Connection destination selection method and program
The method estimates and switches wireless communication terminals to access points with the highest predicted throughput, addressing suboptimal switching issues and maintaining communication quality.
Patent Information
- Application Number
- PCT/JP2025/017144
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-05-09
- Publication Date
- 2026-11-12
AI Technical Summary
Existing wireless communication systems face issues with deteriorating communication quality due to suboptimal access point switching, where switching to a new access point with good received power may result in lower throughput.
A method and device that estimate throughput for multiple access points based on observed wireless information, select the access point with the highest estimated throughput, and notify the communication terminal to switch connections accordingly.
Reduces the likelihood of communication quality deterioration by ensuring seamless transitions to access points with higher predicted throughput, maintaining consistent communication quality.
Smart Images

Figure JP2025017144_12112026_PF_FP_ABST
Abstract
Description
Connection Destination Selection Method and Program
[0001] The present invention relates to a connection destination selection method and a program.
[0002] Conventionally, by making a machine learning model learn the relationship between wireless information (received power, PHY rate, interference airtime ratio of other terminals, etc.) and throughput for the wireless situation at a certain location, the throughput can be estimated by inputting the wireless information observed at the time of inference into the learned model.
[0003] Wakao et al., "Quality Prediction Technology for Optimal Utilization of Multiple Wireless Accesses", NTT Technical Journal, April 2020
[0004] In a wireless LAN environment, in order for a terminal to perform communication via a plurality of access points while moving, the terminal needs to sequentially select an access point with optimal wireless quality. Even if it is detected that the received power or throughput of the connected access point has decreased and the connection is switched to another access point, the received power of the switching destination access point may be good, but due to the large number of accommodated terminals and limited communication opportunities, the throughput may be lower than that of the access point before switching.
[0005] The present invention has been made in view of the above points, and an object thereof is to reduce the possibility of deterioration in communication quality due to access point switching.
[0006] Therefore, in order to solve the above problem, a computer executes an estimation procedure of calculating an estimated throughput value for each piece of wireless information observed at a certain location with respect to a plurality of access points based on the said wireless information, and a notification procedure of notifying a communication terminal connected to any one of the plurality of access points of the access point associated with the highest said estimated value.
[0007] The possibility of deterioration in communication quality due to access point switching can be reduced.
[0008] This figure shows an example of a communication environment in the first embodiment. This figure shows an example of the hardware configuration of the connection destination selection device 10 in the first embodiment. This figure shows an example of the functional configuration of the connection destination selection device 10 in the first embodiment. This is a flowchart illustrating an example of a processing procedure performed by the connection destination selection device 10 in the first embodiment. This figure shows an example of a communication environment in the second embodiment. This figure shows an example of a communication environment in the third embodiment.
[0009] Embodiments of the present invention will be described below with reference to the drawings. Figure 1 is a diagram showing an example of a communication environment in the first embodiment. As shown in Figure 1, in this embodiment, multiple APs 40-1 to 3 (hereinafter referred to as "AP40" when not distinguishing between them) are arranged in an environment in which multiple information collection terminals 30A to C (hereinafter referred to as "information collection terminals 30" when not distinguishing between them) are arranged. We will assume a situation in which the communication terminal 20 moves within this environment.
[0010] AP40 is a device that functions as an access point (base station) for a wireless LAN (e.g., Wi-Fi®).
[0011] The communication terminal 20 is a device that can connect to any AP 40 and communicate via wireless LAN. For example, a smartphone, tablet, PC (Personal Computer), etc., may be used as the communication terminal 20.
[0012] The information gathering terminal 30 is a device that observes (measures) the wireless information of AP 40 at a certain location. Each information gathering terminal 30 is arranged so as to be able to observe the wireless information of two or more AP 40s. The wireless information may be, for example, received power strength, PHY rate, interference airtime rate of other terminals, etc., and can be any set of parameters that can be used as input information in the calculation of throughput.
[0013] Each information gathering terminal 30 and communication terminal 20 connects to the connection destination selection device 10 via a wireless LAN or wired network. The connection destination selection device 10 is one or more computers that select the AP 40 to be the roaming destination (connection destination) for the communication terminal 20 based on the wireless information observed by the information gathering terminal 30 and the wireless information observed (measured) by the communication terminal 20.
[0014] Figure 2 shows an example of the hardware configuration of the connection destination selection device 10 in the first embodiment. The connection destination selection device 10 in Figure 2 includes a drive device 100, an auxiliary storage device 102, a memory device 103, a processor 104, and an interface device 105, etc., which are all interconnected by bus B.
[0015] The program that enables processing in the connection destination selection device 10 is provided on a recording medium 101 such as a CD-ROM. When the recording medium 101 containing the program is set in the drive device 100, the program is installed from the recording medium 101 to the auxiliary storage device 102 via the drive device 100. However, the program does not necessarily have to be installed from the recording medium 101; it may also be downloaded from another computer via a network. The auxiliary storage device 102 stores the installed program as well as necessary files and data.
[0016] The memory device 103 reads and stores a program from the auxiliary storage device 102 when a program startup command is received. The processor 104 is either a CPU or a GPU (Graphics Processing Unit), or both a CPU and a GPU, and executes the functions related to the connection destination selection device 10 according to the program stored in the memory device 103. The interface device 105 is used as an interface for connecting to a network.
[0017] Figure 3 shows an example of the functional configuration of the connection destination selection device 10 in the first embodiment. In Figure 3, it has an acquisition unit 11, an estimation unit 12, a selection unit 13, and a notification unit 14. Each of these units is realized by processing that one or more programs installed in the connection destination selection device 10 cause the processor 104 to execute.
[0018] The following describes the processing procedure performed by the connection destination selection device 10. Figure 4 is a flowchart illustrating an example of the processing procedure performed by the connection destination selection device 10 in the first embodiment. The processing procedure in Figure 4 may be performed periodically (at intervals of 1 second, 10 seconds, 60 seconds, etc.) or in response to a request from the communication terminal 20.
[0019] In step S101, the acquisition unit 11 acquires the radio information observed (currently being observed) from the communication terminal 20 and each of the information collection terminals 30. From the communication terminal 20, radio information observed by the communication terminal 20 for the AP 40 to which the communication terminal 20 is connected is acquired. In the example in Figure 1, since the communication terminal 20 is connected to AP 40-1, the communication terminal 20 acquires the radio information for AP 40-1. From each of the information collection terminals 30, radio information for two or more AP 40s that each is observing is acquired. In the example in Figure 1, the information collection terminal 30A acquires the radio information for AP 40-1 and AP 40-2. The information collection terminal 30B acquires the radio information for AP 40-2 and AP 40-3. The information collection terminal 30C acquires the radio information for AP 40-1 and AP 40-3.
[0020] Next, the estimation unit 12 calculates an estimated throughput (hereinafter referred to as "estimated throughput") based on the wireless information acquired from each information collection terminal 30 (S102). The calculation of the estimated throughput may be performed by deriving a theoretical formula that shows the correspondence between one or more parameters contained in the wireless information and the throughput, and substituting the parameters into the theoretical formula. Alternatively, the calculation may be performed by inputting the parameters into a machine learning model that has already learned the correspondence between one or more parameters contained in the wireless information and the throughput.
[0021] In the example shown in Figure 1, six estimated throughputs are calculated based on the wireless information of AP40-1 and AP40-2 acquired from information collection terminal 30A, the wireless information of AP40-2 and AP40-3 acquired from information collection terminal 30B, and the wireless information of AP40-1 and AP40-3 acquired from information collection terminal 30C.
[0022] Next, the selection unit 13 extracts from the information collection terminals 30A to C the information collection terminal 30 that is observing the wireless information of AP 40 to which the communication terminal 20 is connected (S103). In the example in Figure 1, information collection terminals 30A and 30C are observing the wireless information of AP 40-1 to which the communication terminal 20 is connected. Therefore, these two information collection terminals 30 are extracted.
[0023] Next, the selection unit 13 calculates the similarity between the wireless information of the AP 40 to which the communication terminal 20 is connected, acquired from the communication terminal 20, and the wireless information observed by each extracted information collection terminal 30 regarding the AP 40 (S104). The similarity between wireless information can be calculated by defining a vector of wireless information and calculating its distance (for example, cosine similarity). A vector of wireless information is a vector whose dimensions are numerical values corresponding to each parameter that constitutes the wireless information. In this case, the values of each parameter should be normalized or standardized based on the relative magnitudes of the parameters so that the influence of any one parameter does not become excessive.
[0024] In the example shown in Figure 1, for each piece of wireless information observed by information gathering terminals 30A and 30C regarding AP40-1, the similarity between that information and the wireless information observed by communication terminal 20 regarding AP40-1 is calculated.
[0025] Next, the selection unit 13 selects the information collection terminal 30 related to the wireless information corresponding to the similarity that indicates the highest similarity (and thus the smallest distance in terms of similarity) (S105). This is because the information collection terminal 30 whose wireless information is similar to that of the communication terminal 20 is considered to be located at a location that is similar to the communication terminal 20 in terms of the wireless environment and physically.
[0026] Next, the selection unit 13 selects the AP 40 from among the APs 40 on which the information gathering terminal 30 selected in step S105 observed wireless information, the AP 40 with the highest estimated throughput calculated in step S102, as the AP 40 to which the communication terminal 20 will connect (S106).
[0027] If information gathering terminal 30A is selected, and the estimated throughput based on the wireless information observed by information gathering terminal 30 is higher for AP40-2 than for AP40-1, then AP40-2 will be selected.
[0028] Next, the notification unit 14 notifies the communication terminal 20 of the AP 40 selected by the selection unit 13 (S107). For example, the notification unit 14 notifies the communication terminal 20 of the SSID of the AP 40. Alternatively, the notification unit 14 may send a signal to the communication terminal 20 and the AP 40 prompting them to roam.
[0029] If the AP 40 notified by the notification unit 14 is different from the AP 40 to which the communication terminal 20 is currently connected, the terminal 20 switches its connection destination to the notified AP 40 (roams).
[0030] As described above, according to the first embodiment, based on the wireless information observed by each information collection terminal 30 for each AP 40, the AP 40 that is estimated to have relatively high wireless quality for the communication terminal 20 is selected as the connection destination for the communication terminal 20. Therefore, the possibility of deterioration of communication quality due to access point switching can be reduced. As a result, for example, the communication terminal 20 can continue to communicate while satisfying the user's requested traffic even after roaming.
[0031] Next, a second embodiment will be described. The differences between the second embodiment and the first embodiment will be described. Points not specifically mentioned in the second embodiment may be the same as in the first embodiment.
[0032] Figure 5 shows an example of a communication environment in the second embodiment. In Figure 5, the same parts as in Figure 1 are denoted by the same reference numerals, and their descriptions are omitted.
[0033] In Figure 5, one information gathering terminal 30 is positioned at a location where it can observe silent information from all APs 40.
[0034] In the second embodiment, since there is only one information collection terminal 30, steps S104 and S105 in Figure 4 do not need to be performed.
[0035] In step S106, one information gathering terminal 30 selects the AP 40 with the highest estimated throughput from among the estimated throughputs based on the wireless information observed for each AP 40.
[0036] In the second embodiment, since there is only one information gathering terminal 30, it is not possible to select an AP 40 based on wireless information observed by the information gathering terminal 30, which is located at a location similar to the communication terminal 20 in terms of the wireless environment and physically. However, the throughput of the AP 40 varies greatly depending on the AP 40's capacity (number of connected terminals, airtime, etc.). Therefore, in the second embodiment, the possibility of deterioration in the communication quality of the communication terminal 20 can be reduced based on the AP 40's capacity.
[0037] Next, a third embodiment will be described. The differences between the third embodiment and the first embodiment will be described. Points in the third embodiment that are not specifically mentioned may be the same as in the first embodiment.
[0038] Figure 6 shows an example of a communication environment in the third embodiment. In Figure 6, the same parts as in Figure 1 are denoted by the same reference numerals, and their descriptions are omitted.
[0039] In Figure 6, the information gathering terminal 30 is not positioned. On the other hand, the auxiliary storage device 102 of the connection destination selection device 10 stores wireless information that has been observed in advance for any two or more APs 40 at each of the multiple locations. Each of the multiple locations is a location where wireless information from two or more APs 40 can be observed. For example, each location where the information gathering terminal 30 is positioned in Figure 1 may be multiple locations.
[0040] In the third embodiment, the acquisition unit 11 acquires wireless information from the communication terminal 20. From there, the process can be executed by replacing "information collection terminal 30" with "location".
[0041] In the third embodiment, the same effects as in the first embodiment can be obtained in areas where the temporal changes in the wireless environment are small (layout and pedestrian flow do not change).
[0042] The functions of the elements disclosed herein may be implemented using circuits or processing circuitry that include general-purpose processors, special-purpose processors, integrated circuits, ASICs (Application Specific Integrated Circuits), FPGAs (Field Programmable Gate Arrays), conventional circuits, and / or combinations thereof that are programmed using one or more programs stored in one or more memories, or otherwise configured to perform the disclosed functions. A processor is considered processing circuitry or circuitry because it includes transistors and other circuits. A processor may be a programmed processor that executes programs stored in memory. In this disclosure, a circuit, unit, or means is hardware that performs the enumerated functions, or hardware programmed to perform the enumerated functions. Hardware may be any hardware disclosed herein that is programmed or configured to perform the enumerated functions.
[0043] There is a memory for storing a computer program that includes computer instructions. These computer instructions provide logic and routines that enable hardware (e.g., processing circuitry or circuitry) to perform the methods disclosed herein. This computer program can be implemented in commonly known forms, such as computer-readable storage media, computer program products, memory devices, recording media such as CD-ROMs and DVDs, and / or memory in FPGAs and ASICs.
[0044] The embodiments of the present invention have been described in detail above, but the present invention is not limited to such specific embodiments, and various modifications and changes are possible within the scope of the gist of the present invention described in the claims.
[0045] 10 Connection destination selection apparatus 11 Acquisition unit 12 Estimation unit 13 Selection unit 14 Notification unit 20 Communication terminal 30 Information collection terminal 40 AP 100 Drive apparatus 101 Recording medium 102 Auxiliary storage apparatus 103 Memory apparatus 104 Processor 105 Interface apparatus B Bus
Claims
1. A connection destination selection method characterized in that a computer performs the following steps: an estimation procedure for calculating an estimated throughput value based on wireless information observed at a certain point for each of multiple access points; and a notification procedure for notifying a communication terminal connected to any of the multiple access points of the access point corresponding to the highest estimated throughput value.
2. The connection destination selection method according to claim 1, characterized in that the estimation procedure involves a computer executing a calculation procedure which calculates an estimated value based on the radio information observed for any two or more of the multiple access points at each of the multiple locations, and calculates the similarity between the radio information observed for the first access point by the communication terminal connected to the first access point among the multiple access points and the respective radio information observed for the first access point at two or more locations, and the notification procedure which notifies the communication terminal of the access point with the highest estimated value among the radio information observed at the location relating to the highest similarity.
3. The connection destination selection method according to claim 2, characterized in that the wireless information observed at the plurality of locations is wireless information observed by a plurality of terminals placed at the plurality of locations.
4. A program for causing a computer to execute: an estimation procedure for calculating an estimated throughput value based on radio information observed at a certain point for each of multiple access points; and a notification procedure for notifying a communication terminal connected to any of the multiple access points of the access point with the highest estimated throughput value.
