite map training set containing red, green and blue bands is prepared for a building height presumption model.

In step 503, the encoder decoder structure (e.g., residual network) is designed to perform semantic segmentation on the satellite image; in step 504, a loss function is designed based on the building boundaries and the building footprint shape (e.g., a maximum distance between the predicted building footprint and the real building footprint and an intersection ratio) to characterize the gap between the existing model and the ideal state; obtaining a deep learning model to be trained in step 505; selecting a satellite map and a building floor space label from the training set in step 506, training the deep learning model to predict the building floor space of the building contained in the satellite map, and calculating the result of a loss function; in step 507, it is determined whether the result of the loss function can no longer be decreased, and if not, each parameter of the deep learning model is adjusted by negative feedback, and step 506 is repeated, and if so, the deep learning model at that time is used as the building floor area estimation model.

In step 508, designing a codec structure (e.g., a refining network) to convert the input satellite map data into data containing the predicted altitude; in step 509, a loss function (e.g., mean and variance of the difference between the predicted building height and the actual building height) is designed based on the building height to characterize the difference between the existing model and the ideal state; in step 510, a deep learning model to be trained is obtained; in step 511, selecting a satellite map and a building height label from the training set, training the deep learning model to predict the building height of the building contained in the satellite map, and calculating the result of the loss function; in step 512, it is determined whether the result of the loss function can no longer be decreased, and if not, each parameter of the deep learning model is adjusted by negative feedback, and step 511 is repeated, and if so, the deep learning model at that time is used as the building height estimation model.

Subsequently, in step 513, a building geometric model is built based on the trained building floor area presumption model and building height presumption model, and the building geometric model is stored in the algorithm library 30. Modeling method 500 ends in step 514.

The above-described deep learning model for inferring building footprint and height may perform pixel-by-pixel classification or estimation of satellite images through a codec structure. The encoder can learn texture information, local structure information and object overall information of the image step by step through a plurality of convolution layers and pooling layers to generate a low-resolution characteristic image with semantic features; the decoder may map the low resolution feature image output by the encoder back to the input image size through multiple upsampled and convolutional layers. The difference between the training model and the real data is represented by designing a reasonable loss function, and the accuracy of the model can be continuously improved until the best efficiency of the model is achieved by continuously adjusting the weight of each parameter in the deep learning model by negative feedback.

Fig. 10 illustrates a modeling process 1000 of the building category inference model referred to in the above library construction method 300. The process starts in step 1001, and then in step 1002, a training set for the building class inference model is prepared. Next, in step 1003, socioeconomic characteristics of the interior and the periphery of each building in the target region are extracted from the point-of-interest data, and in step 1004, geometric parameters of the building are extracted from geometric information (building floor area and building height) of each building in the target region. Then, in step 1005, an initial model based on the random forest is created based on the socioeconomic features extracted in step 1003 and the building geometric parameters extracted in step 1004, the initial model is trained by the training set prepared in step 1002, and the trained model is stored as a building type estimation model in the algorithm library 30.

The building energy model (i.e., the building cooling/heating demand assessment model) referred to in step 215 of the above library construction method 300 is described below with reference to fig. 11.

The specifications and standards of different countries have different requirements on the calculation method of the refrigeration load of the building, namely the calculation methods of the transfer relationship between heat and load are different, and the algorithm library according to the embodiment of the invention is internally provided with load algorithms according to the specifications and standards of different countries and can be automatically matched with the algorithms of corresponding countries according to target regions. For example, according to the requirements of the national standard GB50736-2012, the method of calculating the cooling load of the building should use the cooling load coefficient method, and thus when the target region selected by the user is a region in china, the method of calculating the cooling load coefficient in the algorithm library is automatically matched and invoked. Since the target area usually includes a large number of buildings, a large amount of calculation is required to calculate the corresponding cooling/heating load curve for each building, and therefore, in order to reduce the waiting time of users, the model used for calculation needs to be simplified, so as to reduce the amount of calculation and increase the calculation speed.

The following describes how the refrigeration load calculation model according to the embodiment of the present invention simplifies the conventional refrigeration load coefficient method model, taking the target region of china as an example. First, in the refrigeration load calculation model according to the embodiment of the present invention, solar insolation calculation is simplified. Because the orientations of the outer walls of the buildings are different, if the solar illumination intensity of each outer enclosure of each building is calculated, the required calculated amount is in direct proportion to the number of the outer enclosures of the buildings. If a total of ten thousand cuboid buildings are available, at least five ten thousand calculations are required. To reduce the amount of computation, the model according to an embodiment of the invention rounds the orientation of each building to a full value, for example 12.1 degrees north to east is approximately 12 degrees. Before the building cold load operation is carried out, the illumination intensity pre-calculation is carried out on 360 integral azimuth angles and horizontal planes with the azimuth angles of 0-359 degrees for 24 hours (361 times of operation in total). And then when the illumination intensity of the outer enclosure structure is needed in the process of calculating the cold load of the building, the pre-calculated result can be directly used. The computational effort can be reduced by two orders of magnitude by this simplification. Secondly, in the refrigeration load calculation model according to the embodiment of the invention, the heat transfer and indoor heat dissipation of the building enclosures of the same type are simplified. Seem, "Modeling of Heat Transfer in Buildings," University of Wisconsin-Madison,1987 (the contents of which are incorporated herein by reference) proposes a wall Transfer function calculation method, which has high calculation accuracy, but discretizes each wall, writes a state space equation through algebraic operation, and then performs matrix transformation. If only the cold load of individual buildings needs to be solved, the calculation amount of the method is acceptable, and if the transfer function coefficients need to be solved for all buildings in the city, the calculation amount is too large. In order to reduce the amount of computation, in the model according to an embodiment of the present invention, it is assumed that the wall structures of the same building class are similar. For the same type of building, typical wall and roof structures of the type of building are selected for calculating the transfer function coefficients, and the transfer function coefficients of the wall and the roof structures of the type of building are assumed to be the same. Similarly, to simplify the window heat transfer calculations, it is assumed that the heat transfer coefficient and the total solar transmittance are the same for windows of the same type of building. In addition, for the same type of buildings, it is assumed that the personnel density, the heat dissipation of the equipment per unit area and the heat dissipation of the illumination are also equal. Through the simplification, the calculation amount of the model according to the embodiment of the invention is greatly reduced. The inventor tests on a computer configured by i7-4850HQ by using the python language, the calculation time of the hourly cooling load of each building for 24 hours is only about 0.04 second, and the calculation accuracy is relatively good. In addition, compared with the traditional model established completely based on the chinese national standard GB50736-2012, the model according to the embodiment of the present invention has many advantages, including: the model provided by the embodiment of the invention has more flexibility, can calculate the solar illumination intensity in any city and direction angle, and is not limited to eight directions of east, south, west, north, southeast, southwest, northeast and northwest; the model according to the embodiment of the invention is not limited to wall and roof structures, and can be used for carrying out heat transfer calculation on any structure; the model according to the embodiment of the invention can also perform load calculation on buildings with any load curves.

The following describes in detail how the model according to the embodiment of the present invention calculates the cooling load of a building (see fig. 11).

When calculating the cold load, the heat of the building is divided into four parts: (1) radiation heating, including radiation heating caused by sunlight penetrating through glass and indoor heat source; (2) the heat is obtained by convection, which mainly comes from heat obtained by convection caused by an indoor heat source and heat obtained by ventilation of a building; (3) the building envelope gets hot; (4) the illumination gets hot.

For calculating cold load of building caused by different heat sourcesThe model according to an embodiment of the invention uses the transfer coefficient method to calculate the cooling load. The method utilizes z-transform to solve the unsteady heat transfer equation. Wherein, the heat gain q caused by the indoor and outdoor temperature difference and the solar radiation at the time point theta is transmitted through the wall body_e,θCan be obtained from the following formula

Equation 1

The variables in equation 1 are:

a wall area in m²，

t_e,θ-nThe outdoor integrated temperature at time theta-n, in units of c,

q_e,θ-nthe heat gain at time theta-n is calculated from equation 1,

t_rcthe indoor design temperature, in units of,

step size of time in units of s, and

b_n,c_n,d_nwall transfer function coefficients.

In the model, the wall Transfer function coefficients are solved by a state space equation method proposed in the document J.Seem, "Modeling of Heat Transfer in Buildings," University of Wisconsin-Madison, 1987. After the wall structure and the physical characteristics thereof are known, firstly, a one-dimensional Fourier unsteady heat conduction equation is discretized by using a finite volume method, and the discretized equation is converted into a form of a space state equation, which is shown as the following formula:

equation 2

Formula 3 q ═ C · t + D · t_a

The variables in the above formula are respectively:

t is the temperature vector [ t ] of each layer of the wall body of the discretization heat conduction equation₁ t₂ … t_n]^TThe unit is,

is a first derivative vector of the temperature vector t with respect to time,

t_ais a vector t composed of indoor temperature and outdoor integrated temperature_rc t_e,θ]^TThe unit is,

q is the heat flux density received by the inner and outer surfaces of the wall [ q_e q_i]^TIn the unit of W/m²，

A, B, C, D are coefficient matrices of discretized one-dimensional heat transfer equations.

The wall transmission coefficient can be derived through a coefficient matrix of a space state equation, and the specific mathematical derivation refers to the literature J.Seem, "Modeling of Heat Transfer in building," University of Wisconsin-Madison, 1987.

The outdoor integrated temperature in equations 1 to 3 may be calculated as follows:

equation 4

Wherein the variables are respectively as follows,

t_o,θoutdoor dry bulb temperature at time θ, in deg.C

Alpha the absorption coefficient of the outer surface of the wall,

I_t,θthe illumination intensity of the outer surface of the wall body at the time theta is measured in W/m²，

h₀The convection heat transfer coefficient of the outer wall is W/(m)²K)，

Δq_irThe heat flux density of the outer wall surface, the sky and the surrounding environment is W/m²。

The document ASHRAE,1997ASHRAE handbook: fundamentals.Atlanta, GA: ASHRAE,1997 (the content of which is incorporated herein by reference) suggests that for horizontal surfaces

The value-3.9K can be taken and the term can be ignored for vertical surfaces.

The illumination intensity of the outer surface of the wall body in the formula 4 can be calculated by the following formula

Equation 5

Wherein the variables are respectively as follows,

I_Ddirect solar illumination intensity in W/m²，

I_dThe intensity of scattered solar radiation is W/m²，

The angle of inclination of the beta wall body is 90 degrees with the vertical plane outer wall and 0 degree with the horizontal plane roof,

θ_zthe solar altitude angle is set according to the solar altitude,

the angle of incidence of the sunlight theta,

ρ ground reflectance.

Calculation of Solar altitude and Solar incident angle can be found in J.A. Duffee and W.A. Beckman, Solar Engineering of Thermal Processes,4th ed.Hoboken, New Jersey: Wiley, 2013. (the contents of this document are incorporated herein by reference).

Heat flux q into the room through the window_e,θCan be solved by the steady state method as follows

Equation 6 q_e,θ＝U·A·(t_rc-t_o)

Wherein the variables are respectively

U window heat transfer coefficient in W/(m)²K)，

Area of A window in m²，

t_rcThe indoor design temperature, in units of,

t_ooutdoor dry bulb temperature in units of ℃.

And adding the heat gains of all the walls and the windows to obtain the sum, namely the heat gain of the enclosure structure shown in the figure 11.

The convection heat gain of the building is composed of human body convection heat gain and equipment convection heat gain, and the radiation heat gain is composed of human body radiation heat gain, equipment radiation heat gain and solar radiation heat gain through a window. Wherein the heat gain of the sun's radiation through the window can be calculated from the equation

Equation 7 q_s＝SHGC·I_t

Where SHGC is the total solar transmittance of the window.

The heat gain due to the ventilation required for a building can be calculated as follows

Equation 8 q_V＝0.34·n·V_e·(t_rc-t_o)

Wherein the variables are respectively

n number of times of ventilation of building design in unit of h^-1，

V_eVolume of air in the building in m³。

After calculating the radiation heat gain, the convection heat gain, the enclosure heat gain and the illumination heat gain, the building transfer function can be used to respectively obtain the cold load caused by the radiation heat gain, the convection heat gain, the enclosure heat gain and the illumination heat gain, as shown in the following formula

Equation 9Q_i,θ＝v_i,0·q_i,θ+v_i,1·q_i,θ--w_i,1·Q_i,θ-

Wherein the variables are respectively

i type of heat gain, r represents radiant heat gain, c represents convective heat gain, l represents lighting heat gain, e represents enclosure heat gain

q_i,θThe heat gain at the time of theta is,

q_i,θ-the heat gain at the time of theta-time,

Q_i,θ-the cold load at the time theta-is,

v_i,0,v_i,1,w_i,1building transfer function coefficients.

From equation 9, the cooling load Q caused by the heat gain of radiation, the heat gain of the building enclosure and the heat gain of illumination can be obtained_r、Q_eAnd Q_lIs composed of

Equation 10Q_r,θ＝v_r,0·q_r,θ+v_r,1·q_r,θ--w_r,1·Q_r,θ-

Equation 11Q_e,θ＝∑_k＝1(v_e,0q_e,θ,k+v_e,1q_e,θ-,k)-w_e,1Q_e,θ-

Equation 12Q_l,θ＝v_l,0q_l,θ+v_l,1q_l,θ--w_l,1Q_l,θ-

The effect of the convection heating on the building can be considered instantaneous, and therefore, the cooling load caused by the convection heating is the magnitude of the convection heating at that moment.

Equation 13Q_c,θ＝q_c,θ

Adding all the cold loads to obtain the cold load of the building at the theta moment

Equation 14Q_θ＝Q_r,θ+Q_l,θ+Q_e,θ+Q_c,θ

As can be seen from the above formula, the heat gain and the cooling load at the past time point are known when the cooling load is calculated, so the method needs to perform iterative calculation. During calculation, the initial value can be set to zero, the time step can be set to 3600 seconds (1 hour), and the outdoor temperature and the direct sunlight and scattering intensity are set to be periodic functions with the period of 24 hours. It was found through experiments that the hourly cooling load values of the building can converge through seven cycles of iterative calculations (seven days).

The following describes in detail how a model according to an embodiment of the present invention calculates the thermal load of a building (see fig. 11).

The heat load is constituted by heat loss of the enclosure and heat loss due to ventilation. Different from the cold load, the peak value of the heat load occurs at the moment when the heat gain is minimum, so that the heat gain and the heat storage capacity of the building can be not considered when the heat load is calculated, and only a steady-state heat transfer equation needs to be solved. Therefore, the thermal load can be obtained according to the steady state calculation method in the national standard GB 50736-2012. The input required to calculate the thermal load is the area of the outer enclosure structure, its heat transfer coefficient, and the outdoor temperature under the design conditions. For a single building envelope, the heat loss can be calculated according to the calculation method of formula 6. The sum of the heat losses of all the building enclosures is the total building enclosure heat loss Q of the building_TAs shown in the following formula

Equation 15Q_T＝∑_iU_i·A_i·(t_rc-t_o,d)

Wherein the variables are respectively

U_iThe heat transfer coefficient of the enclosure structure i is W/(m)²K)，

A_iArea of enclosure i in m²，

t_rcThe indoor design temperature, in units of,

t_o,dthe outdoor temperature under the design condition is given in units of ℃.

Heat loss due to ventilation required by the building Q_VCan be calculated as follows

Equation 16Q_V＝0.34·n·V_e·(t_rc-t_o,d)

Wherein the variables are respectively

n number of times of ventilation of building design in unit of h^-1，

V_eVolume of air in the building in m³。

The total thermal load Q of the building, i.e. the sum of the two

Equation 17Q ═ Q_T+Q_V

If the hourly heat load value of the building needs to be solved, the heat load can be calculated according to the cold load calculation model.

A construction feasibility evaluation model creation method 600 used in the above-described evaluation method 100 is described below with reference to fig. 12.

The method 600 starts 601, and then in step 602, a satellite map data set of a regional scale of a region of the same type as the target region is prepared; in step 603, randomly selecting two satellite images from the satellite image data set and submitting the two satellite images to an expert for comparison; in step 604, the expert selects a satellite map representing a region more suitable for building a regional refrigeration/heating system from the two satellite maps; in step 605, judging whether the times of expert comparison reaches the preset times, if not, repeating steps 603 and 604, if yes, proceeding to steps 606 and 607, in step 606, calculating the volume ratio, the building category ratio, the vegetation coverage, the water body coverage and the road width of the area represented by each satellite map, and in stepIn step 607, the construction feasibility score Q of the area represented by each satellite map is calculated according to the following formula_i：

Equation 17

Equation 18

Wherein, w_iThe number of times that a representative expert has selected a picture in a pairwise comparison, l_iNumber of times, t, representing the expert not having selected a picture in a pairwise comparison_iRepresenting the times that a user can not judge whether one picture is good or bad with the other picture in the two-to-two comparison.

Equal to when the total number of pictures i exceeds j₁The number of times picture i is preferred,

equal to when picture i is not preferred and the total number exceeds j₂The number of times picture i is not preferred. Equation 18 calibrates equation 17 by adding an average preference rate and removing an average non-preference rate, effectively integrating all pairwise compared picture result information.

Then, in step 608, performing nonlinear fitting modeling on the volume ratio, the building category ratio, the vegetation coverage, the water body coverage and the relationship between the road width and the construction feasibility score of the corresponding area of the area represented by the satellite map to obtain an initial evaluation model; training an initial evaluation model by using a first preset number of satellite images, enabling the initial evaluation model to learn the volume ratio, the building category ratio, the vegetation coverage, the water body coverage and the relation between the road width and the construction feasibility score of the corresponding area of each satellite image, and automatically adjusting the parameters of the model; and performing construction feasibility evaluation on a second preset number of satellite images which are not learned by the adjusted evaluation model, comparing the construction feasibility score of the area represented by each satellite image with the construction feasibility score of the same satellite image obtained based on the evaluation of an industry expert to verify the accuracy of the evaluation model, repeating the training step if the accuracy does not reach an expected value, and storing the adjusted evaluation model into the algorithm library 30 as a construction feasibility evaluation model matched with a target area if the accuracy does not reach the expected value.

In practice, target areas can be classified according to factors such as municipal planning rules, geographic environments and economic development degrees, a corresponding machine learning model is trained and verified in advance for the same type of target areas and stored in a database, and when a user requests to evaluate construction feasibility of one or more areas of the target areas, the corresponding machine learning model is directly extracted from the database to print construction feasibility scores based on satellite maps of the areas.

Referring now to fig. 13, a brief description is provided of how the ultimate cost of building and operating a district cooling/heating system in a district, consisting of the capital expenditure of building the district cooling/heating system in the district, the operating expenditure of operating the district cooling/heating system, and the possible greenery equity reduction, is calculated in accordance with an embodiment of the present invention. The cost calculation method 700 begins at step 701, followed by determining the boundaries of the area to be analyzed at step 702, collecting procurement cost and operating efficiency curves for equipment that may be procured by the area to construct the district cooling/heating system at step 703, and extracting the building cooling/heating load curve for each building within the area from the database 20 at step 704. Next, in step 705, a plurality of different equipment combination schemes are obtained through permutation and combination. In step 707, the quotes for each equipment combination are summed to obtain the initial investment. In the regional energy system project, it is often encountered that the buildings on the demand side are not at the same time, but are gradually added into the range of the regional energy system, in this case, the devices are gradually increased according to the increase amount on the load side, and step 708 is performed to sum the quotes of each new device combination to calculate the subsequent device investment. In step 717, the initial equipment investment obtained in step 707 is added to the subsequent equipment investment obtained in step 708 to calculate the capital expenditure. Meanwhile, in step 706, the operation strategy of each device in a certain combination is preset according to the manual of each device. In step 709, plant operation is simulated on a time-by-time basis according to each operating strategy. The time-by-time energy consumption (i.e., the amount of available power) for each combination of devices is calculated in step 710. In step 712, the electricity consumption is multiplied by the electricity rate of the corresponding period to obtain the corresponding equipment operation cost. Repeating steps 705, 706, 709, 710, 712 to 8760 hours of calculation for the whole year. In step 711, the associated equipment maintenance costs and labor costs are added in percentages at the time points specified in the equipment manual for the refurbishment maintenance and replacement required for the different equipment. In step 713, it is determined whether the device operation policy needs to be optimized, if yes, steps 706, 709, 710, 712 are repeated, otherwise, the process proceeds to step 714. In step 714, it is determined whether the rights and interests of the green license are obtained, and if not, in step 716, the equipment updating and maintenance costs and labor costs obtained in step 711 and the annual operating costs obtained in step 712 are added to obtain the operating expenses. In step 718, the capital expenditure calculated in step 717 is added to the operational expenditure calculated in step 716 to obtain a final cost, which is calculated by the following formula:

totalcost＝argmin(Capex_i+Opex_i)

Capex_i＝N_j*p_j

wherein totalcost is the total cost, Capex_iInitial investment for the ith equipment spread, Opex_iAnd (5) arranging and combining operation expenses for the ith equipment. N is a radical of_jNumber of devices of j type, p_jIs the initial investment of the j-th equipment. c. C_tFor the operation cost of the jth equipment in t hours, c_jequipFor maintenance costs of the jth equipment, c_jlaborIs the labor cost of the jth equipment.

If the determination in step 714 is yes, then a green cost is calculated in step 715 as follows, and then the green cost is charged to the operating expenses in step 716.

A green certificate, i.e., a green electric power certificate (green electric certificate), is a green electric power consumption certificate that can be voluntarily or compulsorily bought in a trading market. In 2017, month 7 and day 1, China formally starts green power certificate subscription work. The green power certificate transaction satisfies the green power consumption requirements of the power consumer. The green electric power certificate transaction system divides green electric power into two different types of commodities, namely a green electric power certificate and the internet electric quantity corresponding to the green electric power certificate. According to the stipulation of 'notice about approval of green certificate of renewable energy resources and voluntary approval of transaction system', 1 green certificate of power corresponds to 1000 kW & lth of green power, and by operating the regional cooling system, a user can add green power cost by paying cold energy use cost, and green power consumption is realized in an aggregated manner. The green electricity purchase cost per kilowatt-hour is calculated as follows:

wherein s is_iThe electricity price of the ith green power on-line, the electricity price of the post of the desulfurization coal-fired unit, r_iThe discount rate of the ith green electric power energy industry, h_iSubsidizing a settlement period for the ith green electric power energy price additional fund, d_iAnd (4) subsidizing additional funds for the electricity price of the ith green electric energy source, and postponing the payment period. Found p_iThe lowest economic selling price of the ith green power certificate. P is to be_iAnd multiplying the cold consumption of each user to obtain the green power purchasing cost of the user.

How to calculate the degree of slowing down the urban heat island effect by building a regional refrigeration system in a region according to an embodiment of the present invention is described below with reference to fig. 14, wherein the degree of slowing down is characterized by comparing the time law and the heat quantity of the air conditioning systems before and after building the regional refrigeration system in the target region to release heat quantity to the urban space. The method 800 begins at step 801, followed by determining the boundaries of a zone to be analyzed at step 803, and collecting the operating efficiency curves of the equipment available to build the district cooling/heating system at step 802. Typical design day time by time refrigeration load demand data for the region is extracted from the database 20 in step 804, and typical design day climate data for the region is extracted from the database 20 in step 805. In step 806, an equipment combination plan using ice/water cold storage is calculated based on typical design day-to-day refrigeration loads for the zone, while in step 807 an equipment combination plan is calculated for cooling all building equipment rooms within the zone without zone refrigeration. In step 808, the operation strategies of the ice/chilled water storage area refrigerating system basic load unit and the ice making unit are optimized according to the ice/chilled water storage device combination scheme in step 806, and then the hourly heat release curve of the ice/chilled water storage area refrigerating system on a typical design day is calculated in step 810 based on the operation strategies. Meanwhile, in step 809, a typical design day hourly heat release curve of each building in the area is calculated according to the equipment combination scheme for cooling all the self-equipment rooms of the buildings in the area without area cooling, and based on this, typical design day hourly heat release curves of all the buildings are calculated in step 811. Then, in step 812, the difference between typical design day-to-day heat release curves for both the zone refrigeration system and the non-zone refrigeration system is calculated and used to characterize the mitigation of the urban heat island effect.

The main contribution of the regional refrigeration system using the ice and water storage technology lies in changing the time law of the heat release from the traditional air conditioning system to the urban space, generally speaking, the continuous high peak load of the air conditioner occurs in the daytime, especially the time point with high outside temperature and large solar load lasts to the next two hours, the regional refrigeration carries out centralized supply to the regional refrigeration demand and uses the ice storage and water storage technology to make ice or cold water at the moment with low night refrigeration demand, the cold storage technology is used for storage and is reused in the daytime, thus most of the heat released to the urban outside space is transferred to the night for release, and the position of the regional refrigeration machine room is generally not in the urban business center with serious high-density building heat island effect, the urban heat island effect is effectively relieved, therefore the slowing of the urban heat island effect is time dimension and cannot be represented by a single numerical value, therefore, the slowing of the urban heat island effect is represented more accurately by the typical design daily heat release quantity time-by-time curve difference before and after the regional refrigeration system for ice/water cold accumulation is established in the region.

A method 900 for calculating the amount of carbon emission reduction caused by building a district cooling/heating system in a district, in which the contribution of the district cooling/heating system to carbon emission reduction is quantified by calculating and comparing the annual carbon emission difference before and after building the district cooling/heating system, according to an embodiment of the present invention will be described with reference to fig. 15. The method 900 begins at step 901, and then at step 903 the boundaries of the area to be analyzed are determined, and at step 902 operating efficiency curves for equipment used to build a regional refrigeration/heating system that is available to the area are collected. In step 904, typical design day time by time refrigeration load demand data for the region is extracted from the database 20. Then, in step 905, an equipment combination plan corresponding to the total district cooling/heating load of the district is calculated, in step 907, a system efficiency curve of the district at different load rates is calculated by combining the equipment work efficiency curve, in step 909, a system efficiency curve of the district cooling/heating system at each hour of the year is calculated according to the hour-by-hour load rate of the district cooling/heating system, then, in step 911, the system efficiency curve is multiplied by the total hour-by-hour load of the system to obtain the electricity consumption power of the district cooling/heating system at each hour of the district, in step 913, the electricity consumption power is multiplied by the carbon emission coefficient of unit electricity consumption to obtain the hour-by-hour carbon emission quantity and the total carbon emission quantity brought by the operation of the district cooling/heating system at the district.

The amount of carbon emission for cooling/heating before the regional cooling/heating system is established in the region is obtained by assuming that each building in the region is supplied with cooling/heating heat by a cooling/heating machine room built in the building and then calculating the amount of carbon emission for operating the machine rooms. Specifically, in step 906, a corresponding equipment combination plan is selected for each building in the cooling/heating unit database, in step 908, the system efficiency curves of the building at different load rates are calculated in combination with the equipment operating efficiency curves, then, in step 910, a time-by-time system efficiency curve of the building all the year is obtained according to the time-by-time load rate of the building, in step 912, the annual hourly system efficiency curve is multiplied by the annual hourly cooling/heating demand to obtain the annual power consumption brought by the cooling/heating of the building, and then in step 914, and multiplying the annual power consumption by the carbon emission coefficient of unit power consumption to obtain the carbon emission caused by the operation of the refrigeration/heating system of the building, and adding the annual hourly carbon emission of all buildings in the target area to obtain the hourly carbon emission and the total carbon emission of the refrigeration/heating before the regional refrigeration/heating system is established in the area.

In step 915, the total carbon emissions before and after the district building district cooling/heating system is subtracted, and the obtained value can represent the contribution of the district cooling/heating system to the reduction of carbon emissions. The method 900 then ends at step 916.

The invention also relates to a computer-readable medium having stored thereon a computer program executable by a processor for implementing the various methods as described above and a database for use in the above method. Computer-readable media include, but are not limited to, hard disks, floppy disks, optical disks, flash memory, RAM, ROM, and the like.

Fig. 16 shows a system 50 for implementing the methods described above, which may be various types of computers or mobile terminals, including a memory 501 and a processor 502, wherein the memory 501 stores a computer program and a database 20 and an algorithm library 30 used in the methods described above, and the computer program can be executed by the processor to call relevant data in the database 20 and relevant models in the algorithm library 30 to implement the methods described above. The system may also include a human-machine interface 503 for receiving user input and presenting the output of the system to the user. Advantageously, a man-machine interface is provided on the touch screen 504, and the user can perform various operations such as input by touch and/or a mouse, a keyboard, etc. The human-computer interface may also be provided on a conventional computer display 505 or any other suitable device. It is to be understood that the memory 501 and the processor 502 may be located in a local server or a cloud server (e.g., Alice cloud) according to actual needs.

The drawings and the foregoing description depict non-limiting specific embodiments of the invention. For the purpose of teaching inventive principles, some conventional aspects have been simplified or omitted. Those skilled in the art will appreciate variations from these embodiments that fall within the scope of the invention. Those skilled in the art will appreciate that the features described above can be combined in various ways to form multiple variations of the invention. Thus, the present invention is not limited to the specific embodiments described above, but only by the claims and their equivalents.

Claims (20)

1. A method of assessing the potential of building a district cooling/heating system in one or more regions of a target area, comprising the steps of:

A) receiving a target area input by a user;

B) receiving one or more areas divided into a target area by a user;

C) receiving a refrigeration/heating demand fraction and a construction feasibility fraction distribution ratio input by a user;

D) if the user uses the automatic meshing tool when the target region is divided in step B, extracting pre-calculated cooling/heating demand scores and construction feasibility scores of the one or more regions from a pre-established database for the target region using a pre-established index;

E) if the lasso tool is used when the user divides the target region in the step B, extracting energy use requirements and construction related data of the one or more regions and national design specification data from the database by using a pre-established index, extracting a building refrigeration/heat supply requirement evaluation model and a construction feasibility evaluation model matched with the target region from an algorithm library established in advance for the target region, and respectively calculating refrigeration/heat supply requirement scores and construction feasibility scores of the one or more regions by using the models based on the data;

F) and C, performing weighted average calculation on the refrigeration/heating demand fraction and the construction feasibility fraction obtained in the step D or E based on the distribution ratio of the refrigeration/heating demand fraction and the construction feasibility fraction received in the step C to obtain the engineering potential fraction of the construction area refrigeration/heating system of the one or more areas, and displaying the engineering potential fraction of the one or more areas to users.

2. The method of claim 1, further comprising the steps of:

G1) if an automatic meshing tool is used when the user divides the target region in the step B, extracting the pre-evaluated profit potential of the one or more regions from the database by using a pre-established index;

H1) if the lasso tool is used when the user divides the target region in step B, extracting a cooling/heating load curve, energy cost data, procurement costs and operating efficiency curves of equipment constituting a regional cooling/heating system for each of the one or more regions from the database using a pre-established index, and calculating a profit potential of the one or more regions based on the data;

I1) and displaying the profit potential of the one or more areas to the user.

3. The method of claim 2, wherein the profitability potential is characterized by a final cost consisting of an investment cost and an operating cost of building the district cooling/heating system in the one or more zones.

4. The method of claim 1, further comprising the steps of:

G2) if the user uses an automatic grid division tool when dividing the target region in the step B, extracting the pre-evaluated energy-saving and emission-reduction potential of the one or more regions from the database by using a pre-established index;

H2) if the lasso tool is used when the user divides the target region in the step B, extracting a cooling/heating load curve of each building in the one or more regions, a working efficiency curve of equipment forming a regional cooling/heating system and climate data of a typical design day from the database by using a pre-established index, and calculating the energy saving and emission reduction potential of the one or more regions based on the data;

I2) and displaying the energy conservation and emission reduction potential of the one or more areas to a user.

5. The method of claim 4, wherein the energy saving and emission reduction potential is characterized by an amount of carbon emission reduction caused by the construction of a district cooling system and/or a degree of mitigation of urban heat island effects in the one or more districts or by an amount of carbon emission reduction caused by the construction of a district heating system in the one or more districts.

6. The method of claim 1, wherein the energy usage requirements and construction related data for the one or more areas comprises satellite maps, point of interest data, climate data, building footprints, building heights, building categories, water locations, and greenfield locations within the one or more areas; the national design specification data of the one or more regions includes cooling/heating related design criteria, cooling/heating load calculation related parameters applicable to the one or more regions.

7. The method of claim 1, wherein the database is established by:

determining the boundary of a target area and dividing the target area into a plurality of areas with the same size according to different gears representing the size of a grid by using an automatic grid dividing tool;

collecting public raw data in a target region from the Internet, wherein the public raw data comprises a satellite map, interest point data, annual climate data, cooling/heating related design standards and cooling/heating load calculation related parameters;

deducing the water body position and the greening position in the area covered by each satellite map from the collected green band, infrared band and near infrared band data in the satellite map by using the normalized vegetation index and the water index, and storing the water body position and the greening position in the database;

dividing an area represented by each grid under each gear aiming at the automatic grid by using a construction feasibility evaluation model called from the algorithm library, calculating a corresponding construction feasibility score based on a satellite map of the area, and storing the construction feasibility score into the database;

using a building geometric model which is extracted from the algorithm library and consists of a building floor area presumption model and a building height presumption model, presuming the building floor area and the building height of each building in the coverage area of each satellite map from the collected red, green and blue wave band data in the satellite map, and storing the building floor area and the building height into the database;

estimating the building type of each building according to the socioeconomic characteristics of the interior and the periphery of each building in the target area extracted from the collected interest point data and the building occupation area and the building height of each building by using the building type estimation model extracted from the algorithm library, and storing the building type in the database;

calculating the refrigerating/heating degree days of the target area from the collected annual climate data and storing the refrigerating/heating degree days in the database;

calculating a cooling/heating load curve of each building based on the building floor area, the building height, the building type, the cooling/heating degree days of the target area, the cooling/heating related design standard and the cooling/heating load calculation related parameters of each building in the target area by using the building cooling/heating demand evaluation model extracted from the algorithm library, and storing the cooling/heating load curve into the database;

and calculating a corresponding refrigeration/heating demand fraction for the area represented by each grid under each gear by using the building refrigeration/heating demand evaluation model of each building, and storing the refrigeration/heating demand fraction into the database.

8. The method of claim 7, wherein the public raw data further includes energy cost data for a target region, the method further comprising the steps of:

calculating the operation expenditure of a refrigeration/heating system in the region operation region aiming at the region represented by each grid under each gear of automatic grid division based on the collected energy cost data and the calculated refrigeration/heating load curve of each building;

collecting the cost of equipment for constructing a regional refrigeration/heating system and the working efficiency curve of the equipment, which are available in a target region, and storing the cost and working efficiency curve into the database;

calculating the capital expenditure for building a district cooling/heating system at the region represented by each grid at each gear for the automatic meshing based on the cost and operating efficiency curves of the plant;

based on the operational and capital expenditures, a final cost of building and operating the district cooling/heating system in the district is calculated for the district represented by each grid at each gear of the automatic meshing, and the final cost is stored to the database.

9. The method of claim 7, further comprising the steps of:

collecting a working efficiency curve of equipment which is purchased in a target area and used for building a regional refrigeration/heating system, and storing the working efficiency curve into the database;

collecting climate data for a typical design day for a target area and storing the climate data in the database;

and calculating the reduction amount of carbon emission and/or the reduction degree of the urban heat island effect caused by building a regional cooling/heating system in the region aiming at the region represented by each grid under each gear of automatic grid division based on the working efficiency curve of the equipment and the climate data of the typical design day of the target region, and storing the reduction amount of carbon emission and/or the reduction degree of the urban heat island effect in the database.

10. The method of claim 1 or 7, wherein calculating a cooling/heating demand score for a region using a building cooling/heating demand assessment model matched to a target region comprises the steps of:

extracting a cooling/heating load curve of each building in the area from the database by using a pre-established index, and calculating typical design day time-by-time total cooling/heating load requirements of all buildings in the area;

calculating the energy efficiency ratio of a refrigeration/heating system, the utilization rate of a refrigeration/heating unit and the total refrigeration/heating demand amount of the typical design day based on the typical design day hourly total refrigeration/heating load demand;

standardizing the energy efficiency ratio of the refrigeration/heating system, the utilization rate of the refrigeration/heating unit and the total refrigeration/heating demand of a typical design day into fractions which are fully divided into N, calculating the average value of the fractions, and taking the average value as the refrigeration/heating demand fraction of the area.

11. The method of claim 10, wherein N is an integer multiple of 10.

12. The method of claim 1 or 7, wherein the construction feasibility assessment model matched with the target region calculates the construction feasibility score of the one or more regions based on the satellite map of the region.

13. The method of claim 12, wherein the construction feasibility assessment model matched with the target region is obtained by:

preparing a satellite map data set of the region scale of the region with the same type as the target region;

randomly selecting two satellite images from the satellite image data set to be compared with an expert, selecting a satellite image which represents a region more suitable for building a regional refrigeration/heating system from the two satellite images by the expert, and repeating the step until the preset times are reached;

calculating construction feasibility scores of the areas represented by each satellite image according to the comparison result of experts;

calculating the volume ratio, the building category ratio, the vegetation coverage rate, the water body coverage rate and the road width of the area represented by each satellite map;

carrying out nonlinear fitting modeling on the volume ratio, the building category ratio, the vegetation coverage, the water body coverage and the relation between the road width and the construction feasibility fraction of the corresponding area of the area represented by the satellite map to obtain an initial evaluation model;

training an initial evaluation model by using a first preset number of satellite images, enabling the initial evaluation model to learn the volume ratio, the building category ratio, the vegetation coverage, the water body coverage and the relation between the road width and the construction feasibility score of the corresponding area of each satellite image, and automatically adjusting the parameters of the model;

and carrying out construction feasibility evaluation on a second preset number of satellite images which are not learned by the adjusted evaluation model, comparing the construction feasibility score of the area represented by each satellite image with the construction feasibility score of the same satellite image obtained based on the evaluation of an industry expert to verify the accuracy of the evaluation model, repeating the training step if the accuracy does not reach an expected value, and storing the adjusted evaluation model into the algorithm library as a construction feasibility evaluation model matched with a target area if the accuracy does not reach the expected value.

14. The method of claim 7, wherein the building footprint inference model is a deep learning model obtained by:

preparing a satellite map training set containing building occupation position labels and red, green and blue wave bands;

designing a coder decoder structure to carry out semantic segmentation on the satellite image;

designing a loss function based on the building boundary and the building floor space shape to represent the difference between the existing model and an ideal state;

acquiring a deep learning model to be trained, selecting a satellite map from a training set, training the deep learning model to predict the building floor area of a building contained in the satellite map, calculating a loss function, adjusting each parameter of the deep learning model through negative feedback, and repeating the step until the loss function can not be reduced any more;

and taking a deep learning model obtained when the loss function can not be reduced any more as a building floor area presumption model.

15. The method of claim 7, wherein the building height inference model is a deep learning model obtained by:

preparing a digital surface model containing height information and a satellite map training set of red, green and blue wave bands;

designing a coder decoder structure, and converting input satellite map data into data containing predicted height;

designing a loss function based on the building height to represent the difference between the existing model and the ideal state;

acquiring a deep learning model to be trained, selecting a satellite map from a training set, training the deep learning model to predict the building height of a building contained in the satellite map, calculating a loss function, adjusting each parameter of the deep learning model through negative feedback, and repeating the step until the loss function can not be reduced any more;

and taking the deep learning model obtained when the loss function can not be reduced any more as the building height presumption model.

16. A method of optimizing the boundaries of a zone suitable for building a zone refrigeration/heating system, comprising the steps of:

a) receiving a target area input by a user;

b) receiving one or more target areas selected by a user in a target area;

c) receiving a refrigeration/heating demand fraction and a construction feasibility fraction distribution ratio input by a user;

d) performing the method of claim 1 to obtain an engineering potential score for the one or more target regions;

e) fine-tuning the boundaries of the one or more target regions by automatically adding or subtracting sub-regions, resulting in new one or more target regions;

f) repeating step d, and calculating the engineering potential scores of the new one or more target areas;

g) comparing the engineering potential score of the new one or more target regions to the engineering potential score of the one or more target regions before adjustment;

h) and if the engineering potential score of the new one or more target areas is larger than the engineering potential score of the one or more target areas before adjustment, repeating the steps e, f and g, and otherwise, displaying the boundary of the new one or more target areas before the last adjustment as an optimized boundary to the user.

17. A computer-readable medium, characterized in that it stores a computer program executable by a processor to implement the method of any one of claims 1-16, and a database and algorithm library for use in the method of any one of claims 1-16.

18. A system comprising a memory and a processor, characterized in that the memory has stored thereon a computer program executable by the processor to implement the method of any one of claims 1-16, and a database and a library of algorithms for use in the method of any one of claims 1-16.

19. The system of claim 18, further comprising a human-machine interface for receiving user input and presenting system output to a user.

20. The system of claim 18 or 19, wherein the memory and processor are located in a cloud server.

Images