摘要:
Methods and systems for broadcast-like effect using fractional-storage servers that receive and store erasure-coded fragments, which are generated on-the-fly from segments of streaming content arriving in real-time. Shortly thereafter, assembling devices obtain the fragments and reconstruct the segments at a rate that allows approximately real-time presentation of the streaming content including the segments.
摘要:
A content delivery system which supports fragment requests without specifying the source address, including an assembling device, a relay server, and fractional-storage servers. The assembling device issues a client-request to receive enough erasure-coded fragments to reconstruct a portion of streaming content. The relay server receives the client-request, selects a plurality of fractional-storage servers that together store enough fragments to reconstruct the portion, and transmits, to the fractional-storage servers, fragment pull protocol requests for these sufficient fragments, on behalf of the assembling device. And the fractional-storage servers transmit the requested fragments to the assembling device in response to the fragment requests.
摘要:
Methods and systems for maximum bandwidth broadcast-like streams, including a plurality of assembling devices; each assembling device retrieves, approximately simultaneously, erasure-coded fragments from a plurality of fractional-storage CDN servers, whereby the broadcast-like streaming contents are reconstructed from the fragments, and wherein different mixtures of broadcast-like streaming contents can be retrieved by the assembling devices until the aggregated bandwidth used by the assembling devices to retrieve the fragments approaches the aggregated fragment delivery bandwidth capabilities of the servers.
摘要:
Fast segment reconstruction from erasure-coded fragments, including the steps of requesting, by an assembling device using a fragment pull protocol, from a plurality of fractional-storage servers, a first quantity of erasure-coded fragments associated with one or more segments of streaming content; the first quantity of fragments is requested approximately according to the sequential order of the segments, and the first quantity of fragments is more than the minimal quantity of fragments needed for reconstructing the one or more segments. And receiving, by the assembling device, a second decodable quantity of fragments as a response; whereby the second quantity of fragments may be smaller than the first quantity due to a failure condition.
摘要:
Obtaining erasure-coded fragments using push and pull protocols, including the steps of receiving a first set of erasure-coded fragments associated with segments via a transmission using push protocol, whereby the first set is not sufficient for reconstructing some of the segments; and retrieving a second set of erasure-coded fragments using a fragment pull protocol, wherein the first and the second sets together are sufficient for reconstructing the segments.
摘要:
Bandwidth amplification using replicated fragments, including fractional-storage CDN servers storing erasure-coded fragments associated with content; and bandwidth amplification devices storing copies of sub-sets of the fragments stored on the servers in order to increase the system's total fragment delivery bandwidth. Wherein the average bandwidth amplification device comprises much less storage space and bandwidth than the average server, and the content can be reconstructed from any combination of enough unique fragments regardless of whether these fragments were obtained from the servers or from the bandwidth amplification devices.
摘要:
Hybrid distributed streaming system comprising high-bandwidth servers and peer-to-peer devices. The system includes fractional-storage CDN servers storing a first portion of rateless-coded fragments; and bandwidth amplification devices having a significantly smaller storage space and bandwidth compared to the servers, and storing a second portion of the fragments. Wherein both portions comprise unique rateless-coded fragments encoded with a high redundancy factor from streaming contents, the second portion is much larger than the first portion, and the first portion comprises approximately enough fragments to reconstruct the streaming contents.
摘要:
Receiving streaming content from servers located around the globe, including the following steps: requesting via the Internet, by an assembling device which may be located almost anywhere around the globe, using a fragment pull protocol, a set of erasure-coded fragments associated with segments of streaming content, from a plurality of fractional-storage servers which may be located almost anywhere around the globe. And compensating for lost fragments by requesting additional erasure-coded fragments that are needed to reconstruct the segments. Wherein the bandwidth of the streaming content is bounded approximately only by the incoming bandwidth of the assembling device.
摘要:
Controlling fragment load on shared links, including a large number of fractional-storage CDN servers storing erasure-coded fragments encoded with a redundancy factor greater than one from contents, and a large number of assembling devices configured to obtain the fragments from sub-sets of the servers. At least some of the servers share their Internet communication link with other Internet traffic, and the fragment traffic via the shared link is determined by the number of sub-sets in which the servers accessed via the shared link participate. Wherein the maximum number of sub-sets in which the servers accessed via the shared link are allowed to participate is approximately a decreasing function of the throughput of the other Internet traffic via the shared link.
摘要:
Methods and devices for comprising: obtaining an estimated heart rate training zone for a user; measuring the pulse rate of the user; and performing a plurality of computerized talk tests, such that a higher number of computerized talk tests are performed when the measured pulse rate is more in the vicinity of the estimated heart rate training zone than outside the vicinity of the estimated heart rate training zone. Other embodiments include devices for controlling an exercise program, comprising: an interface to an element configured to play auditory signals, and an interface to an element configured to record a user's speech in accordance with the auditory signals; wherein the device is configured to provide an indication upon identifying involuntary interruptions in the user's speech.