Classification of urban energy units and energy districts using artificial intelligence technologies

Abstract

The present invention relates to methods, devices and computer programs for supporting the energy analysis of a geographical study area with an actually existing buildings stock. The method can comprise a step of procuring data which describe energy-relevant properties of at least one urban energy unit of the study area. The energy-relevant properties can comprise at least geometric and / or structural properties of the buildings stock in the urban energy unit. The method can comprise a step of automatically classifying the at least one urban energy unit by a classifier based on at least some of the energy-relevant properties. The method can comprise a step of providing the at least one classified urban energy unit for energy analysis. Providing can be carried out in particular by displaying the at least one classified urban energy unit on a map representation of the geographical study area by means of a display device.

Description

[0001] CLASSIFICATION OF URBAN ENERGY UNITS AND ENERGY DISTRICT USING ARTIFICIAL INTELLIGENCE TECHNIQUES

[0002] TECHNICAL FIELD

[0003] The present invention relates generally to the technical field of building planning and its energy analysis and in particular to methods, devices, systems and computer programs for supporting the energy analysis of a geographical study area with an actual existing building stock.

[0004] BACKGROUND

[0005] Smart urban planning must incorporate new ways of thinking with the concept of energy-efficient neighborhoods or districts to develop sustainable energy strategies and minimize CO2 emissions in urban areas. Planning energy systems for neighborhoods makes it easier to integrate fluctuating renewable energy, as it allows for greater flexibility in responding to peak demand and generation than if only individual buildings are considered. District heating networks must also be planned at the neighborhood level.

[0006] There is no generally accepted definition of the term "neighborhood," "quarter," or "district," let alone the term "energy-efficient neighborhoods / districts." The concept can vary depending on the context and quantitative and / or qualitative characteristics (such as administrative areas, building types, social or cultural features). The conventional concept of a neighborhood—as an administrative area within a city—is insufficient when it comes to integrating sustainable energy strategies and energy management concepts into urban planning to minimize overall energy consumption and CO2 emissions. The concept of energy-efficient neighborhoods has been increasingly pursued in urban planning and research for several years.Although there is already work on the energetic characterization of urban regions, there is currently no efficient way to quickly and easily classify urban regions according to their energetic and morphological characteristics, thus providing the necessary basic data for urban and energy planning. Literature on the definition of urban units with energetic characteristics is known from the state of the art. In the book "Energetic Urban Space Types - Structural and Energetic Characteristics of Urban Spaces" by Dettmar et al. (2020), urban units with energetic characteristics are defined. However, since infrastructure, construction patterns, materials, building types, year of construction, and other characteristics vary from region to region and from country to country, these urban units could only be defined as average values ​​for Germany.This book also presents the energy requirements and potentials of typical residential, mixed-use and commercial developments in the form of concise profiles with energy demand values.

[0007] Three large groups for types of urban units were defined: settlement areas, open spaces and individual elements. Due to historically similar urban development, settlement areas in Germany have homogeneous and recurring structural and technical features. These areas are divided into 14 definable building structures from 1 to 10, with further subdivisions. The second main group is open spaces, i.e. undeveloped areas in urban areas, such as public green spaces, traffic areas, bodies of water and rural open spaces. A total of 15 different classes were identified. In addition to the coherent urban structures, special buildings can also play an important role as individual elements in the urban context from an energy perspective. They form the third main group. Individual elements such as educational buildings, hospitals, cinemas, sports fields and buildings can be individually identified and considered.These are mostly non-residential buildings used for monofunctional purposes.

[0008] Also known from the state of the art are methods and approaches for calculating the energy requirements of individual buildings, for calculating the energy requirements of defined neighborhoods, and many different definitions of the term "energy-efficient neighborhood" and its variants, such as energy districts, net-zero districts, and positive energy districts. However, none of these definitions specify what data is required and how this data is to be acquired and processed to create such energy-efficient neighborhoods.

[0009] The problem with the current state of the art is that there is no general procedure that clearly explains what type of data, in which format, should be collected and processed to begin the process of defining energy-efficient districts. There is also no procedure that integrates all information or files into a single format. The second problem is that there is no methodology that could be easily accessible to the public or energy analysts, one that is based, for example, on open-source data, or that classifies a region according to its various structural and morphological characteristics. The third problem is that there is no technique that can be applied flexibly and scalably across different regions of a country, thus being able to analyze both smaller regions and cities, as well as larger regions or entire countries (e.g., Germany).

[0010] It is therefore an object of the present invention to provide techniques for supporting the energetic analysis of a geographical study area with a real existing building stock and thus to at least partially overcome the above-mentioned disadvantages of the prior art.

[0011] SUMMARY OF THE INVENTION

[0012] In its most general form, the present invention provides methods, devices, systems, and computer programs for supporting the energy analysis of a geographical study area with an existing building stock. The described methods can be computer-implemented.

[0013] One aspect of the present invention relates to a method for supporting the energy analysis of a geographical study area with an existing building stock. The method can comprise a step of obtaining data that describe energy-relevant properties of at least one urban energy unit, in particular with multiple buildings, in the study area. The energy-relevant properties can comprise at least geometric and / or structural properties of the building stock in the urban energy unit. The method can comprise a step of automatically classifying the at least one urban energy unit by a classifier based on at least some of the energy-relevant properties. The method can comprise a step of providing the at least one classified urban energy unit for an energy analysis.The provision can be achieved, in particular, by displaying the at least one classified urban energy unit on a map of the geographical study area using a display device. An urban energy unit comprises, in particular, several buildings. For example, the several buildings can comprise different building types, such as single-family homes, multi-family homes, commercial spaces, and / or similar.

[0014] The actual existing building stock and the associated geographical

[0015] The study area can be real buildings (i.e., real objects) and not a hypothetical building stock (i.e., a simulation or model). In particular, the real existing building stock comprises several buildings. Accordingly, the energy-relevant properties can be understood in the sense of measured values ​​that describe the real existing building stock in the associated geographical study area. Thus, automatic classification can also be understood as calculating or predicting a physical state of an existing real object (e.g., one or more buildings and / or one or more urban energy units). Displaying the at least one classified urban energy unit can support a user in carrying out a technical task, in particular energy analysis.

[0016] In a further aspect of the present invention, the classifier may classify an urban energy unit received as input into a class of a plurality of predetermined classes of urban energy units based on its energy-related properties.

[0017] Classifying the urban energy unit into one of the predefined classes has numerous advantages: Classes offer a way to organize urban energy units and, if necessary, even create a hierarchical structure. In particular, classification at the urban energy unit level does not rely on a building type, but rather on characteristics of the urban energy unit as a reference. This facilitates the management and analysis of urban energy units, as they can be grouped according to common features or properties. Classifying urban energy units also reduces complexity. The computing power required to implement the inventive method is thus reduced. Instead of considering each urban energy unit individually, general characteristics and behavior patterns can be identified within a class.Classes also make it possible to establish relationships between urban energy units and / or identify patterns. This enables predictions and / or generalizations by allowing conclusions to be drawn about an urban energy unit within a class that may also apply to other urban energy units of the same class. Furthermore, classes are a means of communicating complex information about urban energy units in a compact and understandable way. Classification also results in standardization and thus improves the scalability of the process. Finally, grouping urban energy units into classes can also help reduce the amount of data by grouping similar urban energy units together. This can improve efficiency and storage requirements when processing large amounts of data.In a further aspect of the present invention, the automatic classification by the classifier can comprise the following steps: Determining, for a plurality of energy-relevant properties, whether their respective value lies within a predetermined value range of each class. Selecting those classes as candidate classes for which the respective value of the majority of the energy-relevant properties lies within the predetermined value range. Classifying the urban energy unit into the class from the candidate classes for which the values ​​of the energy-relevant properties deviate the least from target values.

[0018] The resulting more efficient and accurate classification of the urban energy unit can further improve the energy analysis of the geographical study area.

[0019] In a further aspect of the present invention, the classifier may comprise a decision tree.

[0020] One of the advantages of using a decision tree is that it does not require a large amount of training data. Another advantage is the interpretability and adaptability of the decision tree. Furthermore, decision trees can typically handle both numerical and categorical data and therefore do not require any special preprocessing or data transformation. Furthermore, decision trees generally require less computing power for predicting and classifying data than complex algorithms such as neural networks, making them efficient at processing large data sets.

[0021] In a further aspect of the present invention, the energy-relevant properties can include one or more of the following properties: an area (A), a land-use typology (LU), a number of buildings (NB), an average building height (H), a total floor area (TGA), a total floor area (TFA), a floor area ratio (FAR), a floor area ratio (SAR), a building count ratio (NBR), a gross footprint per total area (BrFA), an average area-volume ratio (A / V ratio), and an open space (FRS).

[0022] The use of one or more of these properties or parameters makes it possible to make an accurate (i.e. generally valid) statement about the study area or to describe it quantitatively.

[0023] In a further aspect of the present invention, several urban

[0024] Energy units are classified, and the method further comprises the following steps: combining the classified urban energy units into at least one energy district based on a combination criterion. The step of providing can comprise providing the at least one energy district for the energy analysis, in particular on a map representation of the geographical study area.

[0025] By grouping the classified energy units into energy districts, the energy analysis of the study area is further improved, as this analysis can now be carried out on the basis of a reliable database. Providing these energy districts on a map supports the user in the analysis, as it allows, for example, patterns regarding the distribution of energy demand within the study area to be directly identified.

[0026] In a further aspect of the present invention, the combination criterion may be selectable by a user.

[0027] This improves the flexibility of summarizing, providing the user with improved support for energetic analysis.

[0028] In a further aspect of the present invention, the combination criterion can be based on one or more of the following factors. One factor can be traffic route network information, in particular regarding the geographical location of major roads. One factor can be power grid information, in particular regarding the geographical location of power generation plants and / or heat generation plants and / or transformer stations. One factor can be administrative area information.

[0029] Using transport network information, particularly regarding the geographical location of major roads, energy districts can be efficiently aggregated. For example, a block (e.g., a building block, etc.) enclosed by roads can be formed using corresponding transport network information (e.g., the road network described by the geographical location of (major) roads). Administrative area information, such as legislatively defined district boundaries, can also simplify the aggregation of classified energy units.

[0030] In a further aspect of the present invention, in which the combination criterion is based at least on power grid information regarding the geographical location of power generation plants and / or heat generation plants and / or transformer stations, the summarizing step can comprise the following steps: A step of generating a Voronoi diagram based on a map representation of the geographical study area, wherein the transformer stations are the centers of the regions of the Voronoi diagram. A step of assigning the classified urban energy units to the regions of the Voronoi diagram. A step of summarizing those classified urban energy units that are assigned to the same region of the Voronoi diagram into an energy district.

[0031] This enables more efficient planning and flexibility of the energy supply (e.g. with regard to load and generation peaks or integration of renewable energy sources).

[0032] In a further aspect of the present invention, the energy analysis can comprise displaying at least one energy-relevant characteristic of the at least one classified urban energy unit on a display device. The at least one energy-relevant characteristic can comprise one or more of the following characteristics: an energy demand of the at least one classified urban energy unit, in particular an electricity demand and / or a heat demand and / or a cooling demand and / or a cooling load, a carbon dioxide emission of the at least one classified urban energy unit. Furthermore, the method can comprise displaying at least one energy-relevant characteristic of the at least one energy district on a display device.The at least one energy-relevant parameter can comprise one or more of the following parameters: an energy demand of the at least one energy district, in particular an electricity demand and / or a heat demand and / or a cooling demand and / or a cooling load, as well as a carbon dioxide emission of the at least one energy district.

[0033] The energy requirement can refer to the requirement per defined area unit (e.g. hectare) per defined period (e.g. year) or for a specific point in time.

[0034] Additionally or alternatively, the energy demand can refer to a heating load and / or electrical load (i.e., what power output a heater must have to maintain a given temperature at an outside temperature). Relevant standards (e.g., DIN EN 12831-1) may be observed in this case. Additionally or alternatively, the energy demand can refer to a cooling load and / or cooling demand. Providing these energy-relevant parameters supports the user in the analysis, as it allows, for example, patterns regarding the distribution of energy demand within the study area to be directly identified.

[0035] In a further aspect of the present invention, the method may further comprise providing a database of building inventory data for the geographical study area. The building inventory data may describe the geometry, building type, and / or associated census data of buildings, preferably all buildings, in the building inventory of the geographical study area.

[0036] Providing a database of building stock data enables public access to data that is relevant and important for the energy analysis of study areas.

[0037] In a further aspect of the present invention, the building inventory data may be based on geometry data of the geographical study area, in particular 3D building data and / or CityGML data, and census data of the geographical study area.

[0038] In particular, 3D building data in combination with CityGML and census data form a comprehensive database for describing building stock data.

[0039] In a further aspect of the present invention, providing the database of building stock data may include assigning the census data to the building stock, in particular to individual buildings within the building stock. The assignment may be performed using a classification and / or regression method, in particular a random forest method.

[0040] This type of projection or allocation of census data to the building stock provides further information (e.g. relationship between the number of people in a building and energy demand).

[0041] In a further aspect of the present invention, the method may further comprise providing a database of urban units for the geographical study area. The urban units may be formed by intersecting the boundaries of the study area, land use data, and / or road infrastructure data. Providing a database of urban units enables public access to data that is relevant and important for the energy analysis of study areas.

[0042] In a further aspect of the present invention, the method may further comprise integrating data from the database of building inventory data and data from the database of urban units, in particular using an integration model. The step of obtaining data describing energy-relevant properties of at least one urban energy unit in the study area may comprise obtaining the integrated data.

[0043] Integration enables the use of a wide variety of data in a wide variety of formats from a wide variety of data sources. This makes it possible to provide a broad database of integrated data, which can further improve the data-driven methods disclosed herein.

[0044] A further aspect of the present invention relates to using the method according to any of the aspects disclosed herein for an energy analysis of a geographical study area with a building stock for one or more applications. Examples of these applications may include urban planning, energy consulting, building management, sector integration and / or sector analysis, and district analysis.

[0045] Another aspect of the present invention relates to a data processing device. The device comprises means for carrying out the method according to any of the aspects disclosed herein.

[0046] Another aspect of the present invention relates to a computer program. The computer program comprises instructions that, when executed by a computer, cause the computer to carry out the method according to any of the aspects disclosed herein.

[0047] BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Preferred embodiments of the present disclosure are described below with reference to the following figures:

[0049] Fig. 1 : A method 100 according to an embodiment of the invention Fig. 2: A classifier 200 according to an embodiment of the invention

[0050] Fig. 3: A study area 300 for energetic analysis according to a

[0051] Embodiment of the invention

[0052] Fig. 4: A result 400 of assigning census data to a

[0053] Building stock of the study area 300, as it can be used to provide a database of building stocks according to an embodiment of the invention

[0054] Fig. 5: A result 500 of classifying urban energy units for an energetic analysis of the study area 300 according to an embodiment of the invention

[0055] Fig. 6: Providing 600 a summarizing of classified urban

[0056] Energy units of the study area 300 to energy districts according to an embodiment of the invention

[0057] Fig. 7a A first overview of urban energy units according to an embodiment of the invention

[0058] Fig. 7b A second overview of urban energy units according to an embodiment of the invention

[0059] Fig. 7c A third overview of urban energy units according to an embodiment of the invention

[0060] Fig. 8 An overview of a system 800 for supporting the energetic analysis of a geographical study area according to an embodiment of the invention

[0061] DETAILED DESCRIPTION

[0062] Below, various aspects of the support for the energetic analysis of a geographical study area with a real existing building stock are described using embodiments of the present invention. Overall, the aspects of the present invention disclosed here represent an improvement over the prior art, since there is no standard method for classifying a geographical study area (e.g., a city) into its urban (energy) units, and although the work of Dettmar et al. (2020) is known, it is not clear where the information originates and how it can be processed to classify the corresponding urban units. On the other hand, some of the input parameters for the classification are measured locally or even privately acquired.The disclosed methodology represents a significant improvement over the prior art because, in some embodiments, it is based, among other things, on freely available data.

[0063] Fig. 1 shows an overview of a method 100 according to an embodiment, which can be used to support the energetic analysis of a geographical study area with a real existing building stock.

[0064] Step 102 comprises: obtaining data describing energy-relevant properties of at least one urban energy unit of the study area, wherein the energy-relevant properties include at least geometric and / or structural properties of the building stock in the urban energy unit.

[0065] Step 104 comprises: automatically classifying the at least one urban energy unit by a classifier based on at least some of the energy-related properties.

[0066] Step 106 includes: providing the at least one classified urban energy unit for an energy analysis.

[0067] This method describes a geographic information system (GIS)-based model that uses various open data sources, processes the respective information, and is capable of classifying each specific region within a country (e.g., Germany) into different urban energy units (UEUs for short). This can then be used, for example, for urban planning, energy consulting, building management, sector coupling and / or sector analysis, district analysis, or within a geographic information system (GIS) or other software applications. The method can be implemented, for example, in Python.

[0068] The model can start from a specific study area, access a wide variety of data (e.g., open-source data), process this information, classify buildings within the study area into different categories, delimit specific spatially defined sections within the study area, classify these sections according to UEUs, and create specific energy-efficient districts that are unique depending on their shape, building infrastructure, and energy demand. Advantages of this approach include modularity, reproducibility, and flexibility.

[0069] Step 102 of method 100 describes obtaining data that describe energy-relevant properties of at least one urban energy unit of the study area, wherein the energy-relevant properties include at least geometric and / or structural properties of the building stock in the urban energy unit. The energy-relevant properties can include one or more of an area (A), a land-use typology (LU), a number of buildings (NB), an average height of buildings (H), a total floor area (TGA), a total floor area (TFA), a floor area ratio (FAR), a floor area ratio (SAR), a building count ratio (NBR), a gross footprint per total area (BrFA), an average area-to-volume ratio (A / V ratio), and an open space (FRS).

[0070] Step 104 of method 100 describes an automatic classification of the at least one urban energy unit by a classifier based on at least some of the energy-relevant properties. This makes it possible to explain the settlement pattern and building properties. The UEUs can thus serve as analysis units for, for example, future urban energy planning. The classifier can classify an urban energy unit received as input into a class from several predetermined classes of urban energy units based on its energy-relevant properties. The automatic classification by the classifier can comprise the following steps: Determining, for several energy-relevant properties, whether their respective value lies within a predetermined value range of each class.Selecting those classes as candidate classes for which the respective values ​​for the majority of energy-relevant properties lie within the specified value range. Classifying the urban energy unit into the class from the candidate classes for which the values ​​of the energy-relevant properties deviate the least from the target values. The classifier can comprise a decision tree, as described in more detail in Fig. 2.

[0071] Step 106 of method 100 describes providing the at least one classified urban energy unit for an energy analysis. This can be done by displaying the at least one classified urban energy unit on a map of the geographical study area using a display device (e.g., tablet, laptop, smartphone, screen, etc.). In step 104, multiple urban energy units can also be classified. In this case, the method can include a step 105 (not shown). In step 105, the classified urban energy units can be combined into at least one energy district based on a combination criterion. Energy districts have the characteristic of being clearly defined in terms of geographical boundaries, energy demand, settlement patterns, and building characteristics.The advantage of such a modular approach to forming energy districts is that it provides every urban planner or energy analyst with a standard approach for planning and analyzing the energy demand of settlements that are, for example, larger than a house or smaller than a city. A UEU can serve as a standard unit to support the energy analysis, and the user (e.g., urban planner) can choose their own combination criteria to combine the UEUs into energy districts. This achieves an efficient compromise between standardization and flexibility, allowing even case-specific special conditions to be taken into account.

[0072] If step 105 has been executed, the provision of step 106 may include providing the at least one energy district for the energy analysis. This may be done, in particular, by means of a map representation of the geographical study area.

[0073] The combination criterion may be user-selectable. Additionally or alternatively, the combination criterion may be based on one or more of the following factors: transport network information, in particular regarding the geographical location of major roads; electricity network information, in particular regarding the geographical location of power generation facilities and / or heat generation facilities and / or transformer stations; and administrative area information. None of the above factors may also be selected (i.e., no combination criterion is selected). In this case, each UEU acts as an energy district.

[0074] If the combination criterion is based at least on power grid information regarding the geographical location of power generation plants and / or heat generation plants and / or transformer stations, the summarizing step 105 may further comprise generating a Voronoi diagram based on a map representation of the geographical study area. The transformer stations may be the centers of the regions of the Voronoi diagram. Furthermore, step 105 may comprise assigning the classified urban energy units to the regions of the Voronoi diagram and summarizing those classified urban energy units that are assigned to the same region of the Voronoi diagram into an energy district. For example, grid transformers may serve as input points for creating a Voronoi diagram.Each transformer can then be associated with a region in the plane where the distance of all its points to this transformer is smallest. These regions are called Voronoi cells. This Voronoi grid can then be overlapped with the already classified UEUs. This is possible because, in one embodiment, both the Voronoi cells and the UEUs are in a multipolygon vector format. Each UEU can then be assigned. To do this, it can be checked whether a UEU overlaps with one of the Voronoi cells by more than 50%. A UEU can only be assigned to one Voronoi cell, even if the UEU may be geographically located in more than one Voronoi cell. Finally, all UEUs belonging to a grid transformer (i.e., input as a Voronoi point) can be grouped together and thus referred to as an energy district.Accordingly, in this example, there will be the same number of energy districts as there are grid transformers. It should be noted that aggregating UEUs based on their closest distance to a grid transformer is only one of countless ways to combine UEUs.

[0075] The energy analysis supported by method 100 can comprise displaying at least one energy-relevant characteristic of the at least one classified urban energy unit on a display device (e.g., tablet, smartphone, screen, etc.). The at least one energy-relevant characteristic can comprise an energy demand of the at least one classified urban energy unit, in particular an electricity demand and / or a heat demand and / or a cooling demand and / or a cooling load. Additionally or alternatively, the energy-relevant characteristic can comprise a carbon dioxide emission of the at least one classified urban energy unit. If step 105 has been executed, at least one energy-relevant characteristic of the at least one energy district can also be displayed.The at least one energy-relevant characteristic of the energy district can comprise an energy demand of the at least one energy district, in particular an electricity demand and / or a heat demand and / or a cooling demand and / or a cooling load. Additionally or alternatively, the characteristic can comprise a carbon dioxide emission of the at least one energy district.

[0076] The method may comprise a step 101 (likewise not shown), which may precede the retrieval of the data in step 102 and may generally relate to the provision and / or integration of a data basis (e.g. in the form of a database). Step 101 may comprise one or more sub-steps. A sub-step 101a may, for example, provide a database of building stock data for the geographical study area. The building stock data may describe the geometry, the building type and / or associated census data of buildings (preferably all buildings) in the building stock of the geographical study area. The building stock data may be based on geometry data of the geographical study area, in particular 3D building data and / or CityGML data, and census data of the geographical study area.

[0077] Providing the database of building stock data may further include assigning the census data to the building stock, in particular to individual buildings within the building stock. The assignment may be performed using a classification and / or regression method (e.g., a random forest method).

[0078] A substep 101b, for example, can provide a database of urban units (UEUs) for the geographical study area. The urban units can be formed by intersecting the boundaries of the study area, land use data, and / or road infrastructure data. The resulting UEUs, as a unit, can not only provide standardization for defining energy districts within a study area, but also allow for modular aggregation to analyze larger settlements. This means that the UEUs, as a unit, can be combined in a modular manner to create energy districts.

[0079] In one example, this database can be generated by preprocessing and integrating the OSM datasets for land use and road infrastructure and calculating the UEU attributes (according to Dettmar et al. (2020)). These attributes are required for the classification of the different UEUs. Of the 47 parameters defined by Dettmar et al., 23 may be sufficient for the classification model (see Table 2). These attributes originate from the processing of the building database into spatially defined sections or urban units. The integration can be achieved using statistical methods for each of the parameters (e.g., by averaging, summing, or listing the respective values ​​of all buildings within the urban units).Since the building database refers to the individual buildings within the study area, and the urban unit database refers to the division of the study area into different urban units, the integration of these two databases is achieved firstly by aggregating the parameters of the individual buildings using statistical methods and secondly by assigning these parameters to each of the urban units within the study area. To have a common reference unit, for example, all parameters can be specified per hectare of the urban unit.

[0080] In step 101, data from the building stock database and data from the urban unit database can also be integrated. This can be done using an integration model. In this case, step 102 of obtaining data describing energy-relevant properties of at least one urban energy unit of the study area involves obtaining the integrated data. Integrating the data is necessary because, for example, 3D GML models and the census database have inherently different data structures, which makes cleaning and processing the data a crucial step in building the database. While 3D GML models usually represent the spatial features of each building with a specific coordinate system and other building characteristics such as function, roof shape, etc.With input points within the markup language, the census data usually has a tabular structure, where each row can correspond to a specific grid cell of, for example, 100 m x 100 m in the INSPIRE-compliant grid format. This requires not only the geolocation of the buildings within the grid format but also the assignment of the census data to the corresponding 3D building model (e.g., using a random forest model).

[0081] The classes of urban energy units (UEUs) can be determined, for example, based on the energetic urban space types (ESTs) and / or individual units (EEs) (e.g., schools, churches, hospitals, etc.) designed by Dettmar et al. Table 1 shows an example of the determination of 16 UEUs based on the ESTs. The properties and characteristics of these 16 UEUs are described in detail in Figs. 7a-c.

[0082] In this determination, UEUs can describe 1-10 classes of built-up areas, and UEUs can describe 11-16 classes of open spaces. The elimination of subclassifications as in Dettmar et al. (e.g., EST 4.a and 4.b) has the advantage that less complex and more general data serve as input for the classifier, which can improve the classifier's performance (e.g., in terms of accuracy). No UEU classes were developed for traffic areas, as the focus is on the energy analysis of study areas with existing building stocks. On the other hand, traffic route network information can serve as factors for the combination criterion.

[0083] Table 3 shows an example overview of energy-relevant properties based on which urban energy units are classified into one of the predefined classes of UEUs. One or more properties can be used for classification. In addition, predefined value ranges are specified for each class of UEUs 1-10. For UEUs 11-16 (i.e., open spaces), the classification can be based on a land-use classification (e.g., by the State Office) and / or OpenStreetMaps. Accordingly, corresponding value ranges are not necessarily required for these UEUs, especially since these would be zero due to the almost nonexistent settlement infrastructure in the open spaces.

[0084] The parameter FAR describes a floor area ratio (e.g., a ratio between the total floor area of ​​the buildings within the section and the total area of ​​the section). The parameter SAR describes a floor area ratio (e.g., ratio between the total floor area of ​​the buildings within the section and the total area of ​​the section). The parameter NBR describes a building number ratio (e.g., number of buildings within the UEU divided by the area in hectares of the UEU, unit in 1 / haEu). The parameter ANS describes an average number of floors of all buildings in the UEU. The parameter BFA describes the floor area of ​​the buildings within the UEU divided by the total area of ​​the UEU (e.g., unit haf 00t / hauEu). The parameter Residential Area describes the living area divided by the total area of ​​the UEU (e.g. ha rest / hauEu). The Industrial Area parameter describes the industrial area divided by the total area of ​​the UEU (e.g., haind / hauEu). The BLS parameter describes the gross living area divided by the total area of ​​the UEU (e.g., defined as BFA x average height of the building). The BrFA parameter describes the gross footprint per total area (e.g., m 2 / hauEu). The parameter A / V-ratio describes the average area-volume ratio (e.g. m 2 / m 3 ). The parameter AES describes the average envelope area of ​​the buildings within the UEU (e.g. m 2). The parameter APF describes the average proportion of the total facade of the buildings within the UEU. The parameter UD describes the usage distribution (e.g. a percentage of the buildings within the UEU that have one of the five different uses: industry, trade, services, residential or other). The parameter CT describes the construction type of the buildings (e.g. a percentage of the buildings within the UEU that have one of the five different construction types: single-family house (SFM), multi-family house (MFH), office, special, hall, other). The parameter FRS describes open space (e.g. open spaces type A from Dettmar et al., calculated using 1-GRZ (floor area ratio)). In addition, alternatively, or in any combination to / with the energy-relevant properties shown in Table 3, the energy-relevant properties can be the parameters area (A) of the UEU (e.g. in hectares), the land use typology (LU) of the UEU (e.g.according to OpenStreetMap), the number of buildings (NB) within the UEU, the average height of the buildings (H) within the UEU (e.g. in meters), the total floor area (TGA) of the UEU (e.g. in hectares), the total floor area (TFA) (e.g. the total built-up area within the UEU taking into account the number of floors in each building of the UEU in hectares), the trading area (e.g. the commercial area divided by the total area of ​​the UEU in e.g. ha. tra / hauEu). Table 2 again shows a possible prioritization of the different parameters with regard to their importance for classification.

[0085] As explained above, the building inventory data can be based on geometric data from the geographical study area, in particular 3D building data and / or CityGML data, and census data from the geographical study area. Sources for this data can be, for example, state offices, land registry offices, or other institutes or sources. For federal states (e.g., Lower Saxony), Level of Detail 2 (LoD2) data can be retrieved, for example, via the corresponding federal state web portal (e.g., opengeodata.lgln.niedersachsen.de). Census data (e.g., basic demographic data, census data, etc.) can be retrieved, for example, via the web portal https: / / www.zensus2011.de / DE / Home / Aktuelles / DemografischeGrunddaten.html?nn=380661 8#Gitter. Table 4 shows an example overview of geometric data, the data types, and a corresponding prioritization according to their importance.

[0086] Fig. 2 shows a classifier 200 according to an embodiment of the invention. The classifier 200 can, for example, be part of the method 100 and can be used to classify an urban energy unit (UEU) received as input into a class of several predetermined classes of urban energy units, as explained with reference to Fig. 1. The classifier 200 shown in Fig. 2 can be a decision tree (DT). The classifier 200 shown in Fig. 2 can be implemented in Python. A DT is a decision support tool that uses a tree-like model of decisions and their possible consequences, including random outcomes. It is a way to represent an algorithm that contains only conditional control statements.The underlying framework consists of a collection of attributes or properties used to describe individual cases, where each case belongs to exactly one class out of a set of classes. The attributes can be either continuous or discrete. The main advantages of choosing a DT for the classification model are: First, decision trees are easy to understand and interpret. Second, decision trees use a white-box model, which means that the decisions made behind the DT are easy to understand and one's own (i.e., developer-side) decisions can be adapted and incorporated into the tree. Third, decision trees do not require a large training set and can operate with little hard data. The DT disclosed herein can classify geographical study areas (e.g., urban areas and / or their differences) into one of several UEU types (respectively,predefined classes of UEUs), as described with reference to Fig. 1. For each class, one or more conditions can be defined in the form of predefined value ranges (e.g., minimum, average, and maximum values, as described in Fig. 1 and Table 3).

[0087] The process or structure of the classifier 200 will now be illustrated using the decision steps shown in Fig. 2. The algorithm selects a UEU (e.g., from the U EU database created in step 101 of the method 100) and compares the specific parameters of this UEU with the specified value ranges (see Table 3). For each individual parameter, the algorithm determines or checks whether the value lies within the respective range (minimum and maximum literature values), and if so, it marks the parameters as true and calculates the respective deviation from the mean literature value. If the value is not within the range, the parameter is classified as incorrect. The algorithm does this for each individual parameter and counts the total number of correct and incorrect values. If the majority is correct, then the selected class is a possible classification for the selected UEU.The algorithm goes through all possible classes and selects the class with the lowest classification error (i.e. the class for which the values ​​of the energy-relevant properties deviate the least from target values).

[0088] Fig. 3 shows a study area 300 for energy analysis according to an embodiment of the invention, to which the method 100 was applied using the classifier 200. In this example, the study area 300 is Oldenburg (Germany). Section 302 of Fig. 3 shows the geographical location of Oldenburg within Germany. Section 304 shows an overall overview of Oldenburg, including the districts of Oldenburg North, Wechloy, Oldenburg Central, Osternburg, Oldenburg West, and Oldenburg South. Section 306 shows a detailed view of the Wechloy district. The individual urban energy units are highlighted according to the legend shown in section 308.

[0089] Fig. 4 shows a result 400 of assigning census data to a building stock, as can be used to provide a database of building stocks according to an embodiment of the invention. In the example shown, the year the building was built and the building type were classified and assigned. Similar to what was explained with reference to Fig. 3, this example concerns a part of the study area of ​​Oldenburg. Section 402 shows a part of Oldenburg before classification with regard to the year the building was built. Section 404, in turn, shows the result of the classification, with the buildings highlighted according to the legend shown in section 406 and according to their class. Section 406 shows another part of Oldenburg before classification with regard to the building type.Section 410 again shows the result of the classification, with the buildings highlighted as either SFH or MFH according to the legend shown in Section 412.

[0090] The relevant data was retrieved from the various (open-source) data sources mentioned above. For this example, 3D building models, CityGML attributes, geolocation, and census data for study area 300 were integrated, creating a resulting database of building inventory data. This exemplary database has a tabular structure with a total of 56,749 records (individual buildings) and 37 attributes describing the geometry, building type, and census data of each building (see Table 4). According to the Oldenburg administration, there are 45,438 residential buildings and approximately 2,956 non-residential buildings; the difference in the number of records is attributable to individual small structures such as garden sheds or garages.The geolocation process enables the integration of the 3D building models with the CityGML attributes and GIS data by using the same ETRS89 Lambert Azimuthal Equal Area coordinate reference system. In this example, the census data was assigned to the building stock, specifically to individual buildings, using a disaggregation model based on a random forest model. The classification attributes used in this model are the geometric and descriptive attributes of the individual buildings, as well as the information from the census grid cell of the INSPIRE-compliant raster format in which each specific building is located. The training dataset was trained using the buildings located in a single-value census grid cell with a building record structure for the city of Wuppertal. The model's overall accuracy reached 84% for building age classification.The results were obtained by training on a 70% subset of the Oldenburg building database, by testing on the remaining 30% (test dataset) and by additional cross-validation.

[0091] Fig. 5 shows a result 500 of a classification of urban energy units for an energetic analysis of the study area 300 according to an embodiment of the invention. Section 502 shows a district of Oldenburg, which has been classified and divided into the different UEU types, as shown in section 506. The result 500 of the classification in section 502 clearly shows that the old town and the surrounding industrial areas are well classified, as are the residential buildings, which predominantly correspond to UEU types 1 and 2. Section 508 shows the corresponding satellite image of the Oldenburg district shown in section 502. Section 504, on the other hand, shows an overall overview of the study area 300 classified and divided according to the different UEU types 506. The residential areas of the city are clearly visible, as are the farmland and forests surrounding the city.This shows that the classification model works on large scales.

[0092] The corresponding data, which are stored or contained, for example, in a database of urban units for the geographical study area, describe information about the spatially defined sections within the study area and the relevant attributes for classification into UEU types. The database created for this example was created by preprocessing and integrating the OSM datasets for land use and road infrastructure and by calculating the UEU attributes from Dettmar et al. (2020). A total of 8,249 UEUs were spatially defined. These UEUs form a database with the 23 parameters shown in Table 2, which were used, for example, for the UEU classification process. Each of the previously spatially defined UEUs was classified into one of the 16 UEUs (see Table 1) by applying the previously described DT classifier 200.

[0093] Fig. 6 shows the provision 600 of a grouping of classified urban energy units of the study area 300 into energy districts according to an embodiment of the invention. In the example shown, power grid information regarding the geographical location of transformer stations was selected as the combination criterion to group the classified UEUs. Transformer stations / grid transformers typically serve as a link between electricity and heat demand. Since, for example, heat demand will be increasingly covered by renewable sources in the future, more electricity must be fed into the grid and distributed via these grid transformers, which is why selecting transformer stations as the combination criterion can be advantageous.In addition, the grid transformers are a point in space, which means that the corresponding data are available in a geographically referential point-vector format to which the disclosed methodology is adaptable.

[0094] However, the combination criterion is freely selectable by anyone wishing to apply this method, demonstrating the flexibility and adaptability of the method in other scenarios, which is a great advantage when attempting to replicate the process in other regions. It is also possible to represent each UEU as a separate energy district (e.g., if no optimal or satisfactory combination criterion can be found). A corresponding dataset was provided by a local grid operator. A total of 8,249 UEUs were classified and summarized into 798 energy districts in the city of Oldenburg.

[0095] Section 602 shows an overall view of the study area, which in this example is Oldenburg, divided into energy districts. Section 604 shows a portion of the urban area of ​​Oldenburg divided into energy districts, along with the corresponding satellite image. The transformer stations are represented as points. To demonstrate the potential of the approach, an exemplary energy district was randomly selected and subjected to an energy analysis. The selected energy district is depicted in more detail in Section 606 and includes four UEUs. The corresponding summary of the results of the energy analysis (e.g., the total energy demand) is presented in Section 610.

[0096] Fig. 7a shows a first overview 700a of urban energy units (UEUs) according to an embodiment of the invention. The UEU types 1-5 shown are primarily used for residential purposes. The middle column shows a conceptual structure of the UEU, while the right column shows an actual satellite image of an exemplary UEU of the corresponding type (here using the example of Oldenburg). UEU-1 is characterized by a small-scale residential development with a mix of detached one- to three-story single-family homes and multi-family houses in open single- or semi-detached construction. UEU-2 is characterized by a terraced housing development with purely residential use. The rows of terraced houses, each consisting of linked 1.5- to 3-story single-family homes, are arranged parallel or orthogonally to each other. UEU-3 is characterized by a 4- to 6-story row development with purely residential use.The rows consist of linked apartment buildings and are arranged approximately parallel with generous spacing. In contrast to the terraced housing development of UEU-2, several individual buildings can be located on the same site. UEU-4 is characterized by a large-scale, irregularly and widely arranged residential development with 7- to 16-story apartment buildings. The UEU consists of a mixture of freestanding point high-rises and a linked construction style as rows and chains of buildings. UEU-5 is characterized by a perimeter block development with 3- to 6-story apartment buildings with predominantly residential use. Depending on the location, commercial and office space may also be present on the first floor to a lesser extent. Fig. 7b shows a second overview 700b of urban energy units according to an embodiment of the invention.The UEU types 6-8 shown are predominantly a mix of residential and industrial or administrative use. UEU types 9 and 10 consist predominantly of administrative and industrial or commercial use. The middle column shows a conceptual structure of the UEU, while the right column shows an actual satellite image of an exemplary UEU of the corresponding type (here using the example of Oldenburg). UEU-6 is characterized by dense, heterogeneous development with detached and clustered single-family and multi-family houses, which, due to historical reasons, often belong to different building ages. The 1.5- to 2.5-story buildings are positioned in closed or open construction along the street and sidewalk edges. UEU-7 is characterized by dense development with 2.5- to 6-story, coupled residential buildings that form a closed building line along winding streets and alleys.For historical reasons, most of the buildings date from before 1918. UEU-8 is characterized by a high building density and describes the characteristics of an urban center, as found in large cities. UEU-9 is characterized by a mix of predominantly 5- to 10-story office and administrative buildings, supplemented by low-rise special-purpose hall buildings of various ages. However, the freestanding office and administrative buildings characterize the appearance of this UEU. UEU-10 is characterized by a mix of predominantly single-story hall buildings, which, depending on their internal use, are supplemented by two- to three-story office and administrative buildings and single-story ancillary buildings.

[0097] Fig. 7c shows a third overview 700c of urban energy units according to an embodiment of the invention. The UEU types 11-16 shown are predominantly locations with open spaces. UEU types 14-16 are mainly agricultural areas that are not primarily used for leisure and recreation, but for the production of food or timber. The middle column shows a conceptual structure of the UEU, while the right column shows an actual satellite image of an exemplary UEU of the corresponding type (here using the example of Oldenburg). UEU-11 describes public parks, which are an important component of the urban green space system. Their size varies from less than one hectare to several hundred hectares. UEU-12 describes cemeteries, which, like parks, are part of the public green spaces. Their design varies depending on their origin and region.Two basic types can be distinguished: stony cemeteries with sparse forest cover and cemeteries with dense forest cover. Both types can also fall into the same category. UEU-13 describes allotment gardens. In contrast to parks and cemeteries, allotment gardens differ little in form and function due to the requirements of the Federal Allotment Garden Act in Germany. Access to the individual gardens is usually provided via an orthogonal network of main and secondary paths. UEll-14 describes arable land, which is classified as agricultural land and is marked accordingly in the land-use plan. UEll-15 describes permanent grassland, which is agricultural land designated as such in the land-use plan. UEll-16 describes forest or forestry land, which is also designated as such in the land-use plan and defined in the Federal Forest Act as areas planted with forest plants.

[0098] Fig. 8 shows an overview of a system 800 for supporting the energy analysis of a geographical study area according to an embodiment of the invention. The system 800 can implement the method 100 described with reference to Fig. 1 for supporting the energy analysis of a geographical study area with an existing building stock.

[0099] Section 801 shows the input of a geographical study area to be used for the energy analysis. Section 802 shows the provision of a database of building stock data (e.g., 3D building data, CityGML data / attributes, and / or census data) for the geographical study area, as explained, for example, in sub-step 101a of the method 100 with reference to Fig. 1. Section 803 shows the provision of a database of urban energy units (UEUs) (e.g., boundaries of the study area, (OSM) land use data, and / or (OSM) road infrastructure data) for the geographical study area, as explained, for example, in sub-step 101b of the method 100 with reference to Fig. 1. Section 804 shows the integration of data from the database of building stock data and data from the database of urban units, as explained in step 101 of the method 100 with reference to Fig.1, as well as determining the UEU classes, as explained, for example, with reference to Fig. 1 and Tables 1-3. Section 805 shows the classification of the input geographic study area using a classifier 200 as explained with reference to Fig. 2. Section 806 shows the resulting classified UEUs, which can then be combined into energy districts 808 based on a combination criterion 807.

[0100] Although some aspects have been described in the context of a device, it is clear that these aspects also represent a description of the corresponding method, with a block or device corresponding to a method step or a function of a method step. Analogously, aspects described in the context of a method step also represent a description of a corresponding block, element, or property of a corresponding device.

[0101] Embodiments of the invention may be implemented in a computer system. The computer system may be a local computing device (e.g., a personal computer, laptop, tablet computer, or mobile phone) having one or more processors and one or more memory devices. The computer system may be a distributed computing system (e.g., a cloud computing system having one or more processors or one or more memory devices distributed at different locations, for example, at a local client and / or one or more remote server farms and / or data centers). The computer system may include any circuitry or combination of circuits. In one embodiment, the computer system may include one or more processors, which may be of any type.The term "processor" is understood to mean any type of computing circuit, such as a microprocessor, a microcontroller, a complex instruction set microprocessor (CISC), a reduced instruction set microprocessor (RISC), a very long instruction word (VLIW) microprocessor, a graphics processor, a digital signal processor (DSP), a multi-core processor, a field-programmable gate array (FPGA), or any other type of processor or processing circuit. Other types of circuitry that may be included in the computer system may be a custom-built circuit, an application-specific integrated circuit (ASIC), or the like, such as one or more circuits (e.g., a communications circuit) for use in wireless devices such as cellular phones, tablet computers, laptop computers, two-way radios, and similar electronic systems.The computer system may include one or more storage devices, which may include one or more storage elements suitable for the particular application, such as main memory in the form of random access memory (RAM), one or more hard disks, and / or one or more drives handling removable media such as CDs, flash memory cards, DVDs, and the like. The computer system may also include a display device, one or more speakers, and a keyboard and / or controller, which may include a mouse, trackball, touchscreen, voice recognition device, or any other device that allows a system user to input information to and receive information from the computer system.Some or all of the method steps may be performed by (or using) a hardware device, such as a processor, a microprocessor, a programmable computer, or an electronic circuit. In some embodiments, one or more of the key method steps may be performed by such a device.

[0102] Depending on specific implementation requirements, embodiments of the invention may be implemented in hardware or software. The implementation may be performed using a non-volatile storage medium, such as a digital storage medium, such as a floppy disk, DVD, Blu-ray, CD, ROM, PROM and EPROM, EEPROM, or FLASH memory, on which electronically readable control signals are stored that interact (or can interact) with a programmable computer system to perform the respective method. Therefore, the digital storage medium may be computer-readable.

[0103] Some embodiments according to the invention comprise a data carrier with electronically readable control signals that can interact with a programmable computer system so that one of the methods described herein is carried out.

[0104] In general, embodiments of the present invention can be implemented as a computer program product with program code, wherein the program code is effective for executing one of the methods when the computer program product is running on a computer. The program code can, for example, be stored on a machine-readable medium.

[0105] Further embodiments include the computer program for carrying out one of the methods described herein, which is stored on a machine-readable carrier.

[0106] In other words, an embodiment of the present invention is therefore a computer program having a program code for carrying out one of the methods described herein when the computer program runs on a computer.

[0107] Another embodiment of the present invention is a storage medium (or a data carrier or a computer-readable medium) comprising a computer program stored thereon for performing one of the methods described herein when executed by a processor. The data carrier, digital storage medium, or recorded medium is typically tangible and / or non-seamless. Another embodiment of the present invention is an apparatus as described herein, comprising a processor and a storage medium.

[0108] A further embodiment of the invention is a data stream or a signal sequence that represents the computer program for implementing one of the methods described herein. The data stream or signal sequence can, for example, be configured such that it is or can be transmitted via a data communication connection, for example, via the Internet.

[0109] A further embodiment comprises a processing means, for example a computer or a programmable logic device, configured or adapted to carry out one of the methods described herein.

[0110] A further embodiment comprises a computer on which the computer program for carrying out one of the methods described herein is installed.

[0111] A further embodiment according to the invention comprises a device or system configured to transmit (e.g., electronically or optically) a computer program for carrying out one of the methods described herein to a recipient. The recipient may, for example, be a computer, a mobile device, a storage device, or the like. The device or system may, for example, comprise a file server for transmitting the computer program to the recipient.

[0112] In some embodiments, a programmable logic device (e.g., a field-programmable gate array, FPGA) may be used to perform some or all of the functionality of the methods described herein. In some embodiments, a field-programmable gate array may cooperate with a microprocessor to perform any of the methods described herein. In general, the methods may preferably be performed by any hardware device. Tables

[0113] Table 1: Example determination of UEUs based on ESTs

[0114]

[0115] Table 2: Example prioritization of energy-relevant properties

[0116]

[0117] Table 3: an exemplary overview of energy-relevant properties and the corresponding value ranges for each class of the UEU1-10.

[0118] 5

[0119] Table 4: Example overview of geometry data.

Claims

CLAIMS 1 . A computer-implemented method (100) for supporting the energy analysis of a geographical study area (300) with a real existing building stock, the method comprising at least the following steps: Obtaining (102) data describing energy-relevant properties of at least one urban energy unit of the study area (300), wherein the energy-relevant properties comprise at least geometric and / or structural properties of the building stock in the urban energy unit; automatically classifying (104) the at least one urban energy unit by a classifier (200) based on at least some of the energy-relevant properties; and Providing (106) the at least one classified urban energy unit for an energetic analysis, in particular by displaying the at least one classified urban energy unit on a map representation of the geographical investigation area (300) by a display device.

2. The method according to claim 1, wherein the classifier (200) classifies an urban energy unit received as input into a class of a plurality of predetermined classes of urban energy units based on its energy-relevant properties.

3. The method according to claim 2, wherein the automatic classification by the classifier (200) comprises the following steps: Determine, for several energy-relevant properties, whether their respective value lies within a given value range of each class; Selecting those classes as candidate classes for which the respective value for the majority of the energy-relevant properties lies within the specified value range; Classify the urban energy unit into the class from the candidate classes for which the values of the energy-relevant properties deviate least from target values.

4. The method according to any one of the preceding claims, wherein the classifier (200) comprises a decision tree.

5. The method according to any one of the preceding claims, wherein the energy-relevant properties comprise one or more of the following properties: Area (A); Land use typology (LU); Number of buildings (NB); average height of buildings (H); Total floor area (TGA); Total floor area (TFA); Floor area ratio (FAR); Floor area ratio (SAR); Number of buildings ratio (NBR); Gross footprint per total area (BrFA); average area-to-volume ratio (A / V ratio); Open space (FRS).

6. The method according to one of the preceding claims, wherein a plurality of urban energy units are classified, and wherein the method further comprises: combining (105) the classified urban energy units into at least one energy district based on a combination criterion; wherein the step of providing (106) comprises: providing the at least one energy district for the energetic analysis, in particular on a map representation of the geographical study area (300).

7. The method of claim 6, wherein the combination criterion is selectable by a user.

8. The method according to claim 6 or 7, wherein the combination criterion is based on one or more of the following factors: Transport network information, in particular regarding the geographical location of main roads; Electricity network information, in particular regarding the geographical location of electricity generation plants and / or heat generation plants and / or transformer stations; Administrative area information.

9. The method according to claim 8, wherein the combination criterion is based at least on power grid information regarding the geographical location of power generation plants and / or heat generation plants and / or transformer stations and wherein the step of summarizing comprises: Generating a Voronoi diagram based on a map representation of the geographical study area (300), wherein the transformer stations are the centers of the regions of the Voronoi diagram; Assigning the classified urban energy units to the regions of the Voronoi diagram; and Combining those classified urban energy units into an energy district that are assigned to the same region of the Voronoi diagram.

10. The method according to any one of the preceding claims, wherein the energetic analysis comprises: Displaying at least one energy-relevant characteristic of the at least one classified urban energy unit on a display device, wherein the at least one energy-relevant characteristic comprises one or more of the following characteristics: An energy demand of the at least one classified urban energy unit, in particular an electricity demand and / or a heat demand and / or a cooling demand and / or a cooling load; a carbon dioxide emission of the at least one classified urban energy unit; and if claim 10 refers back to claim 6, displaying at least one energy-relevant characteristic of the at least one energy district on a display device, wherein the at least one energy-relevant characteristic comprises one or more of the following characteristics: an energy demand of the at least one energy district, in particular an electricity demand and / or a heat demand and / or a cooling demand and / or a cooling load; a carbon dioxide emission of the at least one energy district.

11. The method according to any one of the preceding claims, further comprising: providing a database of building inventory data for the geographical study area (300), wherein the building inventory data describes the geometry, the building type and / or associated census data of buildings, preferably all buildings, in the building inventory of the geographical study area (300).

12. The method according to claim 11, wherein the building inventory data is based on geometry data of the geographical study area (300), in particular 3D building data and / or CityGML data, and census data of the geographical study area (300).

13. The method according to claim 11 or 12, wherein providing the database of building inventory data comprises: Assigning the census data to the building stock, in particular to individual buildings within the building stock; wherein the assignment is carried out using a classification and / or regression method, in particular a random forest method.

14. The method according to any one of the preceding claims, further comprising: providing a database of urban units for the geographical study area (300), wherein the urban units are formed by intersecting the boundaries of the study area (300), land use data and / or road infrastructure data.

15. The method according to any one of claims 11-13 combined with claim 14, further comprising: Integrating data from the database of building inventory data and data from the database of urban units, in particular using an integration model; wherein the step of obtaining data describing energy-relevant properties of at least one urban energy unit of the study area (300) comprises obtaining the integrated data.

16. Use of the method according to one of the preceding claims for an energetic analysis of a geographical study area (300) with a building stock for one or more of the following applications: urban planning; Energy consulting; building management; Sector coupling and / or sector analysis; Neighborhood analysis.

17. A data processing device comprising means for carrying out the method according to any one of the preceding claims 1-15.

18. A computer program or a computer-readable medium on which the computer program is stored, the computer program comprising instructions which, when executed by a computer, cause the computer to carry out the method according to any one of the preceding claims 1-15.

Images