-
公开(公告)号:US12113711B2
公开(公告)日:2024-10-08
申请号:US17669513
申请日:2022-02-11
IPC分类号: H04L47/193 , H04L45/24 , H04L45/302 , H04L47/62 , H04L69/22
CPC分类号: H04L47/193 , H04L45/24 , H04L45/306 , H04L47/62 , H04L69/22
摘要: Various example embodiments for supporting application-based traffic control in a multipath network are presented herein. Various example embodiments for supporting application-based traffic control in a multipath network may be configured to support application-based traffic steering, application-based traffic blocking, or the like, as well as various combinations thereof. Various example embodiments for supporting application-based traffic control in a multipath network may be configured to support application-based traffic control in various types of multipath networks, such as multipath networks combining wireline and wireless access technologies between an end-user customer premises and a network gateway (e.g., between a hybrid-access customer premises equipment (HCPE) and a hybrid-access gateway (HAG), in a hybrid-access communication network (e.g., based on a Broadband Forum TR-348 specification), that are in communication based on a multipath communication capability), multipath networks combining multiple wireless access technologies (e.g., cellular, WiFi, or the like) between an end user mobile device and a network gateway, or the like.
-
2.
公开(公告)号:US20240275725A1
公开(公告)日:2024-08-15
申请号:US18569167
申请日:2021-07-01
发明人: Toshihito FUJIWARA , Satoshi NARIKAWA , Hiroya ONO
IPC分类号: H04L47/122 , H04L47/193
CPC分类号: H04L47/122 , H04L47/193
摘要: An object of the present disclosure is to provide a communication path switching method for improving a throughput of TCP communication at the time of switching a communication path between a first communication path that is at least one of a low latency or high speed and a second communication path that is at least one of a high latency or low speed.
The communication path switching method according to the present disclosure is a communication path switching method for switching a communication path to a first communication path or a second communication path by using operation of a TCP accelerator in a communication path switching system including a terminal that performs TCP communication by switching a communication path between the first communication path that is at least one of a low latency or high speed and the second communication path that is at least one of a high latency or low speed, the communication path switching method including: receiving data from the terminal; and when the data is first received after the communication path is switched from the first communication path to the second communication path, transmitting again to the terminal, an acknowledgement signal transmitted last before the communication path is switched.-
3.
公开(公告)号:US20240121197A1
公开(公告)日:2024-04-11
申请号:US18276788
申请日:2021-03-26
申请人: NEC Corporation
发明人: Yoshihiko Hoshino
IPC分类号: H04L47/193
CPC分类号: H04L47/193
摘要: When a control signal transmitted from a session management functional unit receiving a connection instruction (for example, Attach or the like) of a terminal is received, a policy management functional unit of a network apparatus notifies a LAN located between a core network and the Internet of a policy for the terminal. Specifically, the policy management functional unit notifies the LAN of the policy via a TCP-based interface or an SCTP-based interface. The policy management functional unit receives the control signal via the TCP-based interface or the SCTP-based interface.
-
公开(公告)号:US11943147B2
公开(公告)日:2024-03-26
申请号:US17207954
申请日:2021-03-22
IPC分类号: H04L12/841 , H04L47/193 , H04L47/283 , H04L61/00 , H04L61/2514 , H04L69/163 , H04W80/04
CPC分类号: H04L47/283 , H04L47/193 , H04L61/00 , H04L61/2514 , H04L69/163 , H04W80/04
摘要: A method of determining a passive Round Trip Time, RTT, delay in a telecommunications system for exchanging data packets in accordance with a data transmission protocol between a first device and a second device. The first and second devices are identified by first and second device identifications, respectively. The data packets include an address part including a source address and a destination address. The method is performed in a node by modifying the address part of a received data packet from the first device, and creating a first timestamp before transmitting the modified data packet to the second device. Upon receiving, at the node, from the second device in response to the modified data packet, a data packet having the modified address part of the modified data packet, the node creates a second timestamp that provides for passively measuring the RTT delay.
-
公开(公告)号:US20240054559A1
公开(公告)日:2024-02-15
申请号:US17818773
申请日:2022-08-10
申请人: BGC PARTNERS, L.P.
发明人: Jonathan Joshua , Bijoy Paul
IPC分类号: G06Q40/04 , H04L47/193 , H04L47/56
CPC分类号: G06Q40/04 , H04L47/193 , H04L47/564
摘要: Method, apparatus and system may control chronological sequencing of data items received from a plurality of client computing devices, according to times of completion of transmission respectively from the client computing devices and distributing the data items according to the chronological sequencing to one or more destination computing devices with minimal latency. In an exemplary implementation, trade orders from participant computing devices may be distributed by an electronic trading platform with minimal latency to exchange gateways, based on time of transmission of the trade orders to the platform instead of time of receipt of the trade orders by the platform, thereby avoiding unfairness to those participants whose computing devices are located at greater distances from the platform than other computing devices respectively of other participants.
-
公开(公告)号:US11849012B2
公开(公告)日:2023-12-19
申请号:US17653243
申请日:2022-03-02
申请人: Google LLC
发明人: Akash Deshpande
IPC分类号: H04L69/163 , G06F9/455 , H04L43/0864 , H04L43/106 , H04L47/193 , H04L47/283
CPC分类号: H04L69/163 , G06F9/45558 , H04L43/0864 , H04L43/106 , H04L47/193 , H04L47/283 , G06F2009/45595
摘要: A method for estimation of performance characteristics for transport control protocol includes sparsely sampling, at a middlebox, a plurality of packets from a transport control protocol (TCP) connection between a source endpoint and a destination endpoint through the middlebox. For each packet of the sampled plurality of packets, the method includes generating a time stamp when the packet is sampled and recording a sequence number and an acknowledgment number for the respective packet. The acknowledgment number is recorded when the acknowledgment number exists for the respective packet. The method also includes generating an estimated performance characteristic for the TCP connection between the source endpoint and the destination endpoint through the middlebox over the period of time based on at least two of a respective time stamp, a respective sequence number, or a respective acknowledgment number from one or more of the sampled plurality of packets.
-
公开(公告)号:US20230379258A1
公开(公告)日:2023-11-23
申请号:US17747359
申请日:2022-05-18
发明人: David John Zacks , Jeff Apcar , Oliver Boehmer , Thomas Szigeti
IPC分类号: H04L47/193 , H04B7/185 , H04L69/16
CPC分类号: H04L47/193 , H04B7/18502 , H04L69/16
摘要: Techniques for a TCP proxy to communicate over a LEO satellite network on behalf of a client device by selecting a TCP congestion-control algorithm that is optimal for the LEO satellite network based on the time of day and/or location of the TCP proxy. Based on the locations of satellites during the day as they traverse predefined and patterned orbital paths, different TCP congestion-control algorithms may be more optimized to communicate data through the LEO satellite network. However, client devices generally use a single TCP congestion-control algorithm to communicate over WAN networks. Accordingly, a TCP proxy may be inserted on, for example, a router to communicate with the client device using a TCP congestion-control algorithm that the client device is configured to use, but then communicate over the LEO satellite network using a different TCP congestion-control algorithm that is optimal based on the time of day and/or other factors.
-
公开(公告)号:US11824962B2
公开(公告)日:2023-11-21
申请号:US17498574
申请日:2021-10-11
申请人: Apple Inc.
发明人: Cahya Adiansyah Masputra , Sandeep Nair , Darrin Jewell , Prabhakar Lakhera , Thomas Francis Pauly , Joshua Verweyst Graessley , Wei Shen , Olivier Mardinian
IPC分类号: H04L29/06 , H04L69/16 , H04L69/163 , H04L69/164 , H04L12/46 , G06F9/54 , H04L9/40 , G06F9/48 , G06F9/50 , G06F12/10 , G06F13/16 , G06F3/06 , G06F9/46 , G06F12/02 , H04L47/2475 , H04L47/2483 , H04L47/6295 , H04L49/00 , H04L49/9047 , H04L69/00 , G06F9/455 , H04L47/193 , H04L47/283 , G06F9/52 , H04L43/0864 , G06F16/23 , G06F21/52 , H04L47/24 , H04L47/30 , H04L47/32 , H04L47/6275 , G06F21/56 , H04L69/22 , G06F16/22 , H04L61/103 , H04L61/2503 , H04L67/146 , H04L69/18 , H04L1/00
CPC分类号: H04L69/162 , G06F3/0604 , G06F3/0631 , G06F3/0644 , G06F3/0673 , G06F9/45558 , G06F9/461 , G06F9/4881 , G06F9/5005 , G06F9/5016 , G06F9/5022 , G06F9/52 , G06F9/542 , G06F9/545 , G06F12/023 , G06F12/10 , G06F13/1668 , G06F16/2228 , G06F16/2365 , G06F21/52 , G06F21/568 , H04L12/4641 , H04L43/0864 , H04L47/193 , H04L47/2458 , H04L47/2475 , H04L47/2483 , H04L47/283 , H04L47/30 , H04L47/32 , H04L47/6275 , H04L47/6295 , H04L49/30 , H04L49/9052 , H04L61/103 , H04L61/2542 , H04L63/166 , H04L67/146 , H04L69/02 , H04L69/161 , H04L69/163 , H04L69/164 , H04L69/18 , H04L69/22 , G06F9/50 , G06F2009/45595 , G06F2209/5011 , G06F2212/657 , G06F2221/032 , G06F2221/034 , H04L1/0061
摘要: Methods and apparatus for efficient data transfer within a user space network stack. Unlike prior art monolithic networking stacks, the exemplary networking stack architecture described hereinafter includes various components that span multiple domains (both in-kernel, and non-kernel). For example, unlike traditional “socket” based communication, disclosed embodiments can transfer data directly between the kernel and user space domains. Direct transfer reduces the per-byte and per-packet costs relative to socket based communication. A user space networking stack is disclosed that enables extensible, cross-platform-capable, user space control of the networking protocol stack functionality. The user space networking stack facilitates tighter integration between the protocol layers (including TLS) and the application or daemon. Exemplary systems can support multiple networking protocol stack instances (including an in-kernel traditional network stack).
-
公开(公告)号:US11824746B2
公开(公告)日:2023-11-21
申请号:US17446179
申请日:2021-08-27
发明人: Tracey Ho , John Segui
IPC分类号: H04L43/0829 , H04L47/193 , H04L43/16
CPC分类号: H04L43/0835 , H04L43/16 , H04L47/193
摘要: A method for data communication between a first node and a second node over a data path includes estimating a rate at which loss events occur, where a loss event is either an unsuccessful delivery of a single packet to the second data node or an unsuccessful delivery of a plurality of consecutively transmitted packets to the second data node, and sending redundancy messages at the estimate rate at which loss events occur.
-
公开(公告)号:US20230254730A1
公开(公告)日:2023-08-10
申请号:US18302391
申请日:2023-04-18
发明人: Shu Shi , Rittwik Jana , Bo Han , Bo Chen
IPC分类号: H04W28/02 , H04L47/193 , H04L47/2475 , H04L43/087 , H04L43/10 , A63F13/355 , H04L47/283
CPC分类号: H04W28/0273 , H04L47/193 , H04L47/2475 , H04L43/087 , H04L43/10 , A63F13/355 , H04L47/283 , H04L67/01
摘要: The described technology is generally directed towards a transport protocol for latency sensitive applications. The disclosed transport protocol is “semi-reliable” in that it allows for specification of an importance of data being transmitted, thereby allowing important data to be sent reliably, while other data can be dropped if necessary, e.g., under bad network conditions. A deadline can be specified for such other data, and if the other data cannot be sent prior to the deadline, it can be dropped. Furthermore, the disclosed transport protocol can allow for early discovery of network jitter. A client device can send regular acknowledgments which identify most recently received data packets as well as a number of “heartbeat transmissions” received at the client device. A server device can use the acknowledgments to discover and respond to jitter.
-
-
-
-
-
-
-
-
-