Patents by Inventor Tsong-Ho Wu
Tsong-Ho Wu has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 9954785Abstract: The content-aware application switch and methods thereof intelligently switch client packets to one server among a group of servers in a server farm. The switch uses Layer 7 or application content parsed from a packet to help select the server and to schedule the transmitting of the packet to the server. This enables refined load-balancing and Quality of-Service control tailored to the application being switched. In an exemplary embodiment of the invention, a method includes maintaining a server load metric for each server in a group of servers; parsing application content from a packet; selecting a destination server from the group of servers, wherein selecting the destination server is dependent on the server load metric for each server, assigning a priority to the packet, the priority being dependent on the application content; and dropping the packet if the priority comprises at least one of a predetermined type.Type: GrantFiled: May 31, 2016Date of Patent: April 24, 2018Assignee: Open Invention Network LLCInventors: Leonard L. Lu, Deh-Phone K. Hsing, Bo-Chao Cheng, Tsong-Ho Wu
-
Patent number: 9898321Abstract: Concepts and technologies disclosed herein are directed to data-driven feedback control systems for an acceptable level of real-time application transaction completion rate in virtualized networks, while maximizing virtualized server utilization. According to one aspect disclosed herein, a network virtualization platform (“NVP”) includes a plurality of hardware resources, a virtual machine (“VM”), and a virtual machine monitor (“VMM”). The VMM can track an execution state of each of a plurality of applications associated with the VM. The VMM can measure a real-time application transaction completion rate of the VM. The VMM can determine whether a trigger condition exists for priority scheduling of real-time applications based upon the real-time application transaction completion rate and a pre-set threshold value.Type: GrantFiled: July 23, 2015Date of Patent: February 20, 2018Assignee: AT&T Intellectual Property I, L.P.Inventors: Tsong-Ho Wu, Wen-Jui Li
-
Publication number: 20170295082Abstract: Concepts and technologies disclosed herein are directed to an auto-scaling software-defined monitoring (“SDM”) platform for software-defined networking (“SDN”) service assurance. According to one aspect of the concepts and technologies disclosed herein, an SDM controller can monitor event data associated with a network even that occurred within a virtualized IP SDN network that is monitored by a virtualized SDM resources platform. The SDM controller can measure, based upon the event data, a quality of service (“QoS”) performance metric associated with the virtualized SDM resource platform. The SDN controller can determine, based upon the QoS performance metric, whether an auto-scaling operation is to be performed. The auto-scaling operation can include reconfiguring the virtualized SDM resources platform by adding virtual machine capacity for supporting event management tasks either by instantiating a new virtual machine or by migrating an existing virtual machine to a new hardware host.Type: ApplicationFiled: April 7, 2016Publication date: October 12, 2017Applicant: AT&T Intellectual Property I, L.P.Inventors: Tsong-Ho Wu, Wen-Jui Li, Hasan Erkan
-
Publication number: 20170244614Abstract: Concepts and technologies disclosed herein are directed to context-aware virtualized control decision support system (“DSS”) for providing quality of experience (“QoE”) assurance for Internet protocol (“IP”) streaming video services. A QoE assurance DSS can monitor QoE event and context data to be utilized for QoE assurance analytics, measure QoE performance, perform QoE assurance analytics, and determine whether the QoE assurance analytics indicate that the QoE has been degraded, and if so, construct a fault correlation information model to be utilized for root cause analysis to determine a root cause of the QoE being degraded. The QoE assurance DSS also can determine, based upon the fault correlation information model, whether the root cause of the QoE being degraded is due to a capacity reduction, and if so, the QoE assurance DSS can identify a new network resource for capacity reallocation to accommodate a virtual machine migration.Type: ApplicationFiled: February 19, 2016Publication date: August 24, 2017Applicant: AT&T Intellectual Property I, L.P.Inventors: Tsong-Ho Wu, Wen-Jui Li
-
Publication number: 20170063599Abstract: A service impact event analyzer is used to evaluate service assurance risk in cloud SDN networks. Using data fusion, an alarm subset dataset is generated from a raw trap dataset. Service impact events are identified in the subset dataset. The service impact events are categorized into service impacted event categories, and a model is created for associating the event categories with process function classes. Time durations of the service impact events are computed using correlated secondary alarms from the alarm subset dataset. The service assurance risk is evaluated using the model and the time duration.Type: ApplicationFiled: September 1, 2015Publication date: March 2, 2017Inventors: Tsong-Ho Wu, Wen-Jui Li, Shyhyann Lee, Li-Chuan Sun
-
Publication number: 20170048110Abstract: Concepts and technologies are disclosed herein for a realtime dynamic virtual network topology discovery engine to discover a dynamic network topology in virtualized networks in realtime. A processor that executes a network topology discovery engine can obtain network data that can describe elements of a data center and operational state of the elements. Obtaining network data can include obtaining network data from a network topology inventory database and through detecting operational state change events from virtual network components. The processor can construct a network topology model based upon the network data. The network topology model can include an object (representing an element of the data center) and an attribute representing a state of the element. The processor can update the network topology model in realtime. The network topology model and configurations can be stored for root cause analysis of fault events, resource orchestration in SDN networks, and other applications.Type: ApplicationFiled: August 11, 2015Publication date: February 16, 2017Applicant: AT&T Intellectual Property I, L.P.Inventors: Tsong-Ho Wu, Wen-Jui Li, Shyhyann Lee
-
Publication number: 20170024234Abstract: Concepts and technologies disclosed herein are directed to data-driven feedback control system for an acceptable level of real-time application transaction completion rate in virtualized networks, while maximizing virtualized server utilization. According to one aspect disclosed herein, a network virtualization platform (“NVP”) includes a plurality of hardware resources, a virtual machine (“VM”), and a virtual machine monitor (“VMM”). The VMM can track an execution state of each of a plurality of applications associated with the VM. The VMM can measure a real-time application transaction completion rate of the VM. The VMM can determine whether a trigger condition exists for priority scheduling of real-time applications based upon the real-time application transaction completion rate and a pre-set threshold value.Type: ApplicationFiled: July 23, 2015Publication date: January 26, 2017Applicant: AT&T Intellectual Property I, L.P.Inventors: Tsong-Ho Wu, Wen-Jui Li
-
Patent number: 9356877Abstract: The content-aware application switch and methods thereof intelligently switch client packets to one server among a group of servers in a server farm. The switch uses Layer 7 or application content parsed from a packet to help select the server and to schedule the transmitting of the packet to the server. This enables refined load-balancing and Quality of-Service control tailored to the application being switched. In an exemplary embodiment of the invention, a method includes maintaining a server load metric for each server in a group of servers; parsing application content from a packet; selecting a destination server from the group of servers, wherein selecting the destination server is dependent on the server load metric for each server, assigning a priority to the packet, the priority being dependent on the application content; and dropping the packet if the priority comprises at least one of a predetermined type.Type: GrantFiled: April 3, 2015Date of Patent: May 31, 2016Assignee: Open Invention Network, LLCInventors: Leonard L. Lu, Deh-Phone K. Hsing, Bo-Chao Cheng, Tsong-Ho Wu
-
Patent number: 9032090Abstract: The content-aware application switch and methods thereof intelligently switch client packets to one server among a group of servers in a server farm. The switch uses Layer 7 or application content parsed from a packet to help select the server and to schedule the transmitting of the packet to the server. This enables refined load-balancing and Quality of-Service control tailored to the application being switched. In an exemplary embodiment of the invention, a method includes maintaining a server load metric for each server in a group of servers; parsing application content from a packet; selecting a destination server from the group of servers, wherein selecting the destination server is dependent on the server load metric for each server, assigning a priority to the packet, the priority being dependent on the application content; and dropping the packet if the priority comprises at least one of a predetermined type.Type: GrantFiled: February 11, 2014Date of Patent: May 12, 2015Assignee: Open Invention Network, LLCInventors: Leonard L. Lu, Deh-Phone K. Hsing, Bo-Chao Cheng, Tsong-Ho Wu
-
Patent number: 8656047Abstract: The content-aware application switch and methods thereof intelligently switch client packets to one server among a group of servers in a server farm. The switch uses Layer 7 or application content parsed from a packet to help select the server and to schedule the transmitting of the packet to the server. This enables refined load-balancing and Quality of-Service control tailored to the application being switched. In an exemplary embodiment of the invention, a method includes maintaining a server load metric for each server in a group of servers; parsing application content from a packet; selecting a destination server from the group of servers, wherein selecting the destination server is dependent on the server load metric for each server, assigning a priority to the packet, the priority being dependent on the application content; and dropping the packet if the priority comprises at least one of a predetermined type.Type: GrantFiled: January 23, 2012Date of Patent: February 18, 2014Assignee: Open Invention Network, LLCInventors: Leonard L. Lu, Deh-Phone K. Hsing, Bo-Chao Cheng, Tsong-Ho Wu
-
Patent number: 8122146Abstract: The content-aware application switch and methods thereof intelligently switch client packets to one server among a group of servers in a server farm. The switch uses Layer 7 or application content parsed from a packet to help select the server and to schedule the transmitting of the packet to the server. This enables refined load-balancing and Quality of-Service control tailored to the application being switched. In an exemplary embodiment of the invention, a method includes maintaining a server load metric for each server in a group of servers; parsing application content from a packet; selecting a destination server from the group of servers, wherein selecting the destination server is dependent on the server load metric for each server, assigning a priority to the packet, the priority being dependent on the application content; and dropping the packet if the priority comprises at least one of a predetermined type.Type: GrantFiled: April 14, 2010Date of Patent: February 21, 2012Assignee: Open Invention Network, LLCInventors: Leonard L Lu, Deh-Phone K Hsing, Bo-Chao Cheng, Tsong-Ho Wu
-
Patent number: 7937490Abstract: The content-aware application switch and methods thereof intelligently switch client packets to one server among a group of servers in a server farm. The switch uses Layer 7 or application content parsed from a packet to help select the server and to schedule the transmitting of the packet to the server. This enables refined load-balancing and Quality of-Service control tailored to the application being switched. In another aspect of the invention, a slow-start server selection method assigned an initially boosted server load metric to a server newly added to the group of servers under load balancing. This alleviates the problem of the new server being swamped initially due to a very low load metric compared to that of others. In yet another aspect of the invention, a switching method dependent on Layer 7 content avoids delayed binding in a new TCP session. Layer 7 content is not available during the initial handshaking phase of a new TCP session.Type: GrantFiled: September 22, 2008Date of Patent: May 3, 2011Inventors: Leonard L. Lu, Deh-Phone K. Hsing, Bo-Chao Cheng, Tsong-Ho Wu
-
Publication number: 20090070489Abstract: The content-aware application switch and methods thereof intelligently switch client packets to one server among a group of servers in a server farm. The switch uses Layer 7 or application content parsed from a packet to help select the server and to schedule the transmitting of the packet to the server. This enables refined load-balancing and Quality of-Service control tailored to the application being switched. In another aspect of the invention, a slow-start server selection method assigned an initially boosted server load metric to a server newly added to the group of servers under load balancing. This alleviates the problem of the new server being swamped initially due to a very low load metric compared to that of others. In yet another aspect of the invention, a switching method dependent on Layer 7 content avoids delayed binding in a new TCP session. Layer 7 content is not available during the initial handshaking phase of a new TCP session.Type: ApplicationFiled: September 22, 2008Publication date: March 12, 2009Applicant: Open Invention Network, LLCInventors: Leonard L. Lu, Deh-Phone K. Hsing, Bo-Chao Cheng, Tsong-Ho Wu
-
Patent number: 7437473Abstract: A content-aware application switch and methods thereof intelligently switch client packets to one server among a group of servers in a server farm. The switch uses Layer 7 or application content parsed from a packet to help select the server and to schedule the transmitting of the packet to the server. This enables refined load-balancing and Quality-of-Service control tailored to the application being switched. In another aspect of the invention, a slow-start server selection method assigned an initially boosted server load metric to a server newly added to the group of servers under load balancing. This alleviates the problem of the new server being swamped initially due to a very low load metric compared to that of others. In yet another aspect of the invention, a switching method dependent on Layer 7 content avoids delayed binding in a new TCP session. Layer 7 content is not available during the initial handshaking phase of a new TCP session.Type: GrantFiled: September 2, 2005Date of Patent: October 14, 2008Assignee: SoftShield, LLCInventors: Leonard L. Lu, Deh-Phone K. Hsing, Bo-Chao Cheng, Tsong-Ho Wu
-
Patent number: 7117269Abstract: A content-aware application switch and methods thereof intelligently switch client packets to one server among a group of servers in a server farm. The switch uses Layer 7 or application content parsed from a packet to help select the server and to schedule the transmitting of the packet to the server. This enables refined load-balancing and Quality-of-Service control tailored to the application being switched. In another aspect of the invention, a slow-start server selection method assigned an initially boosted server load metric to a server newly added to the group of servers under load balancing. This alleviates the problem of the new server being swamped initially due to a very low load metric compared to that of others. In yet another aspect of the invention, a switching method dependent on Layer 7 content avoids delayed binding in a new TCP session. Layer 7 content is not available during the initial handshaking phase of a new TCP session.Type: GrantFiled: April 30, 2002Date of Patent: October 3, 2006Assignee: Transtech Networks USA, Inc.Inventors: Leonard L. Lu, Deh-Phone K. Hsing, Bo-Chao Cheng, Tsong-Ho Wu
-
Publication number: 20060031374Abstract: A content-aware application switch and methods thereof intelligently switch client packets to one server among a group of servers in a server farm. The switch uses Layer 7 or application content parsed from a packet to help select the server and to schedule the transmitting of the packet to the server. This enables refined load-balancing and Quality-of-Service control tailored to the application being switched. In another aspect of the invention, a slow-start server selection method assigned an initially boosted server load metric to a server newly added to the group of servers under load balancing. This alleviates the problem of the new server being swamped initially due to a very low load metric compared to that of others. In yet another aspect of the invention, a switching method dependent on Layer 7 content avoids delayed binding in a new TCP session. Layer 7 content is not available during the initial handshaking phase of a new TCP session.Type: ApplicationFiled: September 2, 2005Publication date: February 9, 2006Applicant: Transtech Networks USA, Inc.Inventors: Leonard Lu, Deh-Phone Hsing, Bo-Chao Cheng, Tsong-Ho Wu
-
Patent number: 6944678Abstract: A content-aware application switch and methods thereof intelligently switch client packets to one server among a group of servers in a server farm. The switch uses Layer 7 or application content parsed from a packet to help select the server and to schedule the transmitting of the packet to the server. This enables refined load-balancing and Quality-of-Service control tailored to the application being switched. In another aspect of the invention, a slow-start server selection method assigned an initially boosted server load metric to a server newly added to the group of servers under load balancing. This alleviates the problem of the new server being swamped initially due to a very low load metric compared to that of others. In yet another aspect of the invention, a switching method dependent on Layer 7 content avoids delayed binding in a new TCP session. Layer 7 content is not available during the initial handshaking phase of a new TCP session.Type: GrantFiled: June 18, 2001Date of Patent: September 13, 2005Assignee: Transtech Networks USA, Inc.Inventors: Leonard L. Lu, Deh-phone K. Hsing, Bo-Chao Cheng, Tsong-Ho Wu
-
Patent number: 6772211Abstract: A content-aware application switch and methods thereof intelligently switch client packets to one server among a group of servers in a server farm. The switch uses Layer 7 or application content parsed from a packet to help select the server and to schedule the transmitting of the packet to the server. This enables refined load-balancing and Quality-of-Service control tailored to the application being switched. In another aspect of the invention, a slow-start server selection method assigned an initially boosted server load metric to a server newly added to the group of servers under load balancing. This alleviates the problem of the new server being swamped initially due to a very low load metric compared to that of others. In yet another aspect of the invention, a switching method dependent on Layer 7 content avoids delayed binding in a new TCP session. Layer 7 content is not available during the initial handshaking phase of a new TCP session.Type: GrantFiled: April 30, 2002Date of Patent: August 3, 2004Assignee: Transtech Networks USA, Inc.Inventors: Leonard L. Lu, Deh-Phone K. Hsing, Bo-Chao Cheng, Tsong-Ho Wu
-
Publication number: 20020194345Abstract: A content-aware application switch and methods thereof intelligently switch client packets to one server among a group of servers in a server farm. The switch uses Layer 7 or application content parsed from a packet to help select the server and to schedule the transmitting of the packet to the server. This enables refined load-balancing and Quality-of-Service control tailored to the application being switched. In another aspect of the invention, a slow-start server selection method assigned an initially boosted server load metric to a server newly added to the group of servers under load balancing. This alleviates the problem of the new server being swamped initially due to a very low load metric compared to that of others. In yet another aspect of the invention, a switching method dependent on Layer 7 content avoids delayed binding in a new TCP session. Layer 7 content is not available during the initial handshaking phase of a new TCP session.Type: ApplicationFiled: April 30, 2002Publication date: December 19, 2002Inventors: Leonard L. Lu, Deh-Phone K. Hsing, Bo-Chao Cheng, Tsong-Ho Wu
-
Publication number: 20020194342Abstract: A content-aware application switch and methods thereof intelligently switch client packets to one server among a group of servers in a server farm. The switch uses Layer 7 or application content parsed from a packet to help select the server and to schedule the transmitting of the packet to the server. This enables refined load-balancing and Quality-of-Service control tailored to the application being switched. In another aspect of the invention, a slow-start server selection method assigned an initially boosted server load metric to a server newly added to the group of servers under load balancing. This alleviates the problem of the new server being swamped initially due to a very low load metric compared to that of others. In yet another aspect of the invention, a switching method dependent on Layer 7 content avoids delayed binding in a new TCP session. Layer 7 content is not available during the initial handshaking phase of a new TCP session.Type: ApplicationFiled: June 18, 2001Publication date: December 19, 2002Applicant: TRANSTECH NETWORKS USA, INC.Inventors: Leonard L. Lu, Deh-phone K. Hsing, Bo-Chao Cheng, Tsong-Ho Wu