Method and apparatus for operating a wireless communication network

Abstract

A method for operating a wireless communication network (4), the wireless communication network comprising a plurality of spatially separated communication interfaces (iT1-iT3, iAP), wherein the method comprises: configuring at least a part of the plurality of communication interfaces (iT1-iT3, iAP) according to an estimated future connection quality (q(t2)). Also disclosed is a device for operating a wireless communication network.

Description

Technical Field

[0001] The present invention relates to a method for operating a wireless communication network and an apparatus for operating a wireless communication network. Background Art

[0002] Knowing the quality of a connection between two points is either performed by measurements for the current moment in time.

[0003] Furthermore, it is known from radio network planning to estimate the connection quality based on an environment model. Summary of the invention

[0004] The problem of the prior art is solved by a method according to claim 1 and by a device according to the independent parallel claim. Advantageous developments are specified in the dependent claims.

[0005] According to the first aspect of the present specification, a method for operating a wireless communication network, the wireless communication network includes a plurality of communication interfaces separated from each other in space, wherein the method includes: determining the actual spatial position at which each of the plurality of communication interfaces is located; determining the actual connection quality of a radio connection established or that can be established between two of the plurality of communication interfaces respectively; determining the future spatial position at which each of the plurality of communication interfaces is expected to be located at a future moment; determining the future connection quality of a radio connection established or that can be established between at least two of the plurality of communication interfaces respectively at a second moment based on the actual position, based on the actual connection quality and based on the future position; and configuring at least a portion of the plurality of communication interfaces based on the estimated future connection quality.

[0006] The future connection quality represents a measure that can be easily used to reconfigure the communication network.Therefore, an advantageous mapping of actual status and expected future status to the future connection quality is performed.

[0007] By means of the estimated future connection quality, a targeted reconfiguration of the wireless communication network is advantageously carried out to ensure uninterrupted communication with a high connection quality. In particular, in scenarios in which objects including communication interfaces move, the prediction of the future connection quality makes it possible to improve the availability of the communication network in general.

[0008] The estimated future connection quality advantageously supplements and completes the spatial future representation, so that the prediction foresees a connection loss or a degradation of the connection and can be prevented by corresponding countermeasures in the form of a configuration.

[0009] In the field of industrial automation, for example, new real-time applications can be realized or initially made possible by the proposed method.

[0010] A favourable example is characterized in that the method comprises: propagating the determined actual position, the determined actual connection quality and the future position via a learned artificial neural network, wherein the actual position, the actual connection quality and the future position are provided as input variables in the input area of ​​the artificial neural network, and wherein a prediction that can be used to determine the estimated future connection quality is provided in the output area of ​​the artificial neural network.

[0011] Advantageously, the artificial neural network is used to take into account the scenario dynamics contained in the mapped actual situation when reconfiguring the communication network.The provision of the prediction allows an estimation of the future connection quality.

[0012] An advantageous example is characterized in that the method comprises determining the actual position and / or the future position based on sensor data, the sensor data being provided by a sensor at least partially observing the space.

[0013] Advantageously, the information, which represents for example the actual position of the respective communication interface, is enriched by the sensor data or is only provided by the sensor data. Thus, the information is increased by adding the sensor data.

[0014] A favorable example is characterized in that the method includes: identifying at least one object and its position in the space based on the sensor data; linking the identified object with one of the multiple communication interfaces; and determining the position of the one of the multiple communication interfaces based on the position of the object linked to the one of the multiple communication interfaces.

[0015] The proposed data fusion advantageously improves the position determination for the communication interface.

[0016] A favourable example is characterized in that the method comprises determining the actual position and / or the actual connection quality and / or the future position based on monitoring physical radio channels that have been used for wireless communication by means of the multiple communication interfaces and physical radio channels that can be used for wireless communication by means of the multiple communication interfaces.

[0017] The actual position and / or the estimated future position of the communication interface is determined by the provided monitoring without the need for providing additional hardware for this purpose. Instead, existing hardware can be used.

[0018] A favorable example is characterized in that configuration of at least a portion of the communication interfaces includes: establishing a first radio connection between at least two communication interfaces of the communication network; establishing a second radio connection between the at least two communication interfaces based on the estimated future connection quality; and switching the communication path from the first radio connection to the second radio connection.

[0019] Advantageously, this type of preventive radio channel switching can be used to prevent an undesired interruption of the first radio connection or a degradation of the connection quality of the first radio connection. The availability of the communication within the wireless communication network is thereby increased.

[0020] A second aspect of the present specification relates to a device for operating a wireless communication network, wherein the device includes at least one processor and a memory having computer program code, wherein the computer program code is executed by the processor so that the device determines the actual spatial position at which each of a plurality of communication interfaces is located; determines the actual connection quality of a radio connection established or that can be established between two of the plurality of communication interfaces; determines the future spatial position at which each of the plurality of communication interfaces is expected to be located at a future moment; determines the future connection quality of a radio connection established or that can be established between at least two of the plurality of communication interfaces at a second moment based on the actual position, based on the actual connection quality and based on the future position; and configures at least a portion of the plurality of communication interfaces based on the estimated future connection quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In the attached picture:

[0022] Figure 1 A schematic diagram of an exemplary scene with a space is shown;

[0023] Figure 2 shows the training of a schematic representation of an artificial neural network;

[0024] Figure 3 shows the use of a schematic representation of a trained artificial neural network; and

[0025] Figure 4 and Figure 5 Representatives of the spaces are shown respectively. DETAILED DESCRIPTION

[0026] Figure 1A schematic diagram is shown of an exemplary scenario 2 with a space in which a wireless communication network 4 is operated. The wireless communication network 4 comprises, for example, a number of mobile terminals T1, T3 and / or fixed terminals such as terminal T2. The communication network 4 further comprises access points AP.

[0027] The terminals T1 to T3 and the access point AP respectively include at least one communication interface iT1 to iT3 and iAP. The communication interfaces iT1 to iT3 are, for example, constructed to establish radio connections with each other, such as a radio connection C23. The communication interface iAP provides access to another network area NA. Thus, for example, a radio connection C1AP is established between the communication interface iAP and the communication interface iD1. Thus, the access point AP provides the terminals T1 to T3 with the possibility of communicating with a remotely arranged network unit NE via a communication path CP. Here, the communication path CP includes a radio connection C1AP and at least one other connection Cx between the access point AP and the remotely arranged network unit NE. The network unit NE is, for example, not part of the communication network 4, but is arranged in another network area NA of the respective enterprise to which the communication network 4 is also assigned, or is arranged in a wide area network.

[0028] In addition to the terminals T1 to T3 and at least one access point AP, which represent radio objects, scenario 2 also includes other passive objects O1 and O2, which influence the radio traffic between the terminals T1 to T3 and the access point AP. In the example shown, the radio connection C1AP is not covered by one of the passive objects O1 and O2. The radio connection C1AP is, for example, less affected by signal attenuation than the radio connection C3AP between the communication interface iT3 and iAP, because the communication interface iT1 and iAP have line-of-sight contact, i.e. there is an imaginary straight line connection between the communication module iT1 and iAP that is not directly covered by passive objects or radio objects. In the case of the radio connection C3AP, a higher signal attenuation must be expected compared to the radio connection C1AB.

[0029] If the mobile terminal T1 moves with the assigned communication module iT1 along the trajectory tT1 starting from a first moment, the mobile terminal T1 reaches the position pT1 at a second future moment and is blocked by the passive object O1 from the perspective of the access point AP. That is, the communication module iT1 and iAP have no visual contact at the second moment. Therefore, it must be assumed at the second moment that the signal attenuation for the radio connection C1AP is increased. In another example, it is also conceivable that one of the mobile terminals is located between the first terminal T1 and the access point AP at the second moment.

[0030] The scene 2 or the allocated space is at least partially detected by at least one sensor S, whose sensor data SD are supplied to the device 100. The sensor S is, for example, a camera, a radar sensor, a lidar sensor or an ultrasonic sensor. Of course, a plurality of different types of sensors can also be used to monitor the scene. The device 100 comprises at least one processor and a memory, on which a computer program is stored. When the computer program is executed on the processor, the method steps explained in this specification are performed.

[0031] The access point AP or its communication interface iAP allows observing used and unused radio channels or the entire radio traffic in the communication network 4. The radio observations Obs are transmitted to the device 100 and used for determining the first or second representative.

[0032] According to block 102 of the device 100, an actual spatial position p(t1) at which a respective communication interface of the plurality of communication interfaces iT1 to iT3, iAP is located at a first moment, in particular the current moment, is determined. The actual position p(t1) is determined, for example, based on radio observations Obs and / or based on sensor signals SD.

[0033] Block 104 determines the actual connection qualities q(t1) of the radio connections respectively established between at least two of the plurality of communication interfaces iT1 to iT3, iAP at the first instant in time. These actual connection qualities q(t1) are determined based on radio observations Obs.

[0034] Box 106 determines the respective future spatial positions p(t2) at which the plurality of communication interfaces iT1 to iT3, iAP are expected to be located at a second moment later than the first moment. This is done, for example, by observing the trajectories of the respective communication interfaces iT1 to iT3, iAP, wherein, for example, in addition to the actual positions at the first moment, the associated speed and direction can also be determined. Accordingly, an estimated area is obtained, in which the respective communication interfaces iT1 to iT3, iAP may be located at the second moment. A position in the sense of the spatial position p(t2) can then be selected from the estimated area. Alternatively, the estimated area can also be determined with the aid of box 106, which may still have probabilities associated with the respective positions. Alternatively or additionally, the communication interfaces iT1 to iT3, iAP can transmit the planned trajectories to the device 100, wherein the respective future positions are determined based on the trajectories. In one example, the future position p(t2) is estimated based on the actual position p(t1).

[0035] Block 108 determines the future connection quality q(t2) of the radio connection established or establishable at the second time between at least two of the plurality of communication interfaces iT1 to iT3, iAP, respectively. The connection quality q(t2) is determined as a function of the actual position p(t1), as a function of the actual connection quality q(t1) and as a function of the future position p(t2).

[0036] Block 108 comprises, for example, an artificial neural network which determines the future connection quality q(t2).

[0037] Block 110 determines the configuration Conf of at least some of the communication interfaces iT1 to iT3, iAP based on the estimated future connection quality q(t2). Advantageously, this makes it possible, for example, to clear existing radio connections and establish new radio connections in advance before a connection loss occurs, which can be predicted by the future connection quality q(t2). At least some of the communication interfaces iT1 to iT3, iAP of the communication network 4 are configured accordingly.

[0038] Then, when it is expected that one of the possible radio channels will degrade at the second moment t2, i.e., for example, when line of sight contact is lost, the configuration Conf is determined and executed. Thus, for example, the communication is carried out via a newly established radio channel, the expected signal attenuation of which is lower than that of the existing radio connection at the second moment, if the existing radio channel still exists at the second moment. For example, the moving terminal switches to a radio connection at an access point not shown, which is not the access point AP, before entering the second moment. The configuration Conf is distributed to the terminals T1 to T3, for example, via the access point AP. Then, before or at the time of entering the second moment, the communication interfaces iT1 to iT3 and iAP are partially or completely reconfigured. The reconfiguration includes, for example, the separation and establishment of radio channels, the increase or decrease of the reception strength and / or the transmission strength and / or the data rate and / or the packet rate, the switching of the frequency band, the switching of the modulation and coding scheme, etc. Within the scope of the configuration, for example, coordination between the existing access points is performed.

[0039] The device for training the artificial neural network is Figure 3 The training data E is provided in the form of recorded actual position p(t1), actual connection quality q(t1) and future position p(t2) train .

[0040] The apparatus comprises an artificial neural network 200 having an input layer. For time step i, the input tensor e is input i trainis passed to the input layer. For input E, output O is determined in the form of a prediction of output O or the output O is known in advance. From output O, a tensor o with observations at time step i is determined i train , the observations are assigned to the tensor e i train Observations of E. Each time series of the input E is assigned to one of the three input nodes. In the forward path of the artificial neural network 200, at least one hidden layer follows the input layer. In this example, the number of nodes of the at least one hidden layer is greater than the number of input nodes. This number is considered a hyperparameter and is preferably determined separately. In this example, four nodes are set in the hidden layer. The artificial neural network 200 is taught, for example, by a method of gradient descent according to the back-propagation form. Therefore, the artificial neural network 200 is trained in a monitored manner.

[0041] Of course, the neural network 200 can also be taught in different ways. Thus, for example, the highest possible connection quality can be set as a learning goal, and the artificial neural network 200 can be taught by monitored learning. In contrast, in the case of reinforcement learning, an objective function is used, such as a minimum connection failure rate.

[0042] In the forward path, an output layer 202 is provided after the at least one hidden layer in this example. The predicted values ​​are output at the output layer 202. In this example, one output node is assigned to each predicted value.

[0043] At each time step i, determine the tensor o' i train , which contains the predicted value for time step i. In this example, the tensor is combined with the column vector o of the observed values. i train The training device 204 is configured to determine the prediction error by means of a loss function LOSS (in particular by means of a mean square error) and to train the model using the prediction error and by means of an optimizer (in particular an Adam optimizer). The loss function LOSS in this example is a tensor o according to the observed value. i train and the tensor o' of predicted values i train The deviation between them, especially the mean square error, is used to determine it.

[0044] Once a set criterion is reached, the training is interrupted. In this example, the training is interrupted when the loss no longer decreases over a number of time steps, ie, in particular, the mean square error does not decrease.

[0045] The test data is then fed into the model trained in this way. The model is generated by training using the training data. The model is evaluated using the test data, in particular with respect to the mean and covariance to evaluate the model.

[0046] according to Figure 3 The apparatus shown in , uses the trained model for providing a prediction of the connection quality for the supplied input E. For this purpose, the same data preprocessing steps as in the case of the training data are performed. For example, scaling and determination of the input data and output data are performed. In this example, this determination is performed during the operation of the device 100, that is, in the operation of the wireless communication network 4.

[0047] A digital image that may contain an object to be classified is input into a trained artificial neural network 200. A prediction value is determined based on this. A connection quality score is determined based on this.

[0048] exist Figure 3 The apparatus for determining the quality of the future connection is schematically shown in FIG. As described for training, for time step i, the column vector e of the input E is i By means of block 201, it is transferred to the input layer. After that, unlike training, the device 300 performs a 'i A prediction is performed on the future connection quality.

[0049] The connection quality score is derived for the future connection quality q(t2) and is transmitted to the device 110. In this example, if the connection quality score exceeds a threshold , then the connection quality indicates a future line-of-sight connection, otherwise it does not indicate a future line-of-sight connection. In addition, if the connection quality score is below another threshold, then the connection quality score may indicate that a connection cannot be made. Threshold Preferably, it is a parameter. The parameter is determined, for example, by maximizing a criterion such as precision or recall. For example, the criterion of area under the curve (AUC) or receiver operating characteristic (ROC) is used.

[0050] In particular, for carrying out the described method, instructions of a computer program are provided which implement the artificial neural network 200. Special-purpose hardware may also be provided, in which the trained model is mapped.

[0051] Figure 4A representation R1 of a space monitored by sensors Sa and Sb is shown. In the first representation, a vehicle V1 is moving in a direction r. There are respective line-of-sight radio connections 402, 404 between two access points APa and APb and the industrial robot IR, which are not covered by objects O1, O2 or O3 located in the space.

[0052] exist Figure 5 A second representation R2 of the space is shown, which is in the future based on the first representation R1 and is obtained by means of Figure 2 and Figure 3 The artificial neural network 200 therefore determines that at a future moment, i.e., at a second moment, the vehicle V1 interrupts Figure 4 The line-of-sight connection 404 is lost because the vehicle blocks the industrial robot IR relative to the access point APa. A corresponding reconfiguration may, for example, include increasing the transmission power and the reception power of the respective communication interfaces of the industrial robot IR and the access point APb.

Claims

1. A method for operating a wireless communication network (4) in a space at least partially monitored by a sensor, the wireless communication network comprising a plurality of communication interfaces (iT1-iT3, iAP) separated from each other in space, wherein the method comprises: determining an actual spatial position (p(t1)) at which a respective communication interface of the plurality of communication interfaces (iT1-iT3, iAP) is located, determining an actual connection quality (q(t1)) of a radio connection established or establishable between two communication interfaces of the plurality of communication interfaces (iT1-iT3, iAP), determining a spatial future position (p(t2)) at which each of the plurality of communication interfaces (iT1-iT3, iAP) is expected to be located at a future time, determining a future connection quality (q(t2)) of a radio connection established or establishable at the future time between at least two of the plurality of communication interfaces (iT1-iT3, iAP) based on the actual position (p(t1)), based on the actual connection quality (q(t1)) and based on the future position (p(t2)), wherein determining the future connection quality of the radio connection comprises determining whether the at least two communication interfaces (iT1-iT3, iAP) have line of sight contact at the future time, and configuring at least a portion of the plurality of communication interfaces (iT1-iT3, iAP) according to an estimated future connection quality (q(t2)), wherein at least a portion of the plurality of communication interfaces is reconfigured when it is expected that the line of sight contact will be lost at the future time, Therein the actual position (p(t1)) and / or the future position (p(t2)) are determined based on sensor data (SD) provided by sensors at least partially monitoring the space.

2. The method according to claim 1, wherein: The method comprises: The determined actual position (p(t1)), the determined actual connection quality (q(t1)) and the future position (p(t2)) are propagated via a learned artificial neural network (200), wherein the actual position (p(t1)), the actual connection quality (q(t1)) and the future position (p(t2)) are provided as input variables (E) in an input region of the artificial neural network (200), and wherein a prediction that can be used to determine the estimated future connection quality (q(t2)) is provided in an output region of the artificial neural network (200).

3. The method according to claim 1, wherein: The method comprises: identifying at least one object and its position in said space based on said sensor data (SD), An identified object is linked to one of the multiple communication interfaces (iT1-iT3, iAP), and a position (p(t1), p(t2)) of the one communication interface (iT1-iT3, iAP) is determined based on the position of the object linked to the one of the multiple communication interfaces (iT1-iT3, iAP).

4. A method according to any one of the preceding claims, wherein: The method comprises: Based on monitoring the radio channels that have been used for wireless communication with the help of the multiple communication interfaces (iT1-iT3, iAP) and the radio channels that can be used for wireless communication with the help of the multiple communication interfaces (iT1-iT3, iAP), the actual position (p(t1)) and / or the actual connection quality (q(t1)) and / or the future position (p(t2)) are determined.

5. A method according to any one of the preceding claims, wherein: The configuration of at least a portion of the communication interfaces includes: establishing a first radio connection between at least two communication interfaces (iT1-iT3, iAP) of the communication network (4), establishing a second radio connection between the at least two communication interfaces (iT1-iT3, iAP) according to the estimated future connection quality (q(t2)), and A communication path (CP) is switched from the first radio connection to the second radio connection.

6. A device (100) for operating a wireless communication network (4) in a space at least partially monitored by a sensor, wherein the wireless communication network comprises a plurality of communication interfaces (iT1-iT3, iAP) separated from each other in space, wherein the device (100) comprises at least one processor and a memory with a computer program code, wherein the computer program code is executed by the processor so that the device (100) determining an actual spatial position (p(t1)) at which a respective communication interface of the plurality of communication interfaces (iT1-iT3, iAP) is located, determining an actual connection quality (q(t1)) of a radio connection established or establishable between two communication interfaces of the plurality of communication interfaces (iT1-iT3, iAP), determining a spatial future position (p(t2)) at which each of the plurality of communication interfaces (iT1-iT3, iAP) is expected to be located at a future time, The device (100) is configured to determine a future connection quality (q(t2)) of a radio connection established or capable of being established between at least two of the plurality of communication interfaces (iT1-iT3, iAP) at the future moment in time based on the actual position (p(t1)), based on the actual connection quality (q(t1)) and based on the future position (p(t2)), wherein the device (100) determines whether at least two of the plurality of communication interfaces (iT1-iT3, iAP) have line-of-sight contact at the future moment in time, and configures at least a portion of the plurality of communication interfaces (iT1-iT3, iAP) based on the estimated future connection quality (q(t2)), wherein the device (100) reconfigures at least a portion of the plurality of communication interfaces when the device (100) expects that the line-of-sight contact will be lost at the future moment in time, The device (100) determines the actual position (p(t1)) and / or the future position (p(t2)) based on sensor data (SD) provided by sensors that at least partially monitor the space.

Images