Wireless communication device and method for handover prediction

Abstract

The invention discloses a wireless communication device. The wireless communication device includes a transceiver group and a processor electrically connected to the transceiver group. The transceiver group is configured to simultaneously communicate with a first base station over a first channel according to a first frequency band setting and to communicate with a second base station over a second channel according to a second frequency band setting different from the first frequency band setting. The processor is configured to: generate a first predicted time to arrive at a first handover event corresponding to the first base station using a handover prediction model; generating a second predicted time to a second handover event corresponding to the second base station using the handover prediction model; and determining whether to change one of the first frequency band setting and the second frequency band setting according to the first prediction time, the second prediction time and a first critical value.

Description

Technical Field

[0001] The present disclosure relates to wireless communication devices and methods; more particularly, to wireless communication devices and methods for handoff prediction. Background Art

[0002] Wireless transmission technology has gradually evolved from 4G Long Term Evolution (LTE) to 5G New Radio (NR). In 5G NR networks, a key application scenario is Ultra-Reliable and Low Latency Communications (URLLC), which is used to achieve ultra-low latency and high reliability communications.

[0003] For example, Communication Based Train Control (CBTC) is a high-speed mobile application in the signaling system that uses wireless communication between the onboard and ground track equipment (or trackside equipment) to operate and control the train, achieving convenient and accurate traffic management. In the application of CBTC, high-speed trains need to communicate with ground track equipment with low latency and high reliability to prevent accidents. However, wireless transmission on high-speed moving trains will be affected by multiple handover (HO) and radio link failure (RLF) events, resulting in reduced transmission quality. As a result, data transmission delays and packet loss will increase.

[0004] Therefore, a wireless communication device and method with low latency and high reliability in CBTC is needed. Summary of the invention

[0005] The present disclosure provides a wireless communication device. The wireless communication device includes a transceiver group and a processor electrically connected to the transceiver group. The transceiver group is configured to simultaneously communicate with a first base station through a first channel according to a first frequency band setting, and communicate with a second base station through a second channel according to a second frequency band setting different from the first frequency band setting. The processor is configured to: use a handover prediction model to generate a first prediction time for a first handover event corresponding to the first base station; use the handover prediction model to generate a second prediction time for a second handover event corresponding to the second base station; and, based on the first prediction time, the second prediction time and a first critical value, determine whether to change one of the first frequency band setting and the second frequency band setting.

[0006] Furthermore, the present disclosure provides a wireless communication method. The wireless communication method includes: simultaneously communicating with a first base station through a first channel according to a first frequency band setting and communicating with a second base station through a second channel according to a second frequency band setting; using a handover prediction model to generate a first prediction time of a first handover event corresponding to the first base station; using the handover prediction model to generate a second prediction time of a second handover event corresponding to the second base station; and judging whether to change one of the first frequency band setting and the second frequency band setting according to the first prediction time, the second prediction time and a first critical value.

[0007] In summary, the wireless communication device and method for handover prediction can use the handover prediction model to generate individual prediction times corresponding to handover events of different base stations, and determine whether to change the frequency band setting of the transceiver according to the prediction times to prevent multiple handover events from occurring, thereby reducing the delay and packet loss caused by multiple handover events. Therefore, reliability can be improved and delay can be reduced in the communication train control system.

[0008] Simple diagram description

[0009] The various aspects of the present disclosure can be best understood when reading the following detailed description and the accompanying drawings. It should be noted that the various features in the drawings are not drawn to scale, in accordance with standard operating practices in the art. In fact, the size of certain features may be deliberately enlarged or reduced in order to be clearly described.

[0010] Figure 1 FIG. 4 is a schematic diagram of a wireless communication device according to an embodiment of the present disclosure.

[0011] Figure 2 is a table showing the relationship between the turnover types and event categories according to an embodiment of the present disclosure.

[0012] Figure 3 It is a schematic diagram showing an input feature sequence and a prediction range corresponding to collected data according to an embodiment of the present disclosure.

[0013] Figure 4 It shows that according to one embodiment of the present disclosure Figure 1 Deployment scenarios of wireless communication devices in .

[0014] Figure 5 The invention shows a wireless communication method executed by a wireless communication device on a vehicle according to an embodiment of the present disclosure.

[0015] Figure 6 is a flow chart showing how to determine whether to change a frequency band setting according to an embodiment of the present disclosure.

[0016] Figure 7 is a table showing triggering conditions for reconfiguration according to an embodiment of the present disclosure.

[0017] Implementation

[0018] Some variations of the embodiments are described herein. In the various views and illustrated embodiments, the same reference numerals are used to indicate the same elements. It should be understood that additional operations may be provided before, during, and / or after the disclosed method, and some operations described may be replaced or eliminated for other embodiments of the method.

[0019] The present disclosure provides a wireless communication device and a wireless communication method for handover (HO) prediction to avoid high delay and packet loss in a high-speed environment network (e.g., communication-based train control (CBTC)). The device and method use technologies including band locking technology and machine learning (ML) technology.

[0020] Band locking technology involves applying settings of the wireless communication device or the user so that each wireless interface of the wireless communication device is set to connect only to a subset of the predetermined frequency bands and prohibits connecting to the remaining available frequency bands provided by the base station. By implementing the band locking technology, the number of base station candidate channels to be considered can be reduced to avoid performing unnecessary HO procedures.

[0021] Machine learning (ML) techniques can automatically learn from data and past experience to identify features and make predictions, with a focus on using data and algorithms to mimic how humans learn, gradually improving their accuracy. For example, by using statistical methods, training algorithms to perform classification or prediction, and revealing key insights in data mining projects. These techniques can be particularly helpful.

[0022] These techniques may be particularly useful when the user is in a fast-moving train and the wireless communication device must undergo HO very frequently.Thus, by performing these techniques, abnormal performance is minimized by avoiding overlaps during HO between different wireless interfaces.

[0023] Figure 1 The wireless communication device 100 according to an embodiment of the present disclosure includes a control node 110, a transceiver group 120, and two antenna modules 32 and 34. Figure 1 In the embodiment of the present invention, the transceiver group 120 includes wireless transceivers 22 and 24, and the wireless transceivers 22 and 24 are respectively coupled to the antenna modules 32 and 34. In some embodiments, the transceiver group 120 includes one or more wireless transceivers and one or more antenna modules. The number of wireless transceivers and the number of antenna modules are only examples and are not intended to limit the present disclosure.

[0024] Each of antenna modules 32 and 34 includes a single antenna or an antenna array. Antenna modules 32 and 34 may have the same or different antenna configurations. In some embodiments, antenna modules 32 and 34 may include a single antenna with an omnidirectional radiation pattern, and the single antenna is capable of communicating with different base stations. In some embodiments, antenna modules 32 or 34 may include an antenna array, and the antennas of the antenna array are capable of communicating with at least two base stations.

[0025] Each wireless transceiver 22 and 24 includes one or more integrated transmitters (not shown) and receivers (not shown), or one or more sets of separate transmitters and separate receivers. In general, the receiver is capable of down-converting a received radio frequency (RF) signal or microwave signal to a baseband frequency, and the transmitter is capable of up-converting a received baseband signal to an RF signal or microwave frequency. In addition, each of the wireless transceivers 22 and 24 can be coupled to the control node 110 via an optical fiber, wireless or wired connection.

[0026] The wireless transceiver 22 and the antenna module 32 may form a first RF interface, and the wireless transceiver 24 and the antenna module 34 may form a second RF interface. In some embodiments, the first RF interface and the second RF interface are disposed at the same location. In some embodiments, the first RF interface and the second RF interface are disposed at different locations. For example, the wireless communication device 100 is disposed on a train, and the first RF interface is disposed at the front of the train compartment and the second RF interface is disposed in the middle of the train compartment or in another train compartment.

[0027] The control node 110 includes a processor 12 and a storage device 14. The processor 12 is electrically connected to the transceiver group 120 and is configured to control the transceiver group 120 to establish a communication link with two base stations according to different frequency band settings. The processor 12 can be a central processing unit (CPU), a microprocessor, a microcontroller, a field programmable gate array (FPGA) unit, a graphics programming unit (GPU), a customized integrated circuit (IC), etc.

[0028] In some embodiments, the processor 12 is used to control the transceiver 120 to communicate with two base stations using the same generation or different generations of communication technology. For example, the base station may be an evolved Node-Bs (eNB) of a 3GPP Long-Term Evolution (LTE) network or a gNodeB (gNodeBs, gNB) of a 5G New Radio (NR). A base station may also be referred to as an access point, an access terminal, a base station unit, or other terms used in the art. It should be noted that although the concepts disclosed herein are described in terms of 4G and 5G communication protocols or base stations, the disclosure is not limited to 4G and 5G communication systems and may be extended to other systems.

[0029] In some embodiments, each of the wireless transceivers 22 and 24 may support 3GPP cellular wireless communication standards, such as 4G, 5G, 6G, etc. The wireless transceivers 22 and 24 may support the same or different radio access technologies. Furthermore, the processor 12 is configured to control the wireless transceivers 22 and 24 to use different radio frequency groups. For example, the processor 12 may control the wireless transceiver 22 to use a first set of frequencies including frequencies f1 and f2, and control the wireless transceiver 24 to use a second set of frequencies including frequencies f3 and f4. In addition, the processor 12 may control the wireless transceiver 22 to use a frequency set including frequencies f1, f2, f3, and f4, and control the wireless transceiver 24 to use frequency f1.

[0030] In some embodiments, the processor 12 is configured to control the wireless transceivers 22 and 24 to use LTE / 5G dual mode, such as non-standalone 5G or standalone dual mode LTE / 5G. For example, the processor 12 may control the wireless transceiver 22 to use only LTE, and control the wireless transceiver 24 to use only standalone 5G. In addition, the processor 12 may control the wireless transceiver 22 to use only LTE, and control the wireless transceiver 24 to use both LTE and 5G.

[0031] The processor 12 is used to control the operation of the transceiver 120 according to the program instructions and data stored in the storage device 14. In some embodiments, the storage device 14 is a memory. The storage device 14 is further configured to store a data set for the HO prediction model and the frequency band configuration and a judgment condition for the policy control model. The HO prediction model and the policy control model are executed by the processor 12 or implemented in the processor 12. This data set includes data about HO / radio link failure (RLF) and signal strength. In some embodiments, data on the vehicle is collected in advance by a user equipment (UE) (such as a mobile device), and the vehicle is traveling on a fixed or known route. For example, the vehicle is a train or subway moving along a track path. The collected data may include packet information and signal messages between the UE and the base station collected along the track path when the UE sends a packet with a consistent yield to the base station. By analyzing the collected data, the HO type can be identified and classified.

[0032] Figure 2 is a table showing the relationship between HO types and event categories according to an embodiment of the present disclosure. Figure 2 In the table, HO types are identified and classified based on the events described in the 3GPP specifications. For example, as shown in the second to fourth columns of the table, HO types of LTE HO, Master Node (MN) HO, and MN HO to eNB are caused by E-UTRAN event A3 (neighboring cell is one offset better than special cell (SpCell)) and are classified as LTE HO events. As shown in the fifth and sixth columns of the table, HO types of Secondary Node (SN) HO and SN Release are caused by NR event A3 and are classified as NRHO events. As shown in the seventh to ninth columns of the table, HO types of SN setup, RLF, and SCG failure may be critical events that are not caused by event A3 and are not classified as LTE or NR HO events.

[0033] Event A3 is triggered when the neighboring cell is better than the SpCell by an offset. The special cell is the main serving cell of the Master Cell Group (MCG) or the Secondary Cell Group (SCG). Event A3 is typically used for same-frequency or different-frequency HO procedures. Event A3 provides a HO triggering mechanism based on relative measurement results. For example, it can be set to trigger when the signal quality measurement of the neighboring cell is stronger than the signal quality measurement of the special cell. Signal quality measurements may include Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), or Signal to Interference Noise Ratio (SINR).

[0034] The collected data includes information about signal strength (e.g., signal quality measurement) during a specific time interval and the occurrence of certain types of HO events or critical events. Based on the collected data, the processor 12 is configured to perform an ML task for HO event prediction using the HO prediction model to determine whether to change the frequency band setting of the transceiver group 120 to prevent multiple HO events, thereby reducing delays and packet losses caused by multiple HO events.

[0035] The HO prediction model disclosed herein may be first trained based on a plurality of training data sets. In some embodiments, each training data set includes input training data (e.g., RSRP during a time interval) and output training data (e.g., actual HO timing), and the training data set is collected by a UE. The training data set is used to train the HO prediction model by using a two-stage prediction method to predict HO events. In the first stage prediction, the training data set may be used to train the HO prediction model to predict whether the HO event will occur. In the second stage prediction, the training data set may be used to train the HO prediction model to predict when the HO event will occur. In some embodiments, a classifier is used in the first stage prediction to determine whether the HO event is about to occur, and a regressor is used in the second stage prediction to estimate the remaining time until the HO event occurs.

[0036] In some embodiments, after the processor 12 trains the HO prediction model, the HO prediction model is stored in the storage device 14 for later use. In some embodiments, the HO prediction model is established based on a known ML model, such as a support vector machine (SVM) model, a recurrent neural network (RNN) model, an eXtreme gradient boosting (XGB) model, a gradient boosting (GB) model, or other algorithms based on the above disclosure that a skilled person should understand, which will not be described in detail here.

[0037] In some embodiments, a time series prediction task is used to predict HO events. In the time series prediction task, the collected data is structured into an input feature sequence within a time interval TP (e.g., 1 second), and a sliding time window method is used to generate a sequence of training data points within the prediction range.

[0038] Figure 3 is a schematic diagram showing an input feature sequence according to an embodiment of the present disclosure and a prediction range corresponding to the collected data Data1 and Data2. Figure 3 In the example, the collected data Data1 represents the data scene from time t0 to time t6, and the collected data Data2 represents the data scene from time t1 to time t7. Time t1 occurs immediately after time t0. In some embodiments, the time difference between time t1 and time t0 is one second.

[0039] The collected data is fed into the HO prediction model (or other pre-trained model) as input features for prediction. Corresponding to the input feature sequence, a prediction range is generated for each collected data, so as to predict whether a HO or RLF event will occur through the classification algorithm in the HO prediction model, and use the regression algorithm in the HO prediction model to predict how much time is left before the HO or RLF event. For example, the prediction range 314 between time t2 and time t6 is generated based on the input feature sequence 312 obtained from time t0 to time t2 for the collected Data1, and the prediction range 315 between time t3 and time t7 is generated based on the input feature sequence 313 obtained from time t1 to time t3 for the collected data Data2. Figure 3In the embodiment of the present invention, prediction ranges 314 and 315 are determined by input feature sequence 312 and input feature sequence 313, respectively. Different features between input feature sequence 312 and input feature sequence 313 will lead to different predictions. For example, according to input feature sequence 312, HO event 323 is predicted to occur within prediction range 314 and between time t4 and time t5, as shown in collected data Data1. However, according to input feature sequence 313, no HO event is predicted to occur within prediction range 315, as shown in collected data Data2.

[0040] Figure 4 It shows that according to one embodiment of the present disclosure Figure 1 The deployment scenario of the wireless communication device 100 in FIG. Figure 4 In the embodiment of the invention, the wireless communication device 100 is disposed in a fast moving train 410. In addition, the first RF interface 132 including the wireless transceiver 22 and the antenna module 32 is configured to communicate with the base station 422 using the first frequency band setting. The second RF interface 134 including the wireless transceiver 24 and the antenna module 34 is configured to communicate with the base station 431 using the second frequency band setting. As previously described, the first frequency band setting is different from the second frequency band setting. The first RF interface 132 and the second RF interface 134 can be disposed at the same or different locations in the train 510.

[0041] When the train 410 moves, the HO procedure is performed between base stations along the route of the train 410. For example, when the train 410 moves from the coverage of the base station 422 into the coverage of the base station 424, the HO procedure is performed corresponding to the first HO event HO_1 of the first RF interface 132. Similarly, when the train 410 moves from the coverage of the base station 431 into the coverage of the base station 433, the HO procedure is performed corresponding to the second HO event HO_2 of the second RF interface 134.

[0042] Figure 5 is a diagram showing a vehicle (eg, Figure 4 410) on a wireless communication device (e.g., Figure 1 The vehicle is traveling on a fixed or known route. For ease of explanation, the wireless communication method is performed by Figure 4 To illustrate Figure 5 method.

[0043] This wireless communication method is implemented in CBTC's railway signaling system, which uses telecommunications between trains and ground track equipment for traffic management and infrastructure control. CBTC can know the location of trains more accurately than traditional signaling systems. This makes rail traffic management safer and more efficient. Subways (and other railway systems) can reduce the departure interval while maintaining or even improving safety.

[0044] In operation S510, the wireless communication device 100 is configured to simultaneously establish communication links with at least two base stations according to different frequency band settings. For example, in the wireless communication device 100, the first RF interface 132 is configured to communicate with the base station 422 through the first channel CH1 according to the first frequency band setting, and the second RF interface 134 is configured to communicate with the base station 431 through the second channel CH2 according to the second frequency band setting. Through the communication link, the wireless communication device 100 is configured to send the same packet to the base stations 422 and 431 for CBTC.

[0045] In operation S520, by using the HO prediction model, the processor 12 of the wireless communication device 100 is configured to generate a first predicted time PT1 of a first HO event HO_1 corresponding to the base station 422, and a second predicted time PT2 of a second HO event HO_2 corresponding to the base station 431. The first HO event HO_1 corresponds to a HO procedure between the base stations 422 and 424, and the second HO event HO_2 corresponds to a HO procedure between the base stations 431 and 433. As previously described, the HO prediction model may be an ML model having an ML task for HO event prediction. Corresponding to a current signal quality measurement (e.g., RSRP, RSRQ, or SINR), the HO prediction model is used to obtain predicted times PT1 and PT2 according to a data set stored in the storage device 14, and the data set includes collected data previously collected by the UE. In some embodiments, the first predicted time PT1 and the second predicted time PT2 may be generated using the HO prediction model according to the vehicle speed.

[0046] In operation S530, by using the policy control model, the processor 12 is configured to determine whether the predicted times PT1 and PT2 satisfy a band selection condition for predicting a HO event. If the predicted times PT1 and PT2 do not satisfy any band selection condition, the first band setting of the first RF interface 132 and the second band setting of the second RF interface 134 are maintained (in operation S540). In this way, the first RF interface 132 is configured to continue to communicate with the base station 422 through the first channel CH1 according to the maintained first band setting, and the second RF interface 134 is configured to continue to communicate with the base station 431 through the second channel CH2 according to the maintained second band setting. Then, the process returns to operation S520. Figure 6 The determination of the frequency band selection condition will be described.

[0047] If the predicted times PT1 and PT2 satisfy one of the band selection conditions in operation S530, one of the first band setting and the second band setting is changed in operation S550 corresponding to the satisfied band selection condition, and then the process returns to operation S520. For example, if the first band setting is changed and the second band setting is maintained for the upcoming first HO event HO_1, the first RF interface 132 is configured to communicate with the base station 422 through the third channel CH3 corresponding to the changed first band setting, and the second RF interface 134 is configured to continue to communicate with the base station 431 through the second channel CH2 according to the maintained second band setting. Therefore, the communication between the base station 422 and the first RF interface 132 has been reset to avoid the influence caused by the first HO event HO_1. In other words, since the communication between the base station 422 and the wireless communication device 100 has been reconfigured to the third channel CH3, the first handover event HO_1 will not come. In some embodiments, the third channel CH3 is a candidate channel of the base station 422 in the band locking technique, and the wireless communication device 100 is configured to update the frequency band subset by reporting or not reporting the channel measurement to the base station 422. Similarly, if the first frequency band setting is maintained and the second frequency band setting is changed for the upcoming second HO event HO_2, the first RF interface 132 is configured to continue to communicate with the base station 422 via the first channel CH1 according to the maintained first frequency band setting, and the second RF interface 134 is configured to communicate with the base station 431 via the fourth channel CH4 according to the changed second frequency band setting. Therefore, the communication between the base station 431 and the second RF interface 134 has been reconfigured to avoid the influence caused by the second HO event HO_2. In some embodiments, the fourth channel CH4 is a candidate channel of the base station 431 in the band locking technique, and the wireless communication device 100 is configured to update the frequency band subset by reporting or not reporting the channel measurement to the base station 422. In operation S550, the changed band setting and the unchanged band setting are not on the same band, thereby avoiding using the same service unit, which may cause HO to occur at about the same time. In addition, after a certain band setting is changed, the processor 12 is configured to control the HO prediction model to enter a rest period to avoid the band change procedure affecting the CBTC transmission. In some embodiments, the rest period is greater than the estimated time to complete the reconfiguration after the wireless communication device 100 changes a band setting in operation S550.

[0048] Figure 6 The method of determining whether to change a frequency band setting (ie Figure 5For ease of explanation, the following flowchart will be used in conjunction with Figure 4 To illustrate Figure 6 In addition, the policy control model is used to execute Figure 6 operation.

[0049] First, in operation S602, the processor 12 of the wireless communication device 100 is configured to determine the relationship between the first predicted time PT1, the second predicted time PT2 and the critical value TH. The critical value TH is a predetermined time, for example, 3 seconds. In some embodiments, the critical value TH is determined based on the time interval and HO type of the first HO event HO_1 and the time interval and HO type of the second HO event HO_2. In some embodiments, the critical value TH is determined based on the estimated time for the wireless communication device 100 to complete the reconfiguration. Figure 6 In the embodiment of the present invention, the relationship between the first prediction time PT1, the second prediction time PT2 and the threshold value TH can be divided into a first case, a second case and a third case.

[0050] In the first case, both the first prediction time PT1 and the second prediction time PT2 are greater than the threshold value TH. In other words, the first RF interface 132 is far away from the first HO event HO_1, and the second RF interface 134 is far away from the second HO event HO_2. Therefore, relative to the second and third cases, the first case is considered to be a safe transmission condition.

[0051] In the first case, in operation S604, the processor 12 is further configured to determine whether the physical cell identifiers (PCIs) of the base stations 422 and 431 are the same. If the PCIs of the base stations 422 and 431 are different, then in operation S606 (i.e., Figure 5 In operation S540), the processor 12 is configured to maintain the first frequency band setting of the first RF interface 132 and the second frequency band setting of the second RF interface 134. If the PCIs of the base stations 422 and 431 are the same, then in operation S608, the processor 12 is configured to change the second frequency band setting of the second RF interface 134 to avoid packet loss due to a HO event of a base station with the same PCI, i.e. Figure 5 Therefore, the second RF interface 134 is configured to communicate with the base station 431 through the fourth channel CH4 corresponding to the changed second frequency band setting.

[0052] In some embodiments, in operation S602, when it is determined that both the first predicted time PT1 and the second predicted time PT2 are greater than the threshold value TH, operation S604 may be skipped and operation S608 may be performed by the processor 12 to change the second frequency band setting of the second RF interface 134. In some embodiments, operation S604 may be performed independently of operation S602, and when it is determined that the PCIs of the base stations 422 and 431 are the same, the processor 12 is configured to change the second frequency band setting of the second RF interface 134.

[0053] In the second case, the threshold TH is between the first prediction time PT1 and the second prediction time PT2. If the first prediction time PT1 is greater than the second prediction time PT2 (i.e., PT2<TH<PT1), the first RF interface 132 is far away from the first HO event HO_1, and the second RF interface 134 is close to the second HO event HO_2. On the contrary, if the first prediction time PT1 is less than the second prediction time PT2 (i.e., PT1<TH<PT2), the first RF interface 132 is close to the first HO event HO_1, and the second RF interface 134 is far away from the second HO event HO_2.

[0054] In the second case, in operation S612, the processor 12 is configured to determine whether the wireless communication device 100 operates in the aggressive mode. If the wireless communication device 100 operates in the aggressive mode, the processor 12 is configured to determine whether the wireless communication device 100 operates in the aggressive mode in operation S614 (ie, Figure 5 In operation S550 in the embodiment, the frequency band setting corresponding to the smaller prediction time between the first frequency band setting and the second frequency band setting is changed. For example, if the first prediction time PT1 is less than the second prediction time PT2, the processor 12 is configured to change the first frequency band setting of the first RF interface 132 so that the first RF interface 132 can communicate with the base station 422 through the third channel CH3 corresponding to the changed first frequency band setting.

[0055] If it is determined in operation S612 that the wireless communication device 100 is operating in the normal mode, the processor 12 is configured to compare the time difference between the first prediction time PT1 and the second prediction time PT2 with the critical value Tdiff in operation S616 to determine whether the first prediction time PT1 and the second prediction time PT2 are too close. If the first prediction time PT1 and the second prediction time PT2 are too close (i.e., the time difference is less than the critical value Tdiff), the process proceeds to operation S614. If the first prediction time PT1 and the second prediction time PT2 are not too close (i.e., the time difference is greater than the critical value Tdiff), the process proceeds to operation S606.

[0056] In the third case, both the first prediction time PT1 and the second prediction time PT2 are less than the threshold value TH. In other words, the first RF interface 132 is close to the first HO event HO_1, and the second RF interface 134 is close to the second HO event HO_2. Therefore, relative to the first and second cases, the third case is considered to be an unsafe transmission condition.

[0057] In the third case, in operation S622, the processor 12 is further configured to determine whether the loss difference between the first packet loss Loss1 of the base station 422 and the packet loss Loss2 of the base station 424 is less than a critical value Ldiff or no serious event (e.g., RLF event) occurs. If the loss difference is less than the critical value Ldiff or no serious event occurs, the process proceeds to operation S614. If the loss difference is greater than or equal to the critical value Ldiff or a serious event occurs, then in operation S624, that is, Figure 5 In operation S550, the processor 12 is configured to change the frequency band setting corresponding to the large packet loss or severe event among the first frequency band setting and the second frequency band setting. For example, if the RLF event occurs in the first RF interface 132, the processor 12 is configured to change the first frequency band setting of the first RF interface 132, so that the first RF interface 132 is configured to communicate with the base station 422 through the third channel CH3 corresponding to the changed first frequency band setting.

[0058] In some embodiments, the processor 12 is configured to change the frequency band setting corresponding to the earlier HO event when one or more trigger conditions exist. For ease of explanation, it is expected that the first HO event HO_1 will occur before the second HO event HO_2, and the trigger conditions are as follows: Figure 7 The table shows.

[0059] exist Figure 7, "T_1_start" is the estimated start time of the first HO event HO_1, and "T_1_end" is the estimated end time of the first HO event HO_1. Similarly, "T_2_start" is the estimated start time of the second HO event HO_2, and "T_change" is the estimated reconfiguration time for changing the first frequency band setting. "threshold_1", "threshold_2" and "threshold_3" are critical values ​​determined by the policy control model. In some embodiments, the critical values ​​"threshold_1" and "threshold_2" may be equal to the estimated time "T_change". "Loss_1" is the expected packet loss of the first HO event HO_1, and "Loss_2" is the expected packet loss of the second HO event HO_2. "Delay_1" is the expected packet delay performance of the first HO event HO_1, and "Delay_2" is the expected packet delay performance of the second HO event HO_2. In some embodiments, when one of the triggering conditions exists, the processor 12 is configured to change the first frequency band setting of the first RF interface 132 .

[0060] According to various embodiments, the present disclosure is applicable to vehicles where wireless communication devices may experience frequent HO. The present disclosure enables wireless communication with a base station to reduce HO failures and their associated delays and data packet loss issues by reducing overlap of HO events.

[0061] Although the preferred embodiments of the present disclosure are described above, they are not intended to limit the present disclosure. A person skilled in the art may make several changes and modifications without departing from the spirit and scope of the present disclosure. Therefore, the scope of protection of the present disclosure shall be based on the scope of protection of the attached patent application.

[0062] Explanation of symbols

[0063] 12: Processor

[0064] 14: Storage device

[0065] 22,24: Wireless transceiver

[0066] 32,34: Antenna module

[0067] 100: Wireless communication equipment

[0068] 110: Control node

[0069] 120: transceiver group

[0070] 132: First RF interface

[0071] 134: Second RF interface

[0072] 312,313: Input feature sequence

[0073] 314,315: Preset range

[0074] 323:HO incident

[0075] 410: Rapid moving train

[0076] 422,431,433,424: Base Station

Claims

1. A wireless communication device, comprising: a transceiver set configured to simultaneously communicate with a first base station through a first channel according to a first frequency band setting, and communicate with a second base station through a second channel according to a second frequency band setting different from the first frequency band setting; and A processor is electrically connected to the transceiver group and configured to: Using a handover prediction model, generating a first prediction time of a first handover event corresponding to the first base station; Using the handover prediction model, generating a second predicted time of a second handover event corresponding to the second base station; as well as Whether to change one of the first frequency band setting and the second frequency band setting is determined according to the first prediction time, the second prediction time and a first threshold.

2. A wireless communication device as claimed in claim 1, wherein corresponding to the changed first frequency band setting, the transceiver group is configured to communicate with the first base station through a third channel, and corresponding to the changed second frequency band setting, the transceiver group is configured to communicate with the second base station through a fourth channel. 3 . The wireless communication device of claim 1 , wherein when the first predicted time is less than the first critical value and the second predicted time is greater than the first critical value, the processor is configured to change the first frequency band setting.

4. The wireless communication device of claim 1, wherein when the first predicted time and the second predicted time are greater than the first critical value, the processor is configured to maintain the first frequency band setting and the second frequency band setting.

5. The wireless communication device of claim 1, wherein when one of the following conditions is met: The first prediction time and the second prediction time are both greater than the first critical value; The first base station and the second base station have the same physical cell area identification code; or The first predicted time and the second predicted time are both greater than the first critical value and the physical unit area identification codes of the first base station and the second base station are the same, The processor is configured to change the second frequency band setting.

6. The wireless communication device of claim 1, wherein when the difference between the first predicted time and the second predicted time is less than a second critical value and the first critical value is greater than the first preset time and less than the second critical value, the processor is configured to change the first frequency band setting.

7. A wireless communication device as claimed in claim 1, wherein when the difference between a first packet loss of the first base station and a second packet loss of the second base station is less than a second critical value and the second preset time is less than the first critical value and greater than the first preset time, the processor is configured to change the first frequency band setting.

8. The wireless communication device of claim 1, wherein the processor is configured to: Determining whether a wireless link failure occurs in the first channel or the second channel; and When the first predicted time and the second predicted time are less than the first threshold and the radio link failure is detected in the first channel, the first frequency band setting is changed.

9. The wireless communication device of claim 1, wherein the processor is configured to: Using the handover prediction model, generating the first prediction time according to at least one first signal quality measurement corresponding to the first base station; and The handover prediction model is used to generate the second prediction time according to at least one second signal quality measurement corresponding to the second base station.

10. The wireless communication device of claim 1, wherein the wireless communication device is disposed on a vehicle, and the processor is configured to generate the first prediction time and the second prediction time according to a speed of the vehicle using the handover prediction model.

11. The wireless communication device of claim 1 , wherein the processor is configured to: generating a first time interval of the first handshake event and a first handshake type of the first handshake event; generating a second time interval of the second handshake event and a second handshake type of the second handshake event; and The first critical value is determined according to the first time interval, the first handshake type, the second time interval, and the second handshake type.

12. The wireless communication device of claim 1, wherein the transceiver group is configured to transmit the same packet to the first base station and the second base station.

13. The wireless communication device of claim 1, wherein the transceiver group is configured to communicate with the first base station and the second base station via different generations of communication technologies.

14. A wireless communication method, comprising: Simultaneously communicating with a first base station through a first channel according to a first frequency band setting and communicating with a second base station through a second channel according to a second frequency band setting; Using a handover prediction model, generating a first prediction time of a first handover event corresponding to the first base station; Using the handover prediction model, generating a second predicted time of a second handover event corresponding to the second base station; as well as Whether to change one of the first frequency band setting and the second frequency band setting is determined according to the first prediction time, the second prediction time and a first threshold.

15. The wireless communication method of claim 14, further comprising: corresponding to the changed first frequency band setting, communicating with the first base station through a third channel; as well as Corresponding to the changed second frequency band setting, communicating with the second base station via a fourth channel.

16. The wireless communication method of claim 14, wherein determining whether to change one of the first frequency band setting and the second frequency band setting according to the first predicted time, the second predicted time and the first threshold value further comprises: When the first predicted time and the second predicted time are greater than the first critical value, maintaining the first frequency band setting and the second frequency band setting; When the first predicted time and the second predicted time are greater than the first critical value and the physical unit area identification codes of the first base station and the second base station are the same, changing the second frequency band setting; When the first predicted time is less than the first critical value and the second predicted time is greater than the first critical value, changing the first frequency band setting; When the difference between the first predicted time and the second predicted time is less than a second critical value and the first critical value is greater than the first preset time and less than the second critical value, changing the first frequency band setting; as well as When a difference between a first packet loss of the first base station and a second packet loss of the second base station is smaller than a third threshold and the second preset time is smaller than the first threshold and greater than the first preset time, the first frequency band setting is changed.

17. The wireless communication method of claim 14, further comprising: Determining whether a wireless link failure occurs in the first channel or the second channel; as well as When the first predicted time and the second predicted time are less than the first threshold and the radio link failure is detected in the first channel, the first frequency band setting is changed.

18. The wireless communication method of claim 14, wherein the handover prediction model is used to generate the first prediction time according to at least one first signal quality measurement corresponding to the first base station, and the handover prediction model is used to generate the second prediction time according to at least one second signal quality measurement corresponding to the second base station.

19. The wireless communication method of claim 14, further comprising: Using the turnover prediction model, generating a first time interval of the first turnover event and a first turnover type of the first turnover event; Using the turnover prediction model, generating a second time interval of the second turnover event and a second turnover type of the second turnover event; as well as The first critical value is determined according to the first time interval, the first handshake type, the second time interval, and the second handshake type.

20. The wireless communication method of claim 14, further comprising: The same packet is transmitted to the first base station and the second base station via different generations of communication technologies.

Images