A network monitoring system and methodology that predicts saturation probability from port-based capacity utilization rates.

Abstract

It is a monitoring system for predicting the saturation risk of uplink ports and PON ports of OLT devices, and its features are: a server (1) that communicates with OLT devices in the network and automatically collects uplink port and PON port usage counter data of these devices at predetermined periods and transmits the raw usage data with a timestamp and port ID information; an intermediary layer (2) that receives the necessary inventory and configuration data from different source systems to enrich the data so that the raw counter data can be interpreted; and a software module (4) that performs data enrichment by matching the raw usage data with the inventory data received from the intermediary layer (2) via the port ID and calculates the port-based capacity usage rate by comparing the measured usage value with the port capacity information obtained from the inventory data.An AI algorithm (5) that models the usage trend for each uplink and PON port by continuously learning the calculated port-based capacity usage rates and historical usage data, calculates the probability of the port becoming saturated on a daily basis according to predefined threshold values, and classifies the ports according to the probability value it calculates, generating a degree of importance; an information service that automatically sends warnings about the ports classified as critical and risky according to the generated degree of importance to the network teams and managers determined according to the responsibility area of ​​the relevant port (6); a tracking and reporting screen that lists the port-based interpreted usage rate and saturation risk data according to the responsibility area and shows the ports according to their risk status (7); raw usage data, enriched inventory data,It includes a database (3) in which the calculated port-based capacity utilization rates and the generated saturation probability and risk class values ​​are stored.

Description

1 TARIFF Network monitoring that predicts saturation probability from port-based capacity utilization rates. system and method Technical Area The invention uses artificial intelligence to continuously monitor and analyze the uplinks of OLT devices. With a system and method that provides real-time information and guidance on network saturation status. It is related. 10 State of the Art In today's world, internet speeds are constantly increasing, and customers are also getting higher prices. They expect speeds to be seamless. High speeds on a fixed internet network are 15 OLT internet service provider devices installed for supporting fiber internet infrastructure Their importance is steadily increasing. These systems ensure that all customers receive the speeds they purchase without any shortcomings. Continuous monitoring and analysis are of utmost importance in order to ensure its effectiveness. With the increasing internet subscriber speeds, subscriber speed complaints are also increasing. OLT 20 Speed ​​complaints are received due to uplink saturation issues; subsequently, a manual OLT (Optical Level Transmission) is implemented. OLT Uplink ports are controlled via NMS systems that manage the devices to determine saturation. Whether or not this is the case is checked, and the saturation status is communicated to the relevant units. Additionally, Monitoring is done daily through real-time data collected in a single moment via reporting. This is provided. This situation does not provide a quick solution to complaints. Uplink 25 Because saturation levels could not be proactively addressed quickly, complaints and problems arose. As power increases and high speed purchases become more expensive, customer satisfaction decreases. This situation... This leads to customer loss. Customers switch operators. is going. The application with the number CN111132208A was revealed as a result of technical investigations. In summary; “The implementation of the current application requires accurate forecasting of network capacity and a capacity forecast used to improve the accuracy of capacity planning It describes the method. The method for implementing the current application includes the following: The physical resource module is associated with PRB data and the operational support system OSS with user 35. Obtaining historical data from the service experience quality system SEQ; 2 PRB was determined by processing historical data using multivariate linear regression. Obtaining the predictive value. As can be seen, the invention is related to the capacity forecasting method, and in addition to that, as mentioned above... It does not mention a structure that could provide a solution to the aforementioned disadvantages. 5 In conclusion, due to the negative aspects described above and the current solutions, the subject matter... Due to its shortcomings, it has become necessary to make improvements in the relevant technical field. Purpose of the Invention 10 The invention represents a new breakthrough in this field, unlike the structures used in existing technology. The aim is to create a structure with different technical specifications that bring these elements together. The primary purpose of the invention is to continuously monitor the uplinks of OLT devices with the support of artificial intelligence. It analyzes and provides real-time information and guidance on network saturation status. The goal is to establish a system and method. The purpose of the invention is to reduce customer complaints, and in cases where customer complaints exist, to address them through the call center and... The goal is to speed up the work processes of operational teams. 20 Thanks to this invention, not only the uplinks of Fiber Internet service provider OLT devices, but also PON uplinks on service cards are also continuously monitored and uplinks are determined using artificial intelligence. Capacity utilization interpretation will be classified based on the reading of the received data. Critical All ports that are currently at a critical level or could soon become critical are assigned to Network teams for 25 days. The information will be interpreted and communicated, allowing for follow-up and proactive action. This will... This will help reduce subscriber complaints about speed and page loading issues. As a result... This will also prevent subscriber churn. To fulfill the purposes described above, the invention provides 30 uplink ports for OLT devices. It is a monitoring system for predicting the risk of saturation of PON ports, feature;  Communicating with OLT devices on the network and accessing their uplink ports and PON ports. Port usage counter data is automatically generated at predetermined intervals. 3 collects and compiles raw usage data with timestamps and port ID information. server transmitting together,  Inventory and configuration necessary to make sense of raw meter data. an interface that retrieves data from different source systems and presents it for data enrichment. layer, 5  Raw usage data is obtained from the middleware via inventory data and port ID. by performing data enrichment through matching and deriving it from inventory data Port-based capacity is calculated by comparing the usage value measured with port capacity information. software module that calculates usage rate,  Calculated port-based capacity utilization rates and historical usage data 10 by continuously learning the usage trends for each uplink and PON port. The system models the port's daily saturation based on predefined threshold values. It calculates the probability of occurrence and, based on the calculated probability value, selects the ports. an artificial intelligence algorithm that generates importance levels by classifying,  15 ports classified as critical and risky according to their level of importance. The alerts are sent to network teams assigned according to the responsibility area of ​​the relevant port, and a notification service that automatically sends notifications to managers,  Port-based interpreted usage rate and saturation risk data for responsibility Tracking and reporting that lists ports by area and displays them according to their risk status. screen, 20  Raw usage data, enriched inventory data, calculated port-based capacity utilization rates and the generated saturation probability and risk class values the database where it is stored It includes. The structural and characteristic features and all the advantages of the invention are given in the figures below. Thanks to the detailed explanation written with references to the figures, it becomes clearer. This will be understood, and therefore the evaluation should also take these figures and detailed explanations into account. It must be done by taking it. Figures that will help understand the invention. Figure 1 shows a general representation of the system that is the subject of the invention. Figure 2 is a schematic representation of the method described in the invention. 35 4 The drawings do not necessarily need to be scaled and are necessary for understanding the invention. Details that are not present may have been overlooked. Furthermore, at least to a large extent... Elements that are identical or at least have substantially identical functions are numbered the same. It is shown. Explanation of Part References 1. Server 2. Middle Layer 3. Database 10 4. Software module 5. Artificial intelligence algorithm 6. Information service 7. Tracking and reporting screen 1001. Server (1) of uplink port and PON port usage counter data of OLT devices automatic collection at predetermined intervals by means of raw meter In order to make sense of the data, the necessary inventory and configuration data are needed. is taken from layer (2), 1002. Raw usage data collected is matched with inventory data via port ID. 20 enriched and measured with port capacity information obtained from inventory data The usage value is scaled to determine the port-based capacity utilization rate in the software module. (4) calculation, 1003. calculated port-based capacity usage rates and stored in the database (3) historical usage data is continuously processed by the artificial intelligence algorithm (5) 25 By learning and modeling the usage trends for each port, a predefined threshold is used. Calculating the probability of the port becoming saturated on a daily basis based on its values ​​and this Ports are classified as critical, risky, and problem-free according to probability, and their importance is determined accordingly. production, 1004. In the classified port data tracking and reporting screen, (7) responsibility area 30 They are listed according to their risk level and color-coded as critical and risky. Warnings regarding ports classified as such are given importance by the information service (6) Depending on the level, it is automatically forwarded to the relevant network teams and managers for action. ensuring that it is obtained, 1005. The raw usage data collected, the enriched inventory data, the calculated usage rates and the resulting saturation probability and risk class values (3) storage and reporting in the database. Detailed Description of the Invention 5 In this detailed explanation, the preferred configurations of the invention are not merely for better understanding the subject. in order to facilitate understanding and without imposing any limiting effects It is explained. The invention uses artificial intelligence to continuously monitor and analyze the uplinks of OLT devices. With a system and method that provides real-time information and guidance on network saturation status. It is related. The elements and functions used in the system and method that are the subject of the invention are as follows: 15 Server (1), OLT (Optical Line Terminal) located in the network by communicating with the devices and their uplink ports and PON (Passive Optical Network - Passive Optical Network (PIP) port usage counter data is collected at predetermined intervals. preferably collecting automatic usage data at five-minute intervals; the raw usage data it collects is 20 data transferred to the software module (4) for processing and to the database (3) for storage It is the collection unit. The server (1) collects numerous OLT devices via device management interfaces. It will retrieve data simultaneously and compile the collected data along with timestamp and port ID information. It is structured to transmit. The middle layer (2) enables the raw counter data collected by the server (1) to be interpreted. inventory and configuration data required for (port capacity / speed, device and port) (such as identity, device location and region, relevant area of ​​responsibility and team information) It is an integration unit that enables the acquisition of data from source systems. (Intermediate layer) (2), transforming data from different source systems into a common and standard data structure. It provides the software module (4) for enrichment; so that the system from source systems They are enabled to work independently. The database (3) stores the raw usage data collected by the server (1), middle layer (2) The enriched inventory data obtained from the software module (4) is calculated as 35 port-based capacity utilization rates are generated by the artificial intelligence algorithm (5). 6 saturation probability and risk class values ​​and submitted information records It is the storage unit in which the history of the artificial intelligence algorithm (5) is stored. The database (3) is both the storage unit in which the history of the artificial intelligence algorithm (5) is stored. It creates a data source for learning from data and also a tracking and reporting screen (7) It enables retrospective reporting. Software module (4) receives raw port usage data from server (1) from intermediate layer (2) It performs data enrichment by matching inventory data with port ID, and By comparing the measured usage value with the port capacity information obtained from inventory data. It is the analysis unit that calculates the port-based capacity utilization rate. Software module (4), It records the usage rates it calculates both in the database (3) and for learning and prediction 10 It transmits the data as input to the artificial intelligence algorithm (5) for the process. The artificial intelligence algorithm (5) receives port-based capacity usage from the software module (4). by constantly learning the rates and historical usage data stored in the database (3) Modeling usage trends for each uplink and PON port; predefined threshold 15 It is a forecasting unit that calculates the probability of a port becoming saturated on a daily basis, based on its values. The artificial intelligence algorithm (5) identifies the ports as critical, risky and according to the probability value it calculates. It produces a degree of importance by classifying them as problem-free and sends this result to the information service (6) and transmits to the tracking and reporting screen (7). Information service (6) according to the importance level produced by the artificial intelligence algorithm (5) Warnings regarding ports classified as critical and risky are sent to the area of ​​responsibility of the respective port. Automatically, preferably via email, to designated network teams and managers. It is the notification unit that transmits the information. Thanks to the information service (6), before saturation occurs The relevant teams are informed and preventive action is taken. 25 Monitoring and reporting screen (7), port-based interpreted usage rate and saturation A user interface where risk data is listed according to the network teams' areas of responsibility. It is a unit. On the monitoring and reporting screen, (7) ports are color-coded according to their risk status, Those in critical condition are marked red, those in risky condition are marked yellow, and those without problems are marked green. 30 It is shown; also, reports based on historical data stored in the database (3) are generated. and the actions taken are monitored. The steps involved in the process carried out with the system that is the subject of the invention are listed below:  Uplink port and PON port usage counter data of OLT devices are stored on the server (1) 35 automatic collection at predetermined intervals by means of raw meter 7 In order to make sense of the data, the necessary inventory and configuration data are needed. (1001), taken from layer (2),  Matching the collected raw usage data with inventory data via port ID enriched and measured with port capacity information obtained from inventory data The usage value is scaled to determine the port-based capacity utilization rate in the software module: 5 (4) calculation (1002),  calculated port-based capacity usage rates and history stored in the database (3) By continuously learning the usage data, each artificial intelligence algorithm (5) Modeling the usage trend for the port, based on predefined threshold values. Calculating the daily probability of a port becoming saturated and adjusting ports accordingly (10) generating importance levels by classifying (1003),  on the classified port data tracking and reporting screen (7) according to the area of ​​responsibility They are listed and color-coded according to their risk levels, and categorized as critical and risky. Warnings regarding classified ports are given importance by the information service (6) Depending on the level, it is automatically forwarded to the relevant network teams and managers for action 15. ensuring that it is taken (1004),  collected raw usage data, enriched inventory data, calculated usage rates and the resulting saturation probability and risk class values (3) storage and reporting in the database (1005)

Claims

8 REQUESTS 1. Predicting the risk of saturation in uplink ports and PON ports of OLT devices. It is a monitoring system, the feature of which is;  Communicating with OLT devices on the network and accessing their uplink ports and PON 5 Port usage counter data is automatically generated at predetermined intervals. collects and compiles raw usage data with timestamps and port ID information. server transmitting together (1),  Inventory and configuration necessary to make sense of raw meter data. presenting data by gathering data from different source systems for data enrichment. layer (2),  Raw usage data with inventory data and port ID received from the middle layer (2) enriching data by matching it with inventory data. By comparing the measured usage value with the port capacity information it obtains, it calculates the port-based usage. Software module that calculates capacity utilization rate (4), 15  Calculated port-based capacity utilization rates and historical usage data by continuously learning the usage trends for each uplink and PON port. The system models the port's daily saturation based on predefined threshold values. It calculates the probability of occurrence and, based on the calculated probability value, selects the ports. an artificial intelligence algorithm that produces importance levels by classifying (5), 20  Regarding ports classified as critical and risky according to their level of importance The alerts are sent to network teams assigned according to the responsibility area of ​​the relevant port, and Information service that automatically transmits to managers (6),  Port-based interpreted usage rate and saturation risk data for responsibility Tracking and reporting that lists ports by area and displays them according to their risk status. 25 screen (7),  Raw usage data, enriched inventory data, calculated port-based capacity utilization rates and the generated saturation probability and risk class values database where it is stored (3) It includes. 30 2. The system complies with Request 1 and its feature is that it provides usage counter data at five-minute intervals. It includes a server (1) configured to collect data.

3. The system compliant with Claim 1 is characterized by its ability to manage numerous OLT 35 devices via device management interfaces. It includes a server (1) configured to pull data from the device simultaneously. 9 4. It is a system that complies with Claim 1, and its feature is that it processes the raw usage data it collects. to transfer to the software module (4) and to the database (3) for storage It includes a configured server (1).

5. The system is compliant with claim 1, and its feature is the inventory received by the middle layer (2) and Configuration data includes port capacity and speed, device and port ID, and device location. It should include information about the area of ​​responsibility and team related to the location and region.

6. The system complies with Claim 1, and its feature is that it combines data from different source systems into a common and standardized system. 10 by converting it into a data structure, the system can operate independently of the source systems. It includes an intermediate layer (2) structured to provide.

7. The system complies with Claim 1 and its feature is that it will send alerts via email. It includes a structured information service (6). 15 8. The system complies with Claim 1, and its feature is that the ports are color-coded according to their risk status. It includes the tracking and reporting screen (7).

9. The system complies with claim 1 or 8, and its characteristic is that critical ports are marked red, and risky ports are marked red. The monitoring system shows ports in a problematic state in yellow and ports without problems in green, and 20 It includes reporting screen (7).

10. The system complies with Claim 1, and its characteristics include ports that are critical, risky, and problem-free. It includes an artificial intelligence algorithm (5) that produces a degree of importance by classifying.

11. Predicting the risk of saturation in uplink ports and PON ports of OLT devices. It is a monitoring method aimed at;  Uplink port and PON port usage counter data of OLT devices are stored on the server (1) automatic collection at predetermined intervals by means of raw meter In order to make sense of the data, the necessary inventory and structuring data are needed. (1001), taken from layer (2),  Matching the collected raw usage data with inventory data via port ID enriched and measured with port capacity information obtained from inventory data The software calculates the port-based capacity utilization rate by proportionally calculating the usage value. Calculation of module (4) (1002), 35  calculated port-based capacity usage rates and stored in the database (3) historical usage data is continuously processed by the artificial intelligence algorithm (5) By learning and modeling the usage trends for each port, predefined Calculating the probability of the port becoming saturated on a daily basis based on threshold values ​​and Based on this probability, ports are classified as critical, risky, and problem-free, with importance level 5. degree of production (1003),  in the classified port data tracking and reporting screen (7) area of ​​responsibility They are listed according to their risk level and color-coded as critical and risky. Warnings regarding ports classified as such are given importance by the information service (6) Based on their level, they are automatically forwarded to the relevant network teams and managers. 10 ensuring that action is taken (1004),  collected raw usage data, enriched inventory data, calculated usage rates and the resulting saturation probability and risk class values (3) storage and reporting in the database (1005) It includes the steps of the process. 15 12. This method complies with Claim 11 and its characteristic is that it includes a usage counter in process step 1001. This involves collecting the data at five-minute intervals.

13. This method complies with Claim 14 and its characteristic is that it is in a critical situation in process step 1004. ports are marked in red, ports in a risky state are marked in yellow, and ports without problems are marked in green. This includes the steps of displaying the information and sending alerts via email.

Images