PTAB

IPR2013-00094

Oracle v. CLoudIng IP LLC

Log In

1. Case Identification

2. Patent Overview

  • Title: Method System and Apparatus for Providing Pay-Per-Use Distributed Computing Resources
  • Brief Description: The ’784 patent describes methods and systems for providing on-demand, scalable computational resources to application providers over a distributed network. The technology aims to solve problems related to dynamic resource management and capacity planning by allowing providers to be charged based on the actual amount of resources utilized.

3. Grounds for Unpatentability

Ground 1: Obviousness over Aziz and Reed - Claims 1-3 and 5-7 are obvious over Aziz in view of Reed under 35 U.S.C. §103.

  • Prior Art Relied Upon: Aziz (Patent 6,779,016) and Reed ("Xenoservers: Accountable Execution of Untrusted Programs," a 1999 workshop publication).
  • Core Argument for this Ground:
    • Prior Art Mapping: Petitioner argued that Aziz taught a method for providing on-demand, distributed application processing using a computing grid logically divided into Virtual Server Farms (VSFs). Aziz disclosed allowing an organization (the application provider) to deploy applications onto its VSF, dynamically allocating and monitoring computing resources based on load, and billing customers based on actual usage in a "pay-as-you-go" model. This met most limitations of the independent claims. Reed was argued to supply the teaching of fine-grained, per-application accounting, stating that "all resources that an application consumes -- directly or indirectly - should be accounted to the application" and charged for accordingly.
    • Motivation to Combine: A Person of Ordinary Skill in the Art (POSITA) would combine the references to improve Aziz's system. A POSITA would have recognized the benefit of incorporating Reed’s specific, per-application accounting and charging mechanism into Aziz’s scalable VSF infrastructure to create a more granular, commercially robust, and accountable pay-per-use system.
    • Expectation of Success: A POSITA would have had a high expectation of success, as both references operated in the same field of distributed computing and addressed complementary aspects of resource management and billing.

Ground 2: Obviousness over London and Camiel - Claims 1, 2, 19, 20, and 22 are obvious over London in view of Camiel under §103.

  • Prior Art Relied Upon: London ("POPCORN – A Paradigm for Global-Computing," a 1998 Master's Thesis) and Camiel ("The Shared Object POPCORN System," a 1999 Master's Thesis).
  • Core Argument for this Ground:
    • Prior Art Mapping: Petitioner asserted that London’s "Popcorn" system disclosed a method for on-demand distributed computing over the Internet, which it described as a "simple virtual parallel computer." London taught allowing a "buyer" (application provider) to deploy concurrent programs, broken into "computelets," for remote execution on computers of "sellers." The system metered resource usage by measuring Java Operations (JOPs) and charged the buyer using an abstract currency called "popcoins," proportional to the JOPs consumed. Camiel, which described a component of the same Popcorn system, was argued to provide the missing load-balancing and dynamic resource reallocation features.
    • Motivation to Combine: A POSITA would combine the teachings because Camiel directly addressed and improved upon the Popcorn system described in London. Camiel introduced a "LoadBalancer" to the Popcorn system to move computations from slower to faster machines based on a performance threshold. This was a logical and necessary enhancement to improve the efficiency and scalability of London's foundational system.
    • Expectation of Success: Success was highly predictable because Camiel explicitly described an enhancement for the very system disclosed in London, demonstrating that the two concepts were designed to be fully compatible.

Ground 3: Obviousness over Foster and Grimshaw - Claims 1, 5, 6, 19, 20, and 22 are obvious over Foster in view of Grimshaw-1 and Grimshaw-2 under §103.

  • Prior Art Relied Upon: Foster ("The Grid: Blueprint for a New Computing Infrastructure," a 1998 book), Grimshaw-1 ("Campus-Wide Computing: Early Results Using Legion...," a 1997 journal article), and Grimshaw-2 ("Legion 1.4 Basic User Manual," a 1998 manual).
  • Core Argument for this Ground:
    • Prior Art Mapping: Petitioner argued that Foster described a comprehensive architecture for grid computing, including the "Legion" system, which was designed to support millions of hosts in a distributed environment. Foster taught allowing users to deploy applications onto the grid, described accounting systems to track and charge for resource consumption (e.g., the "NetCheque" system), and discussed adaptive tools for dynamically increasing resources (e.g., obtaining additional processors) when demand exceeds a threshold. Grimshaw-1 and Grimshaw-2, authored by the Legion system's primary architect, provided specific implementation details for the concepts in Foster, such as object-by-object resource monitoring and the commands used to run programs.
    • Motivation to Combine: A POSITA seeking to implement the high-level grid computing architecture described in Foster would have been motivated to consult Grimshaw-1 and Grimshaw-2 for concrete implementation details. The Grimshaw references provided the necessary "how-to" guidance for the Legion system's accounting, monitoring, and user-level functionality that Foster described conceptually.
    • Expectation of Success: A POSITA would have had a very high expectation of success, as all three references described different aspects of the same integrated system (Legion), making their combination a natural and straightforward engineering exercise.
  • Additional Grounds: Petitioner asserted additional obviousness challenges, including combinations of Aziz and Landherr (Patent 6,880,156), Neuman ("The Prospero Resource Manager") and London, and Reed and Aziz. These grounds relied on similar rationales of combining known elements for predictable results.

4. Key Claim Construction Positions

  • "first application": Petitioner argued this term should be construed broadly to include any collection of computer program instructions, without being limited by arbitrary distinctions between "modules" and "applications." This broad construction was asserted to be consistent with the specification and necessary to properly evaluate prior art systems that achieved the same functionality using different nomenclature.
  • "application provider": Petitioner proposed construing this term to include entities that deploy the application onto the network, such as content providers. This construction was based on distinctions the Patent Owner made during prosecution to differentiate its invention from systems where requests came only from passive end-users, and was therefore critical to applying prior art where content providers actively initiated deployment and execution.

5. Relief Requested

  • Petitioner requested institution of an inter partes review and cancellation of claims 1-3, 5-7, 19, 20, and 22 of the ’784 patent as unpatentable.