摘要:
A method includes identifying one or more elephant flows operated by a plurality of user equipment (UE) terminals located in a first coverage area, comparing the one or more elephant flows to threshold characteristics, determining whether the coverage area is congested, causing handover of the plurality of UE terminals from the first coverage area when the one or more elephant flows exceed the threshold characteristics and the first coverage area is congested.
摘要:
A method includes examining a first data packet transmitted to a first network equipment from a second network equipment. A data flow type of the first data packet is determined. If the data flow type is determined to be the first type of data flow, determining a delivery throughput of the first data packet to the first network equipment over a data flow path. The determined delivery performance of the first data packet is compared to an expected peak data throughput capacity for a data packet transmitted to the first network equipment from the second network equipment. Transmission of data packets to the first network equipment is paced if the comparison of the determined delivery performance and the expected peak data throughput capacity indicates a congestion exists over the data flow path.
摘要:
Systems and methods for managing and pacing data flows are described. In some embodiments, the systems and methods may select a data flow for management, the data flow being transmitted from a first network equipment to a second network equipment, determine, at a third network equipment, a delivery performance of the data flow being transmitted to the second network equipment, detect network congestion based on the determined delivery performance of the data flow being transmitted to the second network equipment, and pace, at the third network device and based on the detected network congestion, delivery of the data flow to the second network equipment by reducing a rate at which the data flow is delivered to the second network equipment.
摘要:
Systems and methods for pre-delivering content to user devices are described. In some embodiments, the systems and methods may assign a user device to a group of user devices that receive content from a common network edge cache, identify one or more differences between content delivered to the user device and content delivered to the group of user devices via the common network edge cache, select a piece of content to deliver to the user device based on the identified one or more differences of content, and cause delivery of the selected piece of content to the user device.
摘要:
A networked computing system for optimizing network channel resources. The system includes a sender device, user equipment, a congestion sensing agent, a data transfer agent, and a data communications network facilitating data communications amongst all devices of the system. The networked computing system is configured to detect a portion of channel traffic that is associated with a first data type, detect a portion of the channel traffic that is associated with a second data type, and determine whether to modify at least one data transfer of the second data type based on a comparison of the portions of the channel traffic associated with the first data type and the second data type. The first data type may relate to either voice data communications or another high priority data type, and the second data type may relate to a media content file type.
摘要:
Systems and methods for pre-delivering content to user devices are described. In some embodiments, the systems and methods may assign a user device to a group of user devices that receive content from a common network edge cache, identify one or more differences between content delivered to the user device and content delivered to the group of user devices via the common network edge cache, select a piece of content to deliver to the user device based on the identified one or more differences of content, and cause delivery of the selected piece of content to the user device.
摘要:
Systems and methods for providing the progressive download of media content using techniques that preferentially identify and use periods of surplus network capacity to maintain the content delivery. A buffer of a receiving system is maintained and pre-filled with enough content to bridge playback intervals where a network is unable to deliver content as fast as it is played out. Content delivery does not impact other users' applications and use of the network and its resources since content is preferentially sent when surplus network capacity exists in the network. When no surplus network capacity is available, a user requesting content may be given the option to continue the delivery in the background so that the content may be played at a later time. The user may then resume their playback experience once the content has been completely delivered using surplus network capacity as it becomes available.
摘要:
Sustainable average data throughput rates for data transfer between a sender and a receiver are determined for a network in a steady-state condition. Delivery performance for data transferred in non-steady-state conditions is disregarded in determining sustainable average data throughput rates. The rates may be used to adapt file delivery to network conditions.
摘要:
Systems and methods for determining or “predicting” which media content files are popular or will be popular, and based on that determination, pre-delivering or “pre-positioning” media content files to user devices automatically and without intervention from users so that the media content will be already stored on users' devices when they later select the media content for viewing. The determination of a media content file's popularity may be based on one or more combinations of content statistics (e.g., view count, viewing rate, etc.). The decision to pre-position a media content file may also be based on user profile information (e.g., viewing history). The pre-positioning may be accomplished using transport technology that avoids further burdening the network, such as delivering in real-time using available surplus network capacity.
摘要:
Pre-delivery or “pre-positioning” of advertising content to client computing devices for later playback thereon when users of the client computing devices are consuming non-advertising content. The pre-delivery may be accomplished using transport technology that avoids further burdening the network, such as delivering in real-time using available surplus network capacity. Users may have a limited number of times to watch non-advertising content on a client computing device before a pre-positioned advertisement is played on their client computing device. The advertising content may be viewed instantly without delay since it has been pre-positioned to the client computing devices. Advertising viewing statistics and reports are also generated and distributed.