TW202320503A - Number of repetitions prediction method and number of repetitions prediction device - Google Patents
Number of repetitions prediction method and number of repetitions prediction device Download PDFInfo
- Publication number
- TW202320503A TW202320503A TW110140677A TW110140677A TW202320503A TW 202320503 A TW202320503 A TW 202320503A TW 110140677 A TW110140677 A TW 110140677A TW 110140677 A TW110140677 A TW 110140677A TW 202320503 A TW202320503 A TW 202320503A
- Authority
- TW
- Taiwan
- Prior art keywords
- feature sets
- groups
- retransmissions
- training set
- predicting
- Prior art date
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/04—Error control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/12—Arrangements for detecting or preventing errors in the information received by using return channel
- H04L1/16—Arrangements for detecting or preventing errors in the information received by using return channel in which the return channel carries supervisory signals, e.g. repetition request signals
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
Description
本發明涉及一種預測方法和預測裝置,特別是涉及一種重傳次數預測方法和重傳次數預測裝置。The present invention relates to a prediction method and a prediction device, in particular to a retransmission times prediction method and a retransmission times prediction device.
在第五代行動通訊系統的超可靠低延遲通訊(Ultra-reliable and Low Latency Communications,uRLLC)中,通訊品質較差的用戶設備會需要使用較多重傳來補償額外的訊號衰減。當重傳次數配置不適當時,將會造成傳輸錯誤率高,或者浪費了許多寶貴的無線資源。In Ultra-reliable and Low Latency Communications (uRLLC) of the fifth generation mobile communication system, user equipment with poor communication quality needs to use more retransmissions to compensate for additional signal attenuation. When the number of retransmissions is improperly configured, the transmission error rate will be high, or a lot of precious wireless resources will be wasted.
針對現有技術的不足,本發明之目的在於提供一種重傳次數預測方法和重傳次數預測裝置,能夠產生用於預測用戶設備的重傳次數的模型,更甚至使得基站能夠根據該模型對於不同通訊品質的用戶設備配置適當的重傳次數。In view of the deficiencies in the prior art, the purpose of the present invention is to provide a retransmission number prediction method and a retransmission number prediction device, which can generate a model for predicting the retransmission times of the user equipment, and even enable the base station to use the model for different communications. Quality user equipment is configured with an appropriate number of retransmissions.
為達上述目的,本發明實施例提供一種重傳次數預測方法,包括下列步驟。取得分別對應於多個用戶設備的多個數據集合,該些數據集合分別包含該些用戶設備與至少一基站通訊時產生的多個通訊品質參數。使用降維演算法分析該些通訊品質參數以將該些數據集合降維為多個自定義特徵集合。將該些自定義特徵集合分為訓練集以及測試集,並且使用分類演算法依據可傳輸性對訓練集進行二元分類以決定出多個第一可傳輸樣本。使用分群演算法依據該些用戶設備與該至少一基站通訊時使用的多個重傳次數將該些第一可傳輸樣本分群為多個第一群組,該些第一群組分別對應於不同的該些重傳次數,並且使用該些第一群組對機器學習模型進行訓練以產生重傳次數預測模型。該重傳次數預測模型係用於預測該些用戶設備與該至少一基站通訊時使用的該些重傳次數。To achieve the above purpose, an embodiment of the present invention provides a method for predicting the number of retransmissions, including the following steps. A plurality of data sets respectively corresponding to a plurality of user equipments are obtained, and the data sets respectively include a plurality of communication quality parameters generated when the user equipments communicate with at least one base station. Using a dimensionality reduction algorithm to analyze the communication quality parameters to reduce the dimensionality of the data sets into a plurality of custom feature sets. The custom feature sets are divided into a training set and a test set, and a classification algorithm is used to binary classify the training set according to the transferability to determine a plurality of first transferable samples. Use a grouping algorithm to group the first transmittable samples into a plurality of first groups according to the plurality of retransmission times used when the user equipments communicate with the at least one base station, and the first groups correspond to different The number of retransmissions, and use the first groups to train the machine learning model to generate a prediction model of the number of retransmissions. The retransmission times prediction model is used to predict the retransmission times used when the user equipments communicate with the at least one base station.
另外,本發明實施例提供一種重傳次數預測裝置,包括儲存器以及處理器。儲存器用於儲存分別對應於多個用戶設備的多個數據集合。處理器電性連接儲存器,並且用於執行下列步驟。取得分別對應於該些用戶設備的該些數據集合。該些數據集合分別包含該些用戶設備與至少一基站通訊時產生的多個通訊品質參數。使用降維演算法分析該些通訊品質參數以將該些數據集合降維為多個自定義特徵集合。將該些自定義特徵集合分為訓練集以及測試集,並且使用分類演算法依據可傳輸性對訓練集進行二元分類以決定出多個第一可傳輸樣本。使用分群演算法依據該些用戶設備與該至少一基站通訊時使用的多個重傳次數將該些第一可傳輸樣本分群為多個第一群組,該些第一群組分別對應於不同的該些重傳次數,並且使用該些第一群組對機器學習模型進行訓練以產生重傳次數預測模型。該重傳次數預測模型係用於預測該些用戶設備與該至少一基站通訊時使用的該些重傳次數。In addition, an embodiment of the present invention provides an apparatus for predicting the number of retransmissions, including a memory and a processor. The storage is used for storing multiple data sets respectively corresponding to multiple user equipments. The processor is electrically connected to the storage, and is used for performing the following steps. The data sets respectively corresponding to the user equipments are acquired. The data sets respectively include a plurality of communication quality parameters generated when the user equipments communicate with at least one base station. Using a dimensionality reduction algorithm to analyze the communication quality parameters to reduce the dimensionality of the data sets into a plurality of custom feature sets. The custom feature sets are divided into a training set and a test set, and a classification algorithm is used to binary classify the training set according to the transferability to determine a plurality of first transferable samples. Use a grouping algorithm to group the first transmittable samples into a plurality of first groups according to the plurality of retransmission times used when the user equipments communicate with the at least one base station, and the first groups correspond to different The number of retransmissions, and use the first groups to train the machine learning model to generate a prediction model of the number of retransmissions. The retransmission times prediction model is used to predict the retransmission times used when the user equipments communicate with the at least one base station.
為使能更進一步瞭解本發明的特徵及技術內容,請參閱以下有關本發明的詳細說明與圖式,然而所提供的圖式僅用於提供參考與說明,並非用來對本發明加以限制。In order to further understand the features and technical content of the present invention, please refer to the following detailed description and drawings related to the present invention. However, the provided drawings are only for reference and description, and are not intended to limit the present invention.
以下是通過特定的具體實施例來說明本發明的實施方式,本領域技術人員可由本說明書所提供的內容瞭解本發明的優點與效果。本發明可通過其他不同的具體實施例加以施行或應用,本說明書中的各項細節也可基於不同觀點與應用,在不悖離本發明的構思下進行各種修改與變更。另外,本發明的附圖僅為簡單示意說明,並非依實際尺寸的描繪,事先聲明。以下的實施方式將進一步詳細說明本發明的相關技術內容,但所提供的內容並非用以限制本發明的保護範圍。The implementation of the present invention is illustrated through specific specific examples below, and those skilled in the art can understand the advantages and effects of the present invention from the content provided in this specification. The present invention can be implemented or applied through other different specific embodiments, and various modifications and changes can be made to the details in this specification based on different viewpoints and applications without departing from the concept of the present invention. In addition, the drawings of the present invention are only for simple illustration, and are not drawn according to the actual size, which is stated in advance. The following embodiments will further describe the relevant technical content of the present invention in detail, but the provided content is not intended to limit the protection scope of the present invention.
請參閱圖1,圖1是本發明實施例的無線通訊系統的示意圖。如圖1所示,無線通訊系統1可包括M個基站11
1~11
M以及N個用戶設備12
1~12
N。在本實施例中,M和N分別為大於1的整數,且N可不等於M,但本發明不以此為限制。在其他實施例中,M還可等於1,且N為大於1的整數。總而言之,無線通訊系統1包括至少一基站以及多個用戶設備。另外,本實施例的每一用戶設備可例如為智慧型手機,但本發明亦不以此為限制。
Please refer to FIG. 1 . FIG. 1 is a schematic diagram of a wireless communication system according to an embodiment of the present invention. As shown in FIG. 1 , the
更具體地說,基站11
1~11
M可分別具有訊號涵蓋範圍C
1~C
M,且在本實施例中,相鄰基站的訊號涵蓋範圍可彼此有部分區域重疊,但本發明不以此為限制。因此在這種情況下,無線通訊系統1的每一用戶設備至少位於訊號涵蓋範圍C
1~C
M其中之一並和相應的基站通訊。在本實施例中,每一用戶設備會使用重複性傳送方式(簡稱重傳)來將數據傳送至其通訊的基站。這裡的重傳是指在時域或頻域下連續傳送不同的重傳版本,且在第五代行動通訊系統的協定下,允許對於用戶設備的重傳次數進行配置。
More specifically, the base stations 11 1 - 11 M may respectively have signal coverage areas C 1 -C M , and in this embodiment, the signal coverage areas of adjacent base stations may partially overlap with each other, but the present invention does not for the limit. Therefore, in this case, each user equipment in the
應當理解的是,越靠近訊號涵蓋範圍邊緣的用戶設備會越具有較差的通訊品質以至於需要使用較多重傳來補償額外的訊號衰減。因此,當這種用戶設備的重傳次數配置不足時,將會導致基站端的數據接收失敗,即傳輸錯誤率高。相對地,越靠近訊號涵蓋範圍中心的用戶設備會越具有較佳的通訊品質。因此,當這種用戶設備的重傳次數配置過多時,將會浪費了許多寶貴的無線資源。It should be understood that the UE closer to the edge of the signal coverage area will have poorer communication quality and need to use more retransmissions to compensate for the additional signal attenuation. Therefore, when the number of retransmission times configured for the user equipment is insufficient, data reception at the base station will fail, that is, the transmission error rate is high. Correspondingly, the closer the user equipment is to the center of the signal coverage area, the better the communication quality will be. Therefore, when the number of retransmissions configured for such user equipment is too large, many precious radio resources will be wasted.
為了解決上述問題,本發明是產生一重傳次數預測模型用於預測用戶設備的重傳次數。請參閱圖2A到圖2B和圖3,圖2A到圖2B是本發明實施例的重傳次數預測方法的步驟流程圖,圖3是本發明實施例的重傳次數預測裝置的功能方塊示意圖。圖2A到圖2B的重傳次數預測方法適用於圖1的無線通訊系統1,並且可由圖3的重傳次數預測裝置3來執行。In order to solve the above problems, the present invention generates a retransmission times prediction model for predicting the retransmission times of the user equipment. Please refer to FIG. 2A to FIG. 2B and FIG. 3. FIG. 2A to FIG. 2B are flow charts of steps of a method for predicting the number of retransmissions according to an embodiment of the present invention, and FIG. 3 is a functional block diagram of a device for predicting the number of retransmissions according to an embodiment of the present invention. The method for predicting the number of retransmissions in FIG. 2A to FIG. 2B is applicable to the
在本實施例中,重傳次數預測裝置3可以是自我組織網路(Self-organizing Networks,SON)伺服器、無線電智慧控制器(Radio Intelligent Controller,RIC)或者無線通訊系統1的任一基站等特定的機器或設備,但本發明不限制該特定的機器或設備的具體實現方式。總而言之,重傳次數預測裝置3至少包括儲存器31和處理器33。In this embodiment, the retransmission times prediction device 3 may be a self-organizing network (Self-organizing Networks, SON) server, a radio intelligent controller (Radio Intelligent Controller, RIC) or any base station of the
儲存器31可為用於儲存數據的任何儲存裝置,例如隨機存取記憶體、唯讀記憶體、快閃記憶體或硬碟等,但本發明不以此為限制。在本實施例中,儲存器31經配置用於至少儲存分別對應於用戶設備12
1~12
N的數據集合S
1~S
N。另外,處理器33電性連接儲存器31,並且用於執行圖2A到圖2B的各步驟。如圖2A到圖2B所示,在步驟S201中,處理器33取得分別對應於用戶設備12
1~12
N的數據集合S
1~S
N,數據集合S
1~S
N分別包含用戶設備12
1~12
N與至少一基站通訊時產生的多個通訊品質參數,並且在步驟S202中,處理器33使用降維演算法分析該些通訊品質參數以將數據集合S
1~S
N降維為自定義特徵集合DS
1~DS
N。
The
更詳細地說,每一數據集合可為D維的參數集合,即每一數據集合可包含D個通訊品質參數,D為大於1的整數。另外,本實施例的降維演算法可例如為高相關濾波法(High Correlation Filter)、隨機森林法(Random Forests)、前向特徵構造法(Forward Feature Construction)、反向特徵消除法(Backward Feature Elimination)、缺失值比率法(Missing Values Ratio)、低方差濾波法(Low Variance Filter)及主成分分析法(Principal Component Analysis)其中之一,但本發明不以此為限制。因此,處理器33可使用降維演算法分析該D個通訊品質參數(例如分析該D個通訊品質參數間的關聯性及/或相依性等)以將數據集合S
1~S
N降維為都僅包含K個通訊品質參數的自定義特徵集合DS
1~DS
N,即由D維的參數集合降為K維的參數集合,K為小於D的整數。
In more detail, each data set can be a D-dimensional parameter set, that is, each data set can include D communication quality parameters, and D is an integer greater than 1. In addition, the dimensionality reduction algorithm of this embodiment can be, for example, High Correlation Filter, Random Forests, Forward Feature Construction, Backward Feature Elimination Elimination), Missing Values Ratio, Low Variance Filter and Principal Component Analysis, but the present invention is not limited thereto. Therefore, the
舉例來說,當使用主成分分析法分析該些通訊品質參數時,處理器33會根據數據集合S
1~S
N建立共變異數矩陣(Covariance Matrix),並且分解共變異矩陣為特徵向量(Eigenvectors)和特徵值(Eigenvalues)。接著,處理器33會選取K個最大的特徵值所對應的K個特徵向量,並且對所選取的K個特徵向量進行排序。然後,處理器33使用排序後的K個特徵向量建立投影矩陣(Project Matrix),並且使用投影矩陣轉換數據集合S
1~S
N以獲得自定義特徵集合DS
1~DS
N。
For example, when using the principal component analysis method to analyze these communication quality parameters, the
由此可見,處理器33使用降維演算法分析該些通訊品質參數之目的在於找出數據集合S
1~S
N中較為關鍵的參數以供後續訓練模型用,藉此避免以過多的參數去訓練模型所產生的擬合過度(Overfitting)現象,進而能夠提升機器學習的精準度。請一併參閱表1和表2,表1是本發明實施例的數據集合,表2是本發明實施例的自定義特徵集合。
It can be seen that the purpose of the
如表1所示,每一數據集合的該些通訊品質參數可至少包括一參考訊號接收功率(Reference Signal Received Power,RSRP)、一接收訊號強度指標(Received Signal Strength Indication,RSSI)、一位元錯誤率(Bit Error Rate,BER)、一封包錯誤率(Packet Error Rate,PER)及一數據率(Data Rate),但本發明不以此為限制。
[表1]
另外,如表2所示,在經過步驟S202的降維處理後,處理器33可得到都僅包含參考訊號接收功率、接收訊號強度指標和位元錯誤率的自定義特徵集合DS
1~DS
N,但本發明亦不以此為限制。接著,在步驟S203中,處理器33會將自定義特徵集合DS
1~DS
N分為訓練集Tr以及測試集Te,並且在步驟S204中,使用分類演算法依據可傳輸性對訓練集Tr進行二元分類以決定出多個第一可傳輸樣本。
In addition, as shown in Table 2, after the dimension reduction processing in step S202, the
請一併參閱圖4,圖4是本發明實施例的自定義特徵集合經分為訓練集和測試集的示意圖。如圖4所示,每一自定義特徵集合可被表示為空間中的一點,且處理器33可使用隨機抽樣(Random Sampling)來從自定義特徵集合DS
1~DS
N中挑選一部分作為訓練集Tr而另一部分作為測試集Te,但本發明不以此為限制。總而言之,本發明不限制處理器33將自定義特徵集合DS
1~DS
N分為訓練集Tr和測試集Te的具體實現方式。另外,本實施例的分類演算法可例如為支援向量機法(Support Vector Machine)、線性分類法(Linear Classification)及K近鄰法(K-Nearest Neighbor)其中之一,但本發明亦不以此為限制。
Please also refer to FIG. 4 . FIG. 4 is a schematic diagram of a custom feature set in an embodiment of the present invention divided into a training set and a test set. As shown in Figure 4, each custom feature set can be represented as a point in space, and the
更詳細地說,在確定完訓練集Tr後,處理器33可使用分類演算法依據可傳輸性來把訓練集Tr內的每一自定義特徵集合分類為第一可傳輸樣本或第一不可傳輸樣本。例如,當訓練集Tr內的第i個自定義特徵集合可在重傳次數為128以上成功傳送數據的話,處理器33就能夠把訓練集Tr內的第i個自定義特徵集合分類為第一可傳輸樣本。相對地,當訓練集Tr內的第i個自定義特徵集合不可在重傳次數為128以上成功傳送數據的話,處理器33就能夠把訓練集Tr內的第i個自定義特徵集合分類為第一不可傳輸樣本。請一併參閱圖5,圖5是本發明實施例的訓練集經二元分類以決定出多個第一可傳輸樣本的示意圖。In more detail, after determining the training set Tr, the
如圖5所示,處理器33可用以一區分曲線L來分開訓練集Tr內的該些第一可傳輸樣本和該些第一不可傳輸樣本,且為了方便理解,該些第一可傳輸樣本的集合和該些第一不可傳輸樣本的集合可分別用以符號T11和T12來表示。然後,在步驟S205中,處理器33使用分群演算法依據用戶設備12
1~12
N與該至少一基站通訊時使用的多個重傳次數將該些第一可傳輸樣本分群為多個第一群組,該些第一群組分別對應於不同的該些重傳次數,並且在步驟S206中,處理器33使用該些第一群組對機器學習模型進行訓練以產生重傳次數預測模型。該重傳次數預測模型就用於預測用戶設備12
1~12
N與該至少一基站通訊時使用的該些重傳次數。
As shown in FIG. 5 , the
本實施例的分群演算法可例如為K平均法(K-means)、聚合式分群法(Agglomerative Clustering)及分列式分群法(Divisive Clustering)其中之一,但本發明不以此為限制。請一併參閱圖6,圖6是本發明實施例的第一可傳輸樣本分群為多個第一群組的示意圖。如圖6所示,本實施例可假設處理器33會使用分群演算法來把該些第一可傳輸樣本分群為三個第一群組G11~G13,且該些第一群組G11~G13分別對應於重傳次數為128、256及1024。因此,在使用該些第一群組G11~G13對機器學習模型進行訓練後,處理器33就能夠得到可根據用戶設備的通訊品質來預測重傳次數為128、256或1024的至少一函數,而該至少一函數就為機器學習模型經訓練而產生的重傳次數預測模型。由於機器學習模型的訓練原理已為本領域技術人員所習知,因此有關其細節就不再多加贅述。The clustering algorithm in this embodiment can be, for example, one of K-means, Agglomerative Clustering and Divisive Clustering, but the present invention is not limited thereto. Please also refer to FIG. 6 . FIG. 6 is a schematic diagram of grouping the first transmittable samples into a plurality of first groups according to an embodiment of the present invention. As shown in FIG. 6 , in this embodiment, it can be assumed that the
應當理解的是,由於這時候的重傳次數預測模型是尚未進行優化的模型,因此圖2A到圖2B的重傳次數預測方法還可包括步驟S207~S212。在步驟S207中,處理器33可使用測試集Te測試重傳次數預測模型以得到一準確率,並且在步驟S208中,判斷該準確率是否達到一準確率標準。當該準確率未達到準確率標準時,處理器33會先執行步驟S209以選取訓練集Tr的一子集作為驗證集Va,並且在步驟S210中,使用分類演算法依據可傳輸性對驗證集Va進行二元分類以決定出多個第二可傳輸樣本。It should be understood that, since the retransmission times prediction model at this time is an unoptimized model, the method for retransmission times prediction in FIG. 2A to FIG. 2B may further include steps S207-S212. In step S207, the
接著,在步驟S211中,處理器33使用分群演算法依據用戶設備12
1~12
N與該至少一基站通訊時使用的該些重傳次數將該些第二可傳輸樣本分群為多個第二群組,該些第二群組分別對應於不同的該些重傳次數,並且在步驟S212中,處理器33使用該些第二群組對重傳次數預測模型再次進行訓練以更新重傳次數預測模型。在步驟S212後,處理器33返回執行步驟S207~S208,並且當該準確率還未達到準確率標準時,處理器33則重複執行步驟S209~S212和S207~S208直到該準確率達到準確率標準。
Next, in step S211, the
更詳細地說,針對處理器33如何選取訓練集Tr的一子集作為驗證集Va,本發明共提供了不同的三種實施方式。在第一種實施方式中,處理器33可計算訓練集Tr內的每一自定義特徵集合與區分曲線L的距離,並且從訓練集Tr內的該些自定義特徵集合中選取距離小於一門檻值者作為驗證集Va。請一併參閱圖7,圖7是本發明第一實施例的訓練集經選取一子集作為驗證集示意圖。More specifically, the present invention provides three different implementation manners for how the
如圖7所示,距離越小於門檻值的自定義特徵集合會越靠近區分曲線L。因此,在第一種實施方式中,處理器33也可視為再從訓練集Tr中挑選越靠近區分曲線L的多個自定義特徵集合以作為驗證集Va。需說明的是,對於這時候的處理器33而言,越靠近區分曲線L的自定義特徵集合是越難準確分類為第一可傳輸樣本或第一不可傳輸樣本。因此,處理器33挑選越靠近區分曲線L的多個自定義特徵集合以作為驗證集Va之目的在於利用該些自定義特徵集合來決定新的區分曲線L。As shown in Figure 7, the custom feature set whose distance is smaller than the threshold value will be closer to the distinguishing curve L. Therefore, in the first implementation manner, the
請一併參閱圖8,圖8是圖7的驗證集經二元分類以決定出多個第二可傳輸樣本的示意圖。如圖8所示,在確定完驗證集Va後,處理器33可再使用分類演算法來把訓驗證集Va內的每一自定義特徵集合分類為第二可傳輸樣本或第二不可傳輸樣本。因此,處理器33可利用驗證集Va內的該些自定義特徵集合來決定新的區分曲線L,並且用以新的區分曲線L來分開驗證集Va內的該些第二可傳輸樣本和該些第二不可傳輸樣本。Please also refer to FIG. 8 . FIG. 8 is a schematic diagram of determining a plurality of second transferable samples from the validation set in FIG. 7 through binary classification. As shown in FIG. 8, after the verification set Va is determined, the
由此可見,若以驗證集Va內的該些自定義特徵集合來決定新的區分曲線L,則驗證集Va內的該些自定義特徵集合就能夠更準確分類為第二可傳輸樣本或第二不可傳輸樣本。另一方面,在第二種實施方式中,處理器33可從訓練集Tr中確定應用類型不同的分層,並從每一分層中選出至少一自定義特徵集合作為驗證集Va。具體而言,每一自定義特徵集合可具有一應用類型資訊,用於指出對應的用戶設備的應用類型。因此,處理器33可根據每一自定義特徵集合的應用類型資訊,將訓練集Tr內的該些自定義特徵集合分群為多個第三群組,該些第三群組分別對應於不同的多個應用類型,並且從每一第三群組的該些自定義特徵集合中選取至少一者作為驗證集Va。It can be seen that if these self-defined feature sets in the verification set Va are used to determine the new distinguishing curve L, then these self-defined feature sets in the verification set Va can be more accurately classified as the second transferable sample or the first 2. Samples cannot be transmitted. On the other hand, in the second implementation manner, the
請一併參閱圖9,圖9是本發明第二實施例的訓練集經選取一子集作為驗證集示意圖。如圖9所示,本實施例可假設處理器33會將訓練集Tr內的該些自定義特徵集合分群為三個第三群組G31~G33,且該些第三群組G31~G33分別對應於第一應用類型、第二應用類型和第三應用類型。為了方便理解,第三群組G31的該些自定義特徵集合用以方形符號來表示,第三群組G32的該些自定義特徵集合則用以三角形符號來表示,且第三群組G33的該些自定義特徵集合用以圓形符號來表示。因此,在第二種實施方式中,該些第三群組G31~G33也可視為應用類型不同的分層,且處理器33可再使用隨機抽樣來從每一第三群組的該些自定義特徵集合中挑選至少一者作為驗證集Va。Please also refer to FIG. 9 . FIG. 9 is a schematic diagram of a subset of the training set selected as the verification set according to the second embodiment of the present invention. As shown in FIG. 9 , in this embodiment, it can be assumed that the
由此可見,處理器33使用第二種實施方式之目的在於打破應用類型的相依性,使得處理器33在更新重傳次數預測模型時能考量到應用類型對重傳次數的影響。類似地,在第三種實施方式中,處理器33可從訓練集Tr中確定區域不同的群集,並從每一群集中選出至少一自定義特徵集合作為驗證集Va。具體而言,每一自定義特徵集合可具有一區域資訊,用於指出對應的用戶設備所在的區域,例如位於哪一基站的訊號涵蓋範圍,但本發明不以此為限制。因此,處理器33可根據每一自定義特徵集合的區域資訊,將訓練集Tr內的該些自定義特徵集合分群為多個第三群組,該些第三群組分別對應於不同的多個區域,並且從每一第三群組的該些自定義特徵集合中選取至少一者作為驗證集Va。It can be seen that the purpose of the
請一併參閱圖10,圖10是本發明第三實施例的訓練集經選取一子集作為驗證集示意圖。如圖10所示,本實施例可假設處理器33會將訓練集Tr內的該些自定義特徵集合分群為三個第三群組G34~G36,且該些第三群組G34~G36分別對應於第一區域、第二區域和第三區域。為了方便理解,第三群組G34的該些自定義特徵集合用以方形符號來表示,第三群組G35的該些自定義特徵集合則用以三角形符號來表示,且第三群組G36的該些自定義特徵集合用以圓形符號來表示。因此,在第三種實施方式中,該些第三群組G34~G36也可視為區域不同的群集,且處理器33可再使用隨機抽樣來從每一第三群組的該些自定義特徵集合中挑選至少一者作為驗證集Va。Please also refer to FIG. 10 . FIG. 10 is a schematic diagram of a subset of the training set selected as the verification set according to the third embodiment of the present invention. As shown in FIG. 10 , in this embodiment, it can be assumed that the
由此可見,處理器33使用第三種實施方式之目的在於打破區域的相依性,使得處理器33在更新重傳次數預測模型時能考量到區域對重傳次數的影響。另外, 在不論使用第二種或第三種實施方式以確定完驗證集Va後,處理器33都會同樣再使用分類演算法來把訓驗證集Va內的每一自定義特徵集合分類為第二可傳輸樣本或第二不可傳輸樣本。It can be seen that the purpose of the
接著,本實施例可假設處理器33會使用分群演算法來把該些第二可傳輸樣本分群為三個第二群組G21~G23。該些第二群組G21~G23也可分別對應於重傳次數為128、256及1024,但本發明不以此為限制。因此,在使用該些第二群組G21~G23對機器學習模型再次進行訓練後,處理器33就能夠對重傳次數預測模型進行優化,進而提升重傳次數預測模型的精準度。最後,當該準確率達到準確率標準時,處理器33可執行步驟S213以輸出重傳次數預測模型該至少一基站,使得該至少一基站能夠根據重傳次數預測模型對於不同通訊品質的用戶設備配置適當的重傳次數。Next, in this embodiment, it may be assumed that the
綜上所述,本發明的其中一有益效果在於利用降維演算法找出用戶設備的數據集合中較為關鍵的參數,藉此避免以過多的參數去訓練模型所產生的擬合過度現象。另外,若重傳次數預測模型的準確率未達到準確率標準,本發明的重傳次數預測方法及重傳次數預測裝置會再以考慮其他因素(例如與區分曲線的距離、應用類型或區域)來選取訓練集的子集作為驗證集,並且使用驗證集來進行模型優化,以提升重傳次數預測模型的精準度。藉此,基站還能夠根據本發明的重傳次數預測模型對於不同通訊品質的用戶設備配置適當的重傳次數,達到降低傳輸錯誤率,並且提高資源利用率與傳輸率的功效。To sum up, one of the beneficial effects of the present invention is to use the dimensionality reduction algorithm to find the more critical parameters in the data set of the user equipment, thereby avoiding the phenomenon of over-fitting caused by training the model with too many parameters. In addition, if the accuracy rate of the retransmission number prediction model does not meet the accuracy rate standard, the retransmission number prediction method and the retransmission number prediction device of the present invention will further consider other factors (such as distance from the distinguishing curve, application type or area) To select a subset of the training set as the verification set, and use the verification set to optimize the model to improve the accuracy of the retransmission prediction model. In this way, the base station can also configure appropriate retransmission times for user equipments with different communication qualities according to the retransmission times prediction model of the present invention, so as to reduce transmission error rate and improve resource utilization and transmission rate.
以上所提供的內容僅為本發明的優選可行實施例,並非因此侷限本發明的申請專利範圍,所以凡是運用本發明說明書及圖式內容所做的等效技術變化,均包含於本發明的申請專利範圍內。The content provided above is only a preferred feasible embodiment of the present invention, and does not therefore limit the scope of the patent application of the present invention, so all equivalent technical changes made by using the description and drawings of the present invention are included in the application of the present invention within the scope of the patent.
1:無線通訊系統 11 1~11 M:基站 12 1~12 N:用戶設備 C 1~C M:訊號涵蓋範圍 S 1~S N:數據集合 DS 1~DS N:自定義特徵集合 3:重傳次數預測裝置 31:儲存器 33:處理器 Tr:訓練集 Te:測試集 L:區分曲線 T11:第一可傳輸樣本的集合 T12:第一不可傳輸樣本的集合 G11~G13:第一群組 Va:驗證集 G21~G23:第二群組 G31~G33,G34~G36:第三群組 S201~S213:流程步驟 1: wireless communication system 11 1 ~11 M : base station 12 1 ~12 N : user equipment C 1 ~C M : signal coverage S 1 ~S N : data set DS 1 ~DS N : custom feature set 3: heavy Transmission number prediction device 31: storage 33: processor Tr: training set Te: test set L: distinguishing curve T11: first set of transmittable samples T12: first set of non-transmittable samples G11~G13: first group Va: verification set G21~G23: second group G31~G33, G34~G36: third group S201~S213: process steps
圖1是本發明實施例的無線通訊系統的示意圖。FIG. 1 is a schematic diagram of a wireless communication system according to an embodiment of the present invention.
圖2A到圖2B是本發明實施例的重傳次數預測方法的步驟流程圖。FIG. 2A to FIG. 2B are flowcharts of the steps of the method for predicting the number of retransmissions according to the embodiment of the present invention.
圖3是本發明實施例的重傳次數預測裝置的功能方塊示意圖。FIG. 3 is a schematic functional block diagram of an apparatus for predicting the number of retransmissions according to an embodiment of the present invention.
圖4是本發明實施例的自定義特徵集合經分為訓練集和測試集的示意圖。Fig. 4 is a schematic diagram of a custom feature set in an embodiment of the present invention divided into a training set and a test set.
圖5是本發明實施例的訓練集經二元分類以決定出多個第一可傳輸樣本的示意圖。FIG. 5 is a schematic diagram of binary classification of a training set to determine a plurality of first transmittable samples according to an embodiment of the present invention.
圖6是本發明實施例的第一可傳輸樣本分群為多個第一群組的示意圖。FIG. 6 is a schematic diagram of grouping first transmittable samples into a plurality of first groups according to an embodiment of the present invention.
圖7是本發明第一實施例的訓練集經選取一子集作為驗證集示意圖。FIG. 7 is a schematic diagram of a subset of the training set selected as a verification set according to the first embodiment of the present invention.
圖8是圖7的驗證集經二元分類以決定出多個第二可傳輸樣本的示意圖。FIG. 8 is a schematic diagram of binary classification of the verification set in FIG. 7 to determine a plurality of second transferable samples.
圖9是本發明第二實施例的訓練集經選取一子集作為驗證集示意圖。FIG. 9 is a schematic diagram of a subset of the training set selected as a verification set according to the second embodiment of the present invention.
圖10是本發明第三實施例的訓練集經選取一子集作為驗證集示意圖。FIG. 10 is a schematic diagram of a subset of the training set selected as the verification set according to the third embodiment of the present invention.
S201~S208,S213:流程步驟 S201~S208, S213: process steps
Claims (14)
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW110140677A TWI777840B (en) | 2021-11-02 | 2021-11-02 | Number of repetitions prediction method and number of repetitions prediction device |
CN202111336226.5A CN116095747A (en) | 2021-11-02 | 2021-11-11 | Retransmission number prediction method and retransmission number prediction device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW110140677A TWI777840B (en) | 2021-11-02 | 2021-11-02 | Number of repetitions prediction method and number of repetitions prediction device |
Publications (2)
Publication Number | Publication Date |
---|---|
TWI777840B TWI777840B (en) | 2022-09-11 |
TW202320503A true TW202320503A (en) | 2023-05-16 |
Family
ID=84958227
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW110140677A TWI777840B (en) | 2021-11-02 | 2021-11-02 | Number of repetitions prediction method and number of repetitions prediction device |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN116095747A (en) |
TW (1) | TWI777840B (en) |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10425294B2 (en) * | 2014-01-06 | 2019-09-24 | Cisco Technology, Inc. | Distributed and learning machine-based approach to gathering localized network dynamics |
CN103985055A (en) * | 2014-05-30 | 2014-08-13 | 西安交通大学 | Stock market investment decision-making method based on network analysis and multi-model fusion |
TWI715457B (en) * | 2020-03-04 | 2021-01-01 | 國立中正大學 | Unsupervised malicious flow detection system and method |
-
2021
- 2021-11-02 TW TW110140677A patent/TWI777840B/en active
- 2021-11-11 CN CN202111336226.5A patent/CN116095747A/en active Pending
Also Published As
Publication number | Publication date |
---|---|
CN116095747A (en) | 2023-05-09 |
TWI777840B (en) | 2022-09-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109195214B (en) | Genetic algorithm-based NOMA power allocation method | |
CN112825576B (en) | Cell capacity expansion determining method, device and storage medium | |
CN108242961B (en) | Full-duplex cognitive radio network cooperative spectrum sensing method based on ensemble learning | |
CN113382477B (en) | Method for modeling uplink interference between wireless network users | |
CN113379176A (en) | Telecommunication network abnormal data detection method, device, equipment and readable storage medium | |
CN106936527B (en) | Multi-user cooperative spectrum sensing method based on double thresholds | |
TWI777840B (en) | Number of repetitions prediction method and number of repetitions prediction device | |
CN114465681B (en) | Multi-node cooperation spectrum sensing method and device for electric power Internet of things | |
CN112243283B (en) | Cell-Free Massive MIMO network clustering calculation method based on successful transmission probability | |
Zhang et al. | A data-driven approach to client-transparent access selection of Dual-Band WiFi | |
CN114205238A (en) | Network resource optimization and model training method, device, storage medium and equipment | |
Pu et al. | Primary user emulation detection algorithm based on distributed sensor networks | |
Mondal et al. | Station Grouping Mechanism using Machine Learning Approach for IEEE 802.11 ah | |
CN114792138A (en) | Machine learning model interpretation method, device and storage medium | |
CN112601249A (en) | Interference source identification method and device, network equipment and storage medium | |
Loh et al. | Collision and Energy Efficiency Assessment of LoRaWANs with Cluster-based Gateway Placement | |
Cichoń | Soft network organisation towards future distributed ML-Based sensing systems | |
Pavan et al. | Machine Learning based Prediction for Channel Stability in a 5G Network | |
CN111031606A (en) | Wireless network resource allocation method, system and storage medium | |
WO2022062908A1 (en) | Method and device for configuring switching configuration information | |
Gadre et al. | Designing an ML-Friendly Wireless Physical Layer for Low-Power IoT | |
Al Khansa et al. | A hybrid scheduled and group-based random access solution for massive mtc networks | |
CN110636512B (en) | Equipment model selection method and device | |
CN117193675B (en) | Solid-state storage management system based on distributed computing capacity | |
CN115102909B (en) | IHHO-FCM algorithm-based network flow classification method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GD4A | Issue of patent certificate for granted invention patent |