Systems and methods for compressing packet data by predicting subsequent data

• US 9,363,309 B2
• Filed: 11/17/2014
• Issued: 06/07/2016
• Est. Priority Date: 09/29/2005
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Silver Peak Systems Incorporated (Hewlett-Packard Enterprise Company)
• Inventors: Hughes, David Anthony
• Primary Examiner(s): Pham, Chi H
• Assistant Examiner(s): LOPATA, ROBERT J
• Application Number:
  US14/543,781
• Publication Number:
  US 20150074291A1
• Time in Patent Office: 568 Days
• Field of Search: 370/477
• US Class Current: 1/1
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: H03M 7/3084 using adaptive string matching, e.g. the Lempel-Ziv method
• CPC Class Codes: H03M 7/3086 employing a sliding window, e.g. LZ77
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 69/04 Protocols for data compression, e.g. ROHC
• CPC Class Codes: H04W 28/06 Optimizing the usage of the radio link, e.g. header compression, information sizing , discarding information system modifying transmission characteristic according to link quality by modifying frame length H04L1/0007; dynamic adaptation of the packet size for flow control or congestion control H04L47/365

Abstract

A system, method, and computer program for compressing packet data is provided. In exemplary embodiments, one or more prefix arrays may be generated for retrieved data, and used as the basis for predicting subsequent data. The packet data may be compressed based, at least partially, on the predicted subsequent data. Accordingly, the compressed packet data may be transferred over a communication network.

Claims

1. A method for compressing data using network memory pages, comprising:

scanning packet data for sync points;

using sync points to select one or more network memory pages as a compression context;

priming an encoder at least in part by generating at least one prefix array using at least a portion of information in the selected one or more network memory pages as the compression context, the at least one prefix array comprising characters from the selected one or more network memory pages;

encoding packet data based on the at least one prefix array and the compression context, the encoding comprising using the at least one prefix array to generate a prediction of a subsequent character; and

transferring packet data and selected one or more network memory pages to a decoder.

2. The method of claim 1, wherein the sync point is a coarse sync point, fine sync point, or a global sync point.

4. The method of claim 1, wherein the one or more network memory pages are selected based at least in part on repetitive data between the sync points.

5. The method of claim 1, wherein the at least one prefix array comprises all prior characters from the selected one or more network memory pages.

6. The method of claim 1, wherein the encoding packet data comprises encoding a probability distribution of the predicted subsequent character in the packet data.

7. The method of claim 1, wherein the encoding packet data comprises encoding an escape value and a character from the packet data.

8. The method of claim 1, wherein the encoding packet data comprises encoding a rank value representing the probability of a particular subsequent character in the packet data being the predicted subsequent character.

9. The method of claim 8, wherein the rank value is based at least in part on the frequency of occurrence of the predicted subsequent character in the selected one or more network memory pages.

10. The method of claim 1, wherein the one or more network memory pages comprise packet data previously transferred over a communication network.

3. A method for decompressing data using network memory pages, comprising:

receiving encoded data;

extracting identification information for context network memory pages from the encoded data;

retrieving the context network memory pages from local data storage based on the extracted identification information;

priming a decoder based on the context network memory pages, the priming comprising generating at least one prefix array using the retrieved context network memory pages from local data storage;

decoding packet data based at least in part on the generated at least one prefix array; and

transferring the decoded packet data across a communication network.

11. The method of claim 3, wherein the decoding packet data is further based at least in part on the context network memory pages.

12. The method of claim 3, wherein the context network memory pages were selected based at least in part on repetitive data between sync points.

13. The method of claim 3, wherein the at least one prefix array comprises all prior characters from the context network memory pages.

14. The method of claim 3, wherein the context network memory pages comprise packet data previously transferred over the communication network.