System and method for controlling an environmental condition of a zone

Abstract

The invention relates to a computer-implemented method for controlling the environmental state of a zone (1a-d), comprising acquiring (M1) planning data (21) relating to the planning of future events from a database (12), acquiring (M2) personal data (22) relating to the current locations and movements of persons, acquiring (M3) environmental data (23) relating to the current environmental state of at least one zone (1a-d), calculating (M4) a predicted occupancy (24) of the at least one zone (1a-d) based on the planning data (21) and the personal data (22), calculating (M5) a comfort environmental state (25, 26) of the at least one zone (1a-d) based on the planning data (21), the personal data (22), the environmental data (23) and the predicted occupancy (24) of the zone (1a-d), and controlling (M6) an air conditioning system (2a-d) for the at least one zone (1a-d) based on the calculated comfort environmental condition.

Description

TECHNICAL AREA

[0001] The present disclosure relates to a computer-implemented method for controlling the environmental state of a zone. The present disclosure further relates to a control device, a computer program, and a computer-readable storage medium. BACKGROUND

[0002] Heating, ventilation, and air conditioning (HVAC) systems are building components that account for a significant portion of a building's energy consumption. The importance of HVAC systems for energy costs and air quality has steadily increased in recent years, as the thermal insulation of building envelopes has improved, thereby reducing heat transfer losses and uncontrolled ventilation. Consequently, the share of HVAC systems in the remaining energy demand and in controlled ventilation is also increasing.

[0003] Traditionally, such systems are based on static schedules and preset parameters. Common systems typically include simple thermostats and air conditioners that react to preset temperature and humidity levels without considering the actual use or occupancy of the respective zone. However, the operation of HVAC systems can be adjusted to a certain degree due to their storage capacities, such as hot water storage tanks or thermally activated building systems (TABS), e.g., walls and floors. Therefore, the operation, i.e., the performance of the HVAC systems, can be shifted or adjusted for optimization purposes.

[0004] Optimizing the operation of HVAC systems requires predicting future temperature and air quality requirements. Based on these forecasts, the operation of the HVAC system can be adjusted to achieve a specific goal (e.g., minimizing peak loads) while simultaneously meeting the comfort requirements of the occupants. Occupants are defined here as people who are present in thermal zones, whether as residents, guests, employees, or workers.

[0005] These forecasts are typically based on historical loads and used to predict future loads. However, these forecasts cannot always provide sufficient accuracy. Therefore, despite considerable progress in the field of environmental control systems, there remains a need for systems that enable more precise and efficient control of environmental conditions in buildings, etc.

[0006] Therefore, one of the technical problems underlying the present invention is to provide a system for controlling environmental conditions that at least partially overcomes the disadvantages of known systems. SUMMARY OF THE INVENTION

[0007] An objective of the present invention is to provide a computer-implemented method for controlling an environmental state of a zone, which overcomes one or more of the disadvantages of known systems.

[0008] According to the present disclosure, these problems are solved by the features of independent claim 1. Furthermore, additional advantageous embodiments are described in the dependent claims and the description.

[0009] The invention provides a computer-implemented method for controlling the environmental state of a zone. The method comprises the following steps: acquiring planning data relating to the planning of future events from a database; acquiring personal data relating to the current locations and movements of people; acquiring environmental data relating to the current environmental state of at least one zone; calculating the expected occupancy of the at least one zone based on the planning data and the personal data; calculating a comfort environmental state of the at least one zone based on the planning data, the personal data, the environmental data, and the expected occupancy of the zone; and controlling a climate control system for the at least one zone based on the calculated comfort environmental state.

[0010] The invention also provides a corresponding control device for controlling the environmental state of a zone, comprising a computing unit that includes a database containing information on future events and a processor adapted to execute the method according to the invention. Furthermore, the invention provides a corresponding computer program comprising instructions that cause the control device according to the invention to execute the process steps according to the invention. The invention also provides a computer-readable storage medium on which the computer program according to the invention is stored.

[0011] A fundamental idea of ​​the present invention is to use additional data to predict user-specific behavior. Since current forecasts often neglect user behavior and focus on using historical loads and future weather forecasts to predict future loads, the increasing availability of data and computing power makes it possible to create occupant-specific forecasts. The present invention thus describes the use of data to predict user behavior and thereby improve the prediction of future temperature and air quality requirements for a climate control system, such as an HVAC system. This data includes the planning data, personal data, and environmental data mentioned above.

[0012] A particular advantage of the present invention is that the forecast accuracy is improved through the use of availability or planning data, occupancy or personnel data, and live environmental data. Thus, a system or control device controlled by the method can dynamically adapt to changing conditions, such as the number of people present or upcoming events that necessitate a change in environmental conditions. In particular, the control device is also capable of acquiring and analyzing planning data, personnel data, and environmental data in real time to enable predictive control of environmental conditions. Such control devices can therefore maximize both user comfort and energy efficiency.

[0013] To achieve these goals, the process comprises several steps to ensure an optimal environment. The process begins with the collection of planning data from a database. This planning data contains information about upcoming activities and their environmental requirements. The connection between the database and the processor is established through a suitable interface that guarantees a continuous and reliable data flow.

[0014] Furthermore, personal data is collected, reflecting the current locations and movements of individuals in real time. This data helps to understand and predict the dynamic use of the zone in terms of the number of people. Personal data is collected by various sensors and tracking systems installed in the zone's vicinity. The collected data is transmitted in real time to the central system, where it is available for further processing. The sensors and tracking systems are connected to the central processor via a network, enabling seamless and timely transmission of personal data.

[0015] The environmental data includes live information on temperature, humidity, lighting, and other relevant environmental parameters within the zone. This data is collected by various environmental sensors strategically placed throughout the zone. These sensors are connected to the central system via a communication network, ensuring the continuous transmission of the environmental data. The environmental data describes the current environmental state of the zone, including temperature, humidity, and air quality. Furthermore, the environmental data may include information on target temperatures for the heating zones and ventilation rates, as well as data from thermal imaging cameras used to determine surface temperatures (e.g., skin temperature). This data provides a snapshot of the current conditions within the zones and the people within them.

[0016] Based on the collected data, a projected occupancy of the zone is calculated. This calculation considers both planning data and occupancy data to enable an accurate prediction of future zone usage. Subsequently, a comfort environmental state for the zone is calculated, based on the planning data, occupancy data, environmental data, and the projected occupancy. This calculation aims to determine the optimal environmental conditions that maximize occupancy comfort. Finally, a climate control system for the zone is controlled based on the calculated comfort environmental state. This system can adjust temperature, humidity, and other environmental parameters to achieve the calculated optimal state.

[0017] The collection of planning and personnel data enables proactive and precise control of environmental conditions, while real-time environmental data acquisition ensures that any deviations can be corrected immediately. Calculating anticipated occupancy and comfort levels allows for predictive adjustments to the climate control system, leading to improved energy efficiency and a higher level of comfort. By combining these steps, the system addresses the challenge of managing changing environmental conditions in real time and enabling more precise control of climate control systems.

[0018] When controlling a climate control system for at least one zone, the calculated comfort environmental conditions are transmitted to the climate control system as control parameters. This climate control system can be connected to the central processor via a control network, enabling real-time adjustment of the environmental conditions within the zone. Control is achieved through targeted adjustments of air conditioners, heaters, fans, and other relevant equipment to reach and maintain the calculated comfort environmental conditions. The climate control system is typically an HVAC system and may include a heater, air conditioner, fan, etc.

[0019] Advantageous designs and further developments result from the further sub-claims as well as from the description with reference to the figures in the drawing.

[0020] According to one embodiment, capturing planning data for future events involves reading data from an event planner. This includes integrating an event planner capable of documenting and managing future events. The event planner can be in the form of a software application, such as a calendar, connected to the database from which the planning data is retrieved. This enables precise and up-to-date capture of planning data relevant for calculating the anticipated occupancy and comfort environment of the zone. Reading data from an event planner significantly improves the accuracy and relevance of the captured planning data, as it originates directly from a source specifically designed for event management.This reduces the likelihood of errors or inaccuracies that could occur with manual data entry or when using less specialized data sources. Furthermore, using an event planner allows for dynamic adjustments to the planning data, as changes or new events can be captured and addressed immediately. This is particularly important in environments where event planning is subject to frequent changes, such as conference centers, office buildings, event venues, or factories. The new features thus bring increased accuracy to the process by ensuring that the planning data is always up-to-date and precise.

[0021] According to another embodiment, the collection of personal data regarding the current locations and movements of individuals includes the acquisition of sensor data from at least one sensor. This sensor data contains location information about at least one person. These features thus enable more precise and up-to-date collection of personal data. By integrating sensors that continuously collect data on the locations and movements of individuals, real-time monitoring of people's movements within the zone is made possible. These sensors can utilize various technologies, such as infrared sensors, in particular cameras, RFID tags, or Bluetooth beacons, to collect accurate location information. The acquired sensor data is then transmitted to a central data processing unit, which analyzes this information and integrates it into the system or control device.This allows the system to capture and process current and dynamic occupant movements in real time. By considering this real-time data, the system can calculate a more accurate predicted occupancy of the zone and thus determine a more precise comfort environment. This leads to optimized control of the climate control system, as adjustments can be made based on the current and precise movement data of the occupants. The new features therefore improve the efficiency and accuracy of the system by enabling dynamic and adaptive control of the environmental conditions. This is particularly advantageous in environments where occupancy and occupant movement patterns can vary significantly, such as office buildings, conference centers, or public facilities.

[0022] According to another embodiment, acquiring environmental data regarding the current environmental conditions includes acquiring data from a temperature sensor within the zone. A temperature sensor can continuously or at regular intervals collect temperature data from the zone and transmit this data to the central control system. By directly acquiring the temperature, the system can react more quickly to changes in the environment and make corresponding adjustments to the climate control system to maximize the comfort of the occupants in the zone. The temperature sensor communicates with the central control unit via a wireless or wired network, which analyzes the acquired data and incorporates it into calculations for the comfort environmental conditions. Furthermore, the integration of temperature sensors allows for better adaptation to individual zones within a larger system.Since each zone has its own temperature sensors, the specific environmental conditions of each zone can be individually monitored and controlled, resulting in optimized and differentiated climate control. This is particularly advantageous in buildings with different usage areas, such as offices, conference rooms, or lounges, where varying temperature requirements may exist. The collection of environmental data can also include corresponding data from a sensor measuring humidity or air purity within the zone.

[0023] According to another embodiment, the environmental data includes information about a person's clothing, clothing changes, and / or activity level. Specifically, this environmental data is captured by a camera and extracted from the captured images using appropriate image recognition software. A clothing change refers to the detection of when a person, for example, puts on additional clothing. The activity level refers to a person's behavior, such as whether they are sitting or walking. This environmental data allows for a more accurate prediction of a comfortable environmental state, as individual clothing and activities are taken into account.

[0024] According to another embodiment, the predicted occupancy of the zone is calculated by an artificial intelligence trained on historical planning data, personal data, and environmental data. Specifically, the predicted occupancy is calculated using a neural network. The integration of artificial intelligence enables a dynamic and precise prediction of zone occupancy, as it is able to recognize complex patterns and relationships in the data that would be difficult for conventional algorithms to grasp. Training the artificial intelligence with historical planning data, personal data, and environmental data ensures that the predictions are based on a sound data foundation and can be continuously improved as more data becomes available.This leads to higher accuracy and reliability of the calculations, which in turn increases the efficiency of the climate control system.

[0025] According to another embodiment, the anticipated occupancy of the zone is calculated using a first Markov chain. A Markov chain is a mathematical model that describes a stochastic process chain in which the future state of a system depends only on its current state and not on the sequence of events that led to that state. Using a first Markov chain to calculate the anticipated occupancy of the zone allows for a more precise and dynamic occupancy prediction because it models the probability of transitions between different states. This is particularly useful in environments where the movements and locations of people are variable and difficult to predict. By implementing the Markov chain, the system can continuously calculate updated probabilities for zone occupancy, resulting in more accurate control of the climate control system.Furthermore, the Markov chain is a mathematically sound method for prediction that is less computationally intensive than alternative methods such as complex simulations or heuristic approaches.

[0026] According to another embodiment, calculating the comfort environmental conditions of the zone includes a comfort temperature range and a comfort ventilation rate. The comfort temperature range ensures that the temperature within the zone is regulated to a level that meets the comfort requirements of the occupants. This is achieved by processing planning data, occupancy data, environmental data, and the anticipated occupancy of the zone, thus enabling an accurate prediction of optimal temperature conditions. The comfort ventilation rate refers to the quantity and quality of air circulation within the zone, which is crucial for maintaining a pleasant and healthy indoor climate. By considering these two parameters—temperature and ventilation—a more comprehensive control of the environmental conditions is achieved, going beyond mere temperature regulation.Controlling an air conditioning system for at least one zone based on the comfort temperature range and comfort ventilation rate is achieved through targeted adjustments of the air conditioning system parameters to meet the calculated comfort conditions. This means that the air conditioning system adjusts the temperature and also regulates the ventilation rate to ensure that the air quality and circulation meet the calculated comfort requirements. These advanced control mechanisms improve energy consumption and contribute to the well-being of the occupants in the zone by ensuring a pleasant and healthy indoor climate.

[0027] According to another embodiment, the comfort environment state of the zone is calculated using a second Markov chain. Implementing a second Markov chain makes the calculation of the comfort environment state more precise and dynamic. The second Markov chain can model complex dependencies and transitions between different environmental states that cannot be captured by simple linear or static models. This enables more accurate prediction and real-time adjustment of the comfort environment state, based on the collected planning data, occupancy data, environmental data, and the anticipated occupancy of the zone. Furthermore, it requires less computational and storage resources than other artificial intelligence-based algorithms.Nevertheless, the second Markov chain can be further optimized through machine learning and continuous data analysis to improve the accuracy and efficiency of the calculations over time.

[0028] The above embodiments and further developments can be combined with one another as appropriate. In particular, the embodiments of the method can be applied, where technically feasible, to the control device for controlling an environmental state of a zone, and vice versa. Further possible embodiments, further developments, and implementations of the invention also include combinations of features of the invention described previously or subsequently with respect to the exemplary embodiments, even if not explicitly mentioned. In particular, those skilled in the art will also add individual aspects as improvements or additions to the respective basic form of the present invention. DESCRIPTION OF THE FIGURES

[0029] The present disclosure is further explained with reference to the drawings in which it is illustrated by way of example: Fig. 1 a schematic flowchart of a computer-implemented method for controlling an environmental state of a zone according to an embodiment of the invention; Fig. 2 a schematic representation of an area of ​​a building (e.g. apartment, floor, etc.) with a control device for controlling an environmental state of a zone according to an embodiment of the invention; Fig. 3 a schematic representation of a neural network for calculating the expected occupancy and comfort environmental state according to an embodiment of the invention; and Fig. 4 a schematic representation of a Markov model as a predictive model according to an embodiment of the invention.

[0030] The accompanying drawings are intended to provide a further understanding of the embodiments of the invention. They illustrate embodiments and, in conjunction with the description, serve to explain the principles and concepts of the invention. Other embodiments and many of the advantages mentioned will become apparent with reference to the drawings. The elements of the drawings are not necessarily shown to scale.

[0031] In the figures of the drawings, identical, functionally equivalent and equally effective elements, features and components - unless otherwise stated - are each provided with the same reference symbols.

[0032] Fig. 1 Figure 1 shows a flowchart illustrating the steps of a computer-implemented procedure for controlling the environmental state of Zone 1a-d. The procedure consists of several successive steps, labeled M1 to M6.

[0033] The first step, M1, involves capturing planning data 21 relating to the planning of future events from a database 12. This planning data may contain information about upcoming meetings, events, or other relevant activities scheduled to take place in Zone 1a-d. In certain embodiments, capturing planning data 21 includes reading an event planner, such as a software-based calendar.

[0034] In the second step, M2, personal data 22 regarding the current locations and movements of persons are collected. This data can be collected by various sensors 3a-d installed in zone 1a-d. The sensors can include, for example, cameras 4a-d or other types of motion sensors that monitor the position and movement of persons within zone 1a-d. In certain embodiments, the collection of personal data 22 regarding the current locations and movements of persons includes the collection of sensor data from at least one sensor 3a-d. The sensor data contains location information about at least one person. In certain embodiments, the sensor data is collected by a camera 3a-d.

[0035] The third step, M3, involves acquiring environmental data 23 relating to the current environmental state of at least one zone 1a-d. This environmental data can be collected by various environmental sensors, such as temperature sensors that measure the current temperature in zone 1a-d. In further embodiments, environmental data 23 are also acquired by other sensors, such as cameras 3a-d, and include clothing, changes in clothing, and / or a person's activity level, obtained through image recognition of the images acquired by the camera 3a-d.

[0036] In the fourth step, M4, a projected occupancy 24 of at least one zone 1a-d is calculated based on the planning data 21 and the personal data 22. This calculation can be performed by an artificial intelligence 13 or a first Markov chain 141 trained on the collected data.

[0037] In the fifth step, M5, a comfort environmental state 25, 26 of at least one zone 1a-d is then calculated based on the planning data 21, the personal data 22, the environmental data 23, and the expected occupancy 24 of zone 1a-d. This calculation can be performed using a second Markov chain 142 and includes parameters such as a comfort temperature range 25 and a comfort ventilation rate 26.

[0038] The sixth step, M6, involves controlling an air conditioning system 2a-d for at least one zone 1a-d based on the calculated comfort environmental condition. This means that the air conditioning system is controlled to maintain the comfort temperature range 25 and the comfort ventilation rate 26 in zone 1a-d.

[0039] The figure shows a clear and systematic representation of the procedure, with each step logically building on the previous one and contributing to achieving the final goal of optimally controlling the environmental state of zone 1a-d.

[0040] Fig. 2 Figure 1 shows a schematic representation of an apartment 100 with a control device 10 for controlling an environmental condition in several zones 1a-d. The system comprises a control device 10 with a processor 11 and a database 12. The control device 10 is connected to several climate control units 2a-d, each assigned to a specific zone 1a-d and designed to control the environmental condition in the respective zone 1a-d.

[0041] In Fig. 2 Four zones 1a-d are identifiable in apartment 100, each equipped with at least one camera 3a-3d and one temperature sensor 4a-4d. In the largest zone 1a, which serves as a corridor for the other zones 1b-d (designed as rooms), two cameras 3a1 and 3a2 are installed in addition to a temperature sensor 4a, enabling coverage of the entire zone 1a. It is understood that in further embodiments, zones 1a-d may also include outdoor areas such as terraces, balconies, or gardens.

[0042] Zones 1a-d are separated from each other by walls and contain various sensors 3a-d and 4a-d. The sensors 3a-d, designed as cameras, function as motion or presence sensors, recording data on the current locations and movements of people in the respective zones. The sensors 4a-d are temperature sensors that can detect the temperature of a zone 1a-d and transmit it to the control device 10. In further embodiments, humidity sensors or air quality sensors are provided or integrated into the temperature sensors 4a-d, which can provide information on the humidity or air purity of the corresponding zone 1a-d.

[0043] The control device 10 is designed such that a processor 11 of the control device 12 reads or records planning data 21 from the database 12. This planning data relates to future events and is read from an event planner, such as a calendar. In addition, the control device 10 records personal data 22 from the sensors 3a-d and cameras 4a-d, which provide information about the current locations and movements of the people.

[0044] Environmental data 23 concerning the current environmental condition in zones 1a-d are also recorded. This data can originate from various environmental sensors, such as temperature sensors 4a-d, which are installed in zones 1a-d. In further embodiments, clothing, changes in clothing, and / or a person's activity level are also recognized by image processing based on the images captured by the cameras 3a-d and integrated into the environmental data 23.

[0045] Based on the recorded planning data 21, personal data 22 and environmental data 23, the control device 10 calculates a projected occupancy 24 of zones 1a-d. This calculation can be performed by an artificial intelligence 13 trained with the relevant data, or by a first Markov chain 141.

[0046] Additionally, the control device 10 calculates a comfort environmental condition 25, 26 for zones 1a-d. This comfort environmental condition 25, 26 includes a comfort temperature range 25 and a comfort ventilation rate 26. The calculation of the comfort environmental condition can be performed by a second Markov chain 142.

[0047] The climate control systems 2a-d are controlled based on the calculated comfort environmental conditions to achieve the desired environmental conditions in the respective zones 1a-d. This includes adjusting the temperature and ventilation rate in the zones.

[0048] The control device 10 and its associated components are configured to enable efficient and precise control of the environmental conditions in the various zones 1a-d. The integration of the various sensors, data sources, and calculation algorithms ensures that the comfort of people in the zones is optimized by taking future events and current movements into account.

[0049] The Fig. 2 The diagram also shows the connections between the various components of the system. Cameras 3a-d and temperature sensors 4a-d are strategically positioned in zones 1a-d to ensure comprehensive acquisition of the relevant data. The climate control units 2a-d are also installed in zones 1a-d and are controlled by the control unit 10. Thus, the climate control units 2a-d, cameras 3a-d, and temperature sensors 4a-d are connected to the processor 11 of the control unit 10.

[0050] In summary, it illustrates Fig. 2 the structure and function of a system for controlling the environmental state in multiple zones, integrating various data sources and calculation algorithms to optimize the comfort of people in the zones.

[0051] Fig. 3 Figure 1 shows a schematic representation of a neural network 13 as an example of artificial intelligence 13 for calculating the expected occupancy and the comfort environment according to an embodiment of the invention. The neural network 13 receives input data from three different sources: planning data 21, personal data 22, and environmental data 23. These data sources are each represented by separate input nodes in the neural network.

[0052] The planning data 21 comprises information on future events retrieved from a database. This data is particularly helpful for predicting zone occupancy, as it provides information on when and where specific events will occur. The personnel data 22 contains information on the current locations and movements of people, recorded by sensors. The environmental data 23 relates to the current environmental conditions of the zone, such as temperature, and in further embodiments also humidity and air quality, and can be recorded by appropriate sensors within the zone, as described above.

[0053] Neural network 13 processes this input data through multiple layers of neurons connected by weighted connections. These connections are represented in the figure by lines linking the different neurons. Data processing is performed by applying activation functions to the weighted inputs, resulting in the output data.

[0054] The output data of the neural network includes the expected occupancy 24 of the zone as well as the comfort environmental state, which is divided into two components: the comfort temperature range 25 and the comfort ventilation rate 26. This output data is used to control the climate control systems 2a-d of zones 1a-d and thus ensure optimal comfort for the people in zone 1a-d.

[0055] Fig. 4Figure 14 shows a schematic representation of a Markov model 14 as a predictive model according to an embodiment of the invention. This model 14 is a matrix-based predictive model, wherein the matrices contain probabilities for the corresponding events derived from historical data. The calculations are performed using two separate Markov chains 141 and 142. The planning data 21, personnel data 22, and environmental data 23 are fed into a first Markov chain 141, which calculates the expected occupancy 24 of the zone. This Markov chain uses state transition probabilities to predict future occupancy based on current and historical data.

[0056] The anticipated occupancy 24 and the original input data 21, 22, 23 are then fed into a second Markov chain 142, which calculates the comfort environmental state of the zone. This second Markov chain calculates the comfort temperature range 25 and the comfort ventilation rate 26 based on the state transition probabilities and the current environmental conditions.

[0057] The output data from the second Markov chain 142 is used to control the climate control system of the zone. By using Markov chains, the system can achieve a more precise and dynamic adjustment of the environmental conditions in the zone, based on predicted occupancy and environmental data.

[0058] Both figures clearly show that the planning data 21, personal data 22, and environmental data 23 play central roles in calculating the expected occupancy 24 and the comfort environment 25, 26. These data sources are therefore advantageous for the effective control of the climate control system and for ensuring optimal comfort in the zone.

[0059] Although the present invention has been fully described above with reference to preferred embodiments, it is not limited thereto, but can be modified in many different ways. Reference symbol list

[0060] 1a-d Climate control unit 2a-d Zone 3a-d Camera 4a-d Sensor 10 Computing unit 11 Processor 12 Database 13 Artificial intelligence 14 Markov model Predictive model 21 Planning data 22 Personal data 23 Environmental data 24 Expected occupancy 25 Comfort temperature range 26 Comfort ventilation rate 100 Apartment 141 First Markov chain 142 Second Markov chain M1-M6 Process steps

Claims

1. Computer-implemented method for controlling an environmental state of a zone (1a-d), comprising: collecting (M1) planning data (21) relating to a plan of future events from a database (12), collecting (M2) personal data (22) relating to current locations and movements of people, collecting (M3) environmental data (23) relating to a current environmental state of at least one zone (1a-d), calculating (M4) a predicted occupancy (24) of the at least one zone (1a-d) based on the planning data (21) and the personal data (22), calculating (M5) a comfort environmental state (25, 26) of the at least one zone (1a-d) based on the planning data (21), the personal data (22), the environmental data (23) and the predicted occupancy (24) of the zone (1a-d), controlling (M6) an air conditioning system (2a-d) for the at least one zone (1a-d) based on the calculated comfort environmental condition.

2. Method according to claim 1, characterized by thatThe acquisition of planning data (21) relating to the planning of future events includes reading from an event planner.

3. Method according to any of the foregoing claims, characterized by that The recording of personal data (22) relating to current locations and movements of persons includes the recording of sensor data from at least one sensor (3a-d), wherein the sensor data contains location information about at least one person, and wherein the sensor data is recorded in particular by a camera (3a-d).

4. Method according to any of the foregoing claims, characterized by that The acquisition of environmental data (23) relating to a current environmental condition includes the acquisition of data from a temperature sensor (4a-d) in the zone (1a-d).

5. Method according to any of the foregoing claims, characterized by thatthe environmental data (23) include clothing, changes in clothing and / or activity levels of a person, in particular captured by a camera (3a-d).

6. Method according to any of the foregoing claims, characterized by that The calculation of the expected occupancy (24) of the zone (1a-d) is carried out by an artificial intelligence (13), in particular by a neural network (13) which was trained with historical planning data (21), personal data (22) and environmental data (23).

7. Method according to any of the foregoing claims, characterized by that the calculation of the expected occupancy (24) of the zone (1a-d) is carried out by a first Markov chain (141).

8. Method according to any of the foregoing claims, characterized by thatthe calculation of the comfort environmental condition (25, 26) of the zone (1a-d) includes a comfort temperature range (25) and a comfort ventilation rate (26), and the control of an air conditioning system (2a-d) is preferably carried out for the at least one zone (1a-d) based on the comfort temperature range (25) and the comfort ventilation rate (26).

9. Method according to any of the foregoing claims, characterized by that The calculation of the comfort environmental state of zone (1a-d) is carried out by a second Markov chain (142).

10. Control device (10) for controlling an environmental state of a zone (1a-d), comprising a computing device comprising: - a database (12) containing information on future events, and - a processor (11) adapted to execute the method according to any of the preceding claims.

11. Computer program comprising commands that cause the control device (10) according to claim 10 to perform the method steps according to any one of claims 1 to 9.

12. Computer-readable storage medium on which the computer program according to claim 11 is stored.

Images