TWI785718B - Self-healing system and self-healing method for telecommunication network - Google Patents
Self-healing system and self-healing method for telecommunication network Download PDFInfo
- Publication number
- TWI785718B TWI785718B TW110128703A TW110128703A TWI785718B TW I785718 B TWI785718 B TW I785718B TW 110128703 A TW110128703 A TW 110128703A TW 110128703 A TW110128703 A TW 110128703A TW I785718 B TWI785718 B TW I785718B
- Authority
- TW
- Taiwan
- Prior art keywords
- network
- obstacle
- self
- deep learning
- module
- Prior art date
Links
Images
Landscapes
- Radio Relay Systems (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
Description
本發明是有關於一種電信網路技術,且特別是有關於一種電信網路的自我修復系統和自我修復方法。The present invention relates to a telecommunication network technology, and in particular to a self-repairing system and a self-repairing method of a telecommunication network.
在傳統的網路管理系統中,當電信網路的使用者發現網路異常時,使用者可以透過網路客服系統向網路服務供應商進行申告,反應電信網路有障礙。服務供應商可根據電信網路的路由資訊,逐段進行查測,找出網路障礙點,並依據經驗執行人工修復。如果網路服務供應商無法執行正確修復動作,可能會導致網路持續無法運作,將耗費昂貴的成本。In the traditional network management system, when the user of the telecommunication network finds that the network is abnormal, the user can report to the network service provider through the network customer service system, reflecting that there is an obstacle in the telecommunication network. The service provider can conduct a segment-by-segment inspection based on the routing information of the telecommunication network, find out network obstacles, and perform manual repairs based on experience. If the ISP fails to perform corrective repair actions, the network may remain inoperable and costly.
本發明提供一種電信網路的自我修復系統和自我修復方法,可自動地修復電信網路的障礙。The invention provides a self-repairing system and a self-repairing method of a telecommunication network, which can automatically repair obstacles of the telecommunication network.
本發明的一種電信網路的自我修復系統,包含處理器、儲存媒體以及收發器。儲存媒體儲存多個模組。處理器耦接儲存媒體以及收發器,並且存取和執行多個模組,其中多個模組包含障礙查測路由模組、深度學習推薦模組以及障礙自動修復模組。障礙查測路由模組取得對應於電信網路的網路資訊。深度學習推薦模組根據網路資訊以及深度學習模型產生機率向量,並且根據機率向量決定障礙排除手段以及障礙排除對象。障礙自動修復模組通過收發器輸出對應於障礙排除手段以及障礙排除對象的指令。A self-repairing system of a telecommunication network of the present invention includes a processor, a storage medium and a transceiver. The storage medium stores multiple modules. The processor is coupled to the storage medium and the transceiver, and accesses and executes multiple modules, wherein the multiple modules include an obstacle detection and routing module, a deep learning recommendation module, and an obstacle automatic repair module. The obstacle detection routing module obtains network information corresponding to the telecommunication network. The deep learning recommendation module generates probability vectors based on network information and deep learning models, and determines obstacle removal methods and objects based on the probability vectors. The obstacle automatic repair module outputs instructions corresponding to the obstacle removal means and the obstacle removal object through the transceiver.
在本發明的一實施例中,上述的多個模組更包含查測路由資料庫。查測路由資料庫儲存網路資訊,其中障礙查測路由模組通過收發器接收對應於電信網路的障礙申告通報,並且存取查測路由資料庫以取得對應於障礙申告通報的網路資訊。In an embodiment of the present invention, the above-mentioned modules further include a query routing database. The route detection database stores network information, wherein the fault detection routing module receives the fault report report corresponding to the telecommunication network through the transceiver, and accesses the route search database to obtain the network information corresponding to the fault report report .
在本發明的一實施例中,上述的多個模組更包含查測資料清理模組。查測資料清理模組對網路資訊執行前處理以產生輸入資料,其中深度學習推薦模組將輸入資料輸入至深度學習模型以產生機率向量。In an embodiment of the present invention, the above-mentioned multiple modules further include a query data cleaning module. The query data cleaning module performs pre-processing on the network information to generate input data, and the deep learning recommendation module inputs the input data to the deep learning model to generate a probability vector.
在本發明的一實施例中,上述的前處理包含下列的至少其中之一:特徵篩選、正規化以及異常值刪除。In an embodiment of the present invention, the above pre-processing includes at least one of the following: feature screening, normalization and outlier removal.
在本發明的一實施例中,上述的深度學習模型為對應於多元分類技術。In an embodiment of the present invention, the above-mentioned deep learning model corresponds to a multi-class classification technique.
在本發明的一實施例中,上述的機率向量包含分別對應於多個障礙排除手段以及多個障礙排除對象的多個機率,其中深度學習推薦模組根據多個機率的排序產生優先清單,其中障礙自動修復模組根據優先清單輸出指令。In an embodiment of the present invention, the above-mentioned probability vector includes a plurality of probabilities respectively corresponding to a plurality of obstacle removal means and a plurality of obstacle removal objects, wherein the deep learning recommendation module generates a priority list according to the ordering of the plurality of probabilities, wherein The obstacle automatic repair module outputs instructions according to the priority list.
在本發明的一實施例中,上述的多個模組更包含歷史查測申告資料庫。歷史查測申告資料庫通過收發器接收對應於電信網路的障礙修復記錄,並且儲存障礙修復記錄;以及深度學習訓練模組,根據障礙修復記錄更新深度學習模型。In an embodiment of the present invention, the above-mentioned multiple modules further include a database of historical inspection reports. The historical inspection report database receives the fault repair record corresponding to the telecommunication network through the transceiver, and stores the fault repair record; and the deep learning training module updates the deep learning model according to the fault repair record.
在本發明的一實施例中,上述的障礙排除手段包含下列的至少其中之一:連接埠重置、組態重新供裝以及網路限速。In an embodiment of the present invention, the above troubleshooting method includes at least one of the following: port reset, configuration re-provisioning and network speed limit.
在本發明的一實施例中,上述的電信網路包含至少一設備,其中網路資訊包含對應於至少一設備的設備資訊以及組態資訊。In an embodiment of the present invention, the above-mentioned telecommunication network includes at least one device, wherein the network information includes device information and configuration information corresponding to the at least one device.
本發明的一種電信網路的自我修復方法,包含:取得對應於電信網路的網路資訊;根據網路資訊以及深度學習模型產生機率向量,並且根據機率向量決定障礙排除手段以及障礙排除對象;以及輸出對應於障礙排除手段以及障礙排除對象的指令。A self-repair method for a telecommunication network of the present invention includes: obtaining network information corresponding to the telecommunication network; generating a probability vector according to the network information and a deep learning model, and determining an obstacle removal method and an obstacle removal object according to the probability vector; And an instruction corresponding to the obstacle removal means and the obstacle removal object is output.
基於上述,本發明的自我修復系統可利用查測申告和查測路由資料,先用規則式的判斷元件,進行障礙資料清理,再運用深度學習模型,進一步診斷並產出障礙修復的推薦清單。依據模型推薦修復方式,自我修復系統可自動執行障礙修復,例如:自我修復系統可執行連接埠重置、網路組態重新供裝或網路限速等。深度學習模型可以從過往的歷史資料中學習。當障礙點的資訊和歷史資訊相似時,深度學習模型即會自動推薦理想的障礙修復手段。根據本發明,電信網路的管理人員可參考自動產出的障礙修復的推薦清單,加速完成網路障礙修復,減少網路障礙申告結單的流程作業時間。對於網路服務供應商,本發明可降低維運的人力與成本,且大幅度地減少網路問題修復時間。Based on the above, the self-repair system of the present invention can use the inspection report and inspection routing data to first use the rule-based judgment element to clean up the obstacle data, and then use the deep learning model to further diagnose and generate a recommendation list for obstacle repair. According to the repair method recommended by the model, the self-healing system can automatically perform obstacle repair, for example: the self-healing system can perform port reset, network configuration re-provisioning or network speed limit, etc. Deep learning models can learn from past historical data. When the information of the obstacle point is similar to the historical information, the deep learning model will automatically recommend the ideal obstacle repair method. According to the present invention, the management personnel of the telecommunication network can refer to the recommended list of automatically produced fault repairs to speed up the completion of network fault repairs and reduce the process operation time of network fault declaration and statement. For network service providers, the present invention can reduce the manpower and cost of maintenance and operation, and greatly reduce the repair time of network problems.
為了使本發明之內容可以被更容易明瞭,以下特舉實施例作為本發明確實能夠據以實施的範例。另外,凡可能之處,在圖式及實施方式中使用相同標號的元件/構件/步驟,係代表相同或類似部件。In order to make the content of the present invention more comprehensible, the following specific embodiments are taken as examples in which the present invention can actually be implemented. In addition, wherever possible, elements/components/steps using the same reference numerals in the drawings and embodiments represent the same or similar parts.
圖1根據本發明的一實施例繪示電信網路的示意圖。電信網路可可包含多個網路節點。網路節點例如是終端裝置、光纖網路單元(optical network unit,ONU)、光纖線路終端(optical line termination,OLT)或多重服務邊緣路由器(multi-service edge router,MSER)等,本發明不限於此。FIG. 1 shows a schematic diagram of a telecommunication network according to an embodiment of the present invention. A telecommunications network may contain multiple network nodes. A network node is, for example, a terminal device, an optical network unit (ONU), an optical line terminal (OLT) or a multi-service edge router (MSER). The present invention is not limited to this.
圖2根據本發明的一實施例繪示一種電信網路的自我修復系統100的示意圖。請參照圖1和圖2,自我修復系統100可用以監視終端裝置50與網際網路70之間的電信網路60。在本實施例中,電信網路60可包含光纖網路單元61、光纖線路終端62、多重服務邊緣路由器63以及多重服務邊緣路由器64等網路節點。FIG. 2 is a schematic diagram of a self-
自我修復系統100可包含處理器110、儲存媒體120以及收發器130。處理器110例如是中央處理單元(central processing unit,CPU),或是其他可程式化之一般用途或特殊用途的微控制單元(micro control unit,MCU)、微處理器(microprocessor)、數位信號處理器(digital signal processor,DSP)、可程式化控制器、特殊應用積體電路(application specific integrated circuit,ASIC)、圖形處理器(graphics processing unit,GPU)、影像訊號處理器(image signal processor,ISP)、影像處理單元(image processing unit,IPU)、算數邏輯單元(arithmetic logic unit,ALU)、複雜可程式邏輯裝置(complex programmable logic device,CPLD)、現場可程式化邏輯閘陣列(field programmable gate array,FPGA)或其他類似元件或上述元件的組合。處理器110可耦接至儲存媒體120以及收發器130,並且存取和執行儲存於儲存媒體120中的多個模組和各種應用程式。The self-
儲存媒體120例如是任何型態的固定式或可移動式的隨機存取記憶體(random access memory,RAM)、唯讀記憶體(read-only memory,ROM)、快閃記憶體(flash memory)、硬碟(hard disk drive,HDD)、固態硬碟(solid state drive,SSD)或類似元件或上述元件的組合,而用於儲存可由處理器110執行的多個模組或各種應用程式。在本實施例中,儲存媒體120可儲存包含障礙查測路由模組121、查測路由資料庫122、查測資料清理模組123、深度學習推薦模組124、障礙自動修復模組125、歷史查測申告資料庫126以及深度學習訓練模組127等多個模組,其功能將於後續說明。The
收發器130以無線或有線的方式傳送及接收訊號。收發器130還可以執行例如低噪聲放大、阻抗匹配、混頻、向上或向下頻率轉換、濾波、放大以及類似的操作。The
圖3根據本發明的一實施例繪示由多個模組對電信網路執行自我修復程序的流程圖。在本實施例中,自我修復系統100可通過收發器130通訊連接至網管客服系統20以及網管維運系統30。查測路由資料庫122可通過收發器130存取電信網路60以取得並儲存電信網路60的網路資訊。另一方面,查測路由資料庫122也可自網管客服系統20取得並儲存電信網路60的網路資訊。FIG. 3 is a flowchart illustrating a self-healing procedure performed by a plurality of modules on a telecommunication network according to an embodiment of the present invention. In this embodiment, the self-
在步驟S301中,障礙查測路由模組121可自網管客服系統20接收對應於通信網路60的障礙申告通報。障礙查測路由模組121可解讀障礙申告通報以取得對應的工務資料。障礙查測路由模組121可具備端對端電信網路查測、透通防火牆以及介面資料傳送與交換等功能。障礙查測路由模組121可通過標準資料庫指令對查測路由資料庫122中的資料進行擷取、修改或查詢等操作。In step S301 , the fault
在步驟S302中,障礙查測路由模組121可存取查測路由資料庫122以取得對應於障礙申告通報的網路資訊,其中所述網路資訊即為電信網路60的網路資訊。具體來說,障礙查測路由模組121可通過標準資料存取指令讀取查測路由資料庫122,藉以取得對應於障礙申告通報的網路資訊。網路資訊可包含電信網路60中的設備(例如:光纖網路單元61、光纖線路終端62、多重服務邊緣路由器63或多重服務邊緣路由器64)的設備資訊以及組態資訊。In step S302 , the fault detection and
在步驟S303中,障礙查測路由模組121可將網路資訊傳送給查測資料清理模組123。In step S303 , the obstacle
在步驟S304中,查測資料清理模組123可對網路資訊執行前處理以產生用於訓練深度學習模型的輸入資料。前處理可包含特徵篩選、資料正規化或異常值刪除等,本發明不限於此。In step S304, the query
在步驟S305中,深度學習推薦模組124可根據網路資訊以及深度學習模型產生機率向量,並且根據所述機率向量決定障礙排除手段以及障礙排除對象。具體來說,深度學習推薦模組124可儲存採用多元分類(multiclass classification)技術的深度學習模型,並可將經過前處理過的網路資訊輸入至深度學習模型中。深度學習模型可輸出對應於網路資訊的機率向量。機率向量可包含分別對應於多個障礙排除手段以及多個障礙排除對象的多個機率。障礙排除手段可包含但不限於連接埠重置、組態重新供裝或網路限速等。障礙排除對象可包含電信網路60中的設備,諸如光纖網路單元61、光纖線路終端62、多重服務邊緣路由器63或多重服務邊緣路由器64。深度學習推薦模組124可根據多個機率的排序產生優先清單。具體來說,假設多個機率包含第一機率和第二機率,其中第一機率大於第二機率。深度學習推薦模組124可將對應於第一機率的障礙排除手段和障礙排除對象排列在優先清單中的前方,並可將對應於第二機率的障礙排除手段和障礙排除對象排列在優先清單中的後方。也就是說,對應於第一機率的障礙排除手段和障礙排除對象優先於對應於第二機率的障礙排除手段和障礙排除對象。In step S305 , the deep
舉例來說,電信網路60的網路資訊的特徵可包含設備種類、地理區域、雜訊比(正規化後的訊號雜訊比)或光功率(正規化後的光功率)等參數,如表1所示。深度學習推薦模組124可將如表1所示的網路資訊(即:設備種類、地理區域、雜訊比或光功率)輸入至深度學習模型以產生機率向量。機率向量可包含對應於光纖網路單元61和連接埠重置的機率「0.7」、對應於光纖網路單元61和組態重新供裝的機率「0.2」、對應於光纖網路單元61和網路限速的機率「0.1」、對應於光纖線路終端62和連接埠重置的機率「0.3」、對應於光纖線路終端62和組態重新供裝的機率「0.5」、對應於光纖線路終端62和網路限速的機率「0.2」、對應於重服務邊緣路由器63和連接埠重置的機率「0.3」、對應於重服務邊緣路由器63和組態重新供裝的機率「0.2」、對應於重服務邊緣路由器63和網路限速的機率「0.5」、對應於重服務邊緣路由器64和連接埠重置的機率「0.6」、對應於重服務邊緣路由器64和組態重新供裝的機率「0.1」以及對應於重服務邊緣路由器64和網路限速的機率「0.3」。
表1
接著,深度學習推薦模組124可根據修復規則以及上述的機率向量排序障礙排除手段以及障礙排除對象以產生優先清單。由實務經驗可知電信網路中越靠近使用者的終端裝置的設備發生障礙的可能性越高。因此,修復規則可預設為「根據障礙排除對象與終端裝置之間的設備數量由小到大排序以決定障礙排除對象的優先度」。以圖1的電信網路60為例,由於光纖網路單元61與終端裝置50之間的設備數量為「0」,故深度學習推薦模組124可根據修復規則判斷光纖網路單元61為具有最高優先度的障礙排除對象。由於光纖線路終端62與終端裝置50之間的設備數量為「1」,故深度學習推薦模組124可根據修復規則判斷光纖線路終端62為具有次高優先度的障礙排除對象。由於多重服務邊緣路由器63與終端裝置50之間的設備數量為「2」,故深度學習推薦模組124可根據修復規則判斷多重服務邊緣路由器63為具有次低優先度的障礙排除對象。由於多重服務邊緣路由器64與終端裝置50之間的設備數量為「3」,故深度學習推薦模組124可根據修復規則判斷多重服務邊緣路由器64為具有最低優先度的障礙排除對象。Then, the deep
在決定各個障礙排除對象的優先度後,深度學習推薦模組124可根據對應於障礙排除對象多個機率產生優先清單。具體來說,深度學習推薦模組124可將對應於障礙排除對象的多個機率由大至小排序以決定對應於所述障礙排除對象的障礙排除手段的優先度。以表1為例,深度學習推薦模組124可先對作為具有最高優先度之障礙排除對象的光纖網路單元61的障礙排除手段進行排序。由於對應於「連接埠重置」的機率「0.7」大於對應於「組態重新供裝」的機率「0.2」,並且對應於「組態重新供裝」的機率「0.2」大於對應於「網路限速」的機率「0.1」。據此,深度學習推薦模組124可根據機率的大小排序障礙排除手段,以使「連接埠重置」優先於「組態重新供裝」,並使「組態重新供裝」優先於「網路限速」。基於類似的方式,深度學習推薦模組124可排序每一個障礙排除對象的障礙排除手段以產生如表2所示的優先清單。
表2
在步驟S306中,障礙自動修復模組125可根據優先清單以通過收發器130輸出對應於障礙排除手段以及障礙排除對象的指令。網管維運系統30可自障礙自動修復模組125接收指令,並且根據指令所指示的障礙排除手段來自動地修復指令所指示的障礙排除對象。In step S306 , the obstacle auto-
在步驟S307中,在網管維運系統30完成電信網路60的修復後,歷史查測申告資料庫126可通過收發器130接收來自網管維運系統30的電信網路60的障礙修復記錄,並可儲存所述障礙修復記錄。舉例來說,網管維運系統30可傳送包含障礙修復記錄的申告結單記錄給歷史查測申告資料庫126。In step S307, after the network management and
在一實施例中,其他元件(例如:網管維運系統30或深度學習訓練模組127)可通過標準資料庫指令存取歷史查測申告資料庫126中的資料以執行擷取、查詢或修改等操作。In one embodiment, other components (for example: the network
在步驟S308中,深度學習訓練模組127可將歷史查測申告資料庫126中的障礙修復記錄作為訓練資料集以重新訓練或更新儲存在深度學習推薦模組124的深度學習模型。表3為訓練資料集的範例。
表3
圖4根據本發明的一實施例繪示一種電信網路的自我修復方法的流程圖,其中所述自我修復方法可由如圖2所示的自我修復系統100實施。在步驟S401中,取得對應於電信網路的網路資訊。在步驟S402中,根據網路資訊以及深度學習模型產生機率向量,並且根據機率向量決定障礙排除手段以及障礙排除對象。在步驟S403中,輸出對應於障礙排除手段以及障礙排除對象的指令。FIG. 4 shows a flow chart of a self-healing method for a telecommunication network according to an embodiment of the present invention, wherein the self-healing method can be implemented by the self-healing
綜上所述,本發明可讓網路服務營運商能快速地修復端對端電信網路的障礙,可節省障礙查測的時間成本。本發明的方法可實施於現有設備。因此,網路服務營運商不需新購設備,也可執行本發明。本發明可與網管客服系統或網管維運系統協作。在網管人員決定將人員派工到現場進行修復之前,可事先通過本發明執行自動修復,並提供修復優先順序清單,可大幅地降低查修電信網路的人力成本、維運人員的工作量以及網路障礙的修復時間。To sum up, the present invention enables network service operators to quickly repair the faults of the end-to-end telecommunication network, and saves the time and cost of fault detection. The method of the present invention can be implemented in existing equipment. Therefore, network service operators can implement the present invention without purchasing new equipment. The invention can cooperate with the network management customer service system or the network management maintenance and operation system. Before the network management personnel decide to send personnel to the site for repair, the invention can perform automatic repair in advance and provide a repair priority list, which can greatly reduce the labor cost of checking and repairing the telecommunication network, the workload of maintenance personnel and Repair time for network failures.
100:自我修復系統100: Self-healing system
110:處理器110: Processor
120:儲存媒體120: storage media
121:障礙查測路由模組121: Obstacle detection routing module
122:查測路由資料庫122: Query routing database
123:查測資料清理模組123: Detect data cleaning module
124:深度學習推薦模組124:Deep Learning Recommendation Module
125:障礙自動修復模組125: Obstacle automatic repair module
126:歷史查測申告資料庫126:Historical investigation report database
127:深度學習訓練模組127:Deep learning training module
130:收發器130: Transceiver
20:網管客服系統20: Network management customer service system
30:網管維運系統30:Network management and maintenance system
50:終端裝置50: terminal device
60:電信網路60: Telecommunications network
61:光纖網路單元61: Optical network unit
62:光纖線路終端62: Fiber optic line terminal
63、64:多重服務邊緣路由器63, 64: Multi-service edge router
70:網際網路70:Internet
S301、S302、S303、S304、S305、S306、S307、S308、S309、S401、S402、S403:步驟S301, S302, S303, S304, S305, S306, S307, S308, S309, S401, S402, S403: steps
圖1根據本發明的一實施例繪示電信網路的示意圖。 圖2根據本發明的一實施例繪示一種電信網路的自我修復系統的示意圖。 圖3根據本發明的一實施例繪示由多個模組對電信網路執行自我修復程序的流程圖。 圖4根據本發明的一實施例繪示一種電信網路的自我修復方法的流程圖。 FIG. 1 shows a schematic diagram of a telecommunication network according to an embodiment of the present invention. FIG. 2 is a schematic diagram of a self-healing system for a telecommunication network according to an embodiment of the present invention. FIG. 3 is a flowchart illustrating a self-healing procedure performed by a plurality of modules on a telecommunication network according to an embodiment of the present invention. FIG. 4 is a flow chart of a self-repair method for a telecommunication network according to an embodiment of the present invention.
S401、S402、S403:步驟 S401, S402, S403: steps
Claims (9)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW110128703A TWI785718B (en) | 2021-08-04 | 2021-08-04 | Self-healing system and self-healing method for telecommunication network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW110128703A TWI785718B (en) | 2021-08-04 | 2021-08-04 | Self-healing system and self-healing method for telecommunication network |
Publications (2)
Publication Number | Publication Date |
---|---|
TWI785718B true TWI785718B (en) | 2022-12-01 |
TW202308353A TW202308353A (en) | 2023-02-16 |
Family
ID=85794727
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW110128703A TWI785718B (en) | 2021-08-04 | 2021-08-04 | Self-healing system and self-healing method for telecommunication network |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI785718B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103081407A (en) * | 2011-03-03 | 2013-05-01 | 株式会社日立制作所 | Failure analysis device, and system and method for same |
JP5518594B2 (en) * | 2010-06-30 | 2014-06-11 | 三菱電機株式会社 | Internal network management system, internal network management method and program |
-
2021
- 2021-08-04 TW TW110128703A patent/TWI785718B/en active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5518594B2 (en) * | 2010-06-30 | 2014-06-11 | 三菱電機株式会社 | Internal network management system, internal network management method and program |
CN103081407A (en) * | 2011-03-03 | 2013-05-01 | 株式会社日立制作所 | Failure analysis device, and system and method for same |
Also Published As
Publication number | Publication date |
---|---|
TW202308353A (en) | 2023-02-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11057266B2 (en) | Identifying troubleshooting options for resolving network failures | |
CN109787817B (en) | Network fault diagnosis method, device and computer readable storage medium | |
CN109617715A (en) | Network fault diagnosis method, system | |
US7409593B2 (en) | Automated diagnosis for computer networks | |
US20170155539A1 (en) | Systems and methods for correlating alarms in a network | |
US20220245462A1 (en) | Training a digital twin in artificial intelligence-defined networking | |
US20210266230A1 (en) | Classification and Relationship Correlation Learning Engine for the Automated Management of Complex and Distributed Networks | |
CN105703934B (en) | A kind of PON network method for diagnosing faults and device towards home broadband business | |
US20220247643A1 (en) | Network control in artificial intelligence-defined networking | |
US20240177175A1 (en) | Guided computing device repair systems, methods, and apparatus | |
US11316752B2 (en) | Action recommendation engine (ARE) of a closed-loop machine learning (ML) system for controlling a network | |
CN106130761A (en) | The recognition methods of the failed network device of data center and device | |
WO2013163432A1 (en) | Estimating a severity level of a network fault | |
EP2842264A1 (en) | Estimating physical locations of network faults | |
US11894969B2 (en) | Identifying root causes of network service degradation | |
WO2007147327A1 (en) | Method, system and apparatus of fault location for communicaion apparatus | |
CN109150619A (en) | A kind of fault diagnosis method and system based on network flow data | |
US20160359688A1 (en) | System and method for network management automation | |
CN112817785A (en) | Anomaly detection method and device for micro-service system | |
CA3210058A1 (en) | Systems and methods for artificial intelligence-defined networking | |
US20220345356A1 (en) | Determining a root-cause of a network access failure and conducting remediation | |
TWI785718B (en) | Self-healing system and self-healing method for telecommunication network | |
WO2017200651A1 (en) | Anomaly detection and prediction in a packet broker | |
CN111277427B (en) | Data center network equipment inspection method and system | |
US20230188440A1 (en) | Automatic classification of correlated anomalies from a network through interpretable clustering |