11058554 (B.P.A.I. Jun. 3, 2011)

Ex Parte Belady et al

Board of Patent Appeals and InterferencesJun 3, 2011

11058554 (B.P.A.I. Jun. 3, 2011)

UNITED STATES PATENT AND TRADEMARK OFFICE ____________________ BEFORE THE BOARD OF PATENT APPEALS AND INTERFERENCES ____________________ Ex parte CHRISTIAN L. BELADY and TOM L. VADEN ____________________ Appeal 2009-007983 Application 11/058,554 Technology Center 2100 ____________________ Before THU A. DANG, CAROLYN D. THOMAS, and DEBRA K. STEPHENS, Administrative Patent Judges. DANG, Administrative Patent Judge. DECISION ON APPEAL Appeal 2009-007983 Application 11/058,554 2 I. STATEMENT OF THE CASE Appellants appeal under 35 U.S.C. § 134(a) from a Final Rejection of claims 1-38, 40-45, and 49-51. We have jurisdiction under 35 U.S.C. § 6(b). We reverse. A. INVENTION Appellants’ invention relates to a power management system that collects resource utilization data, predicts future utilization, and allocates resources based on this data while powering down unnecessary resources (Abstract ). B. ILLUSTRATIVE CLAIM Claim 1 is exemplary: 1. A method comprising: collecting utilization data for a resource; inputting parameters specifying a desired capacity of said resource; predicting by a power management system, based on said collected utilization data, future utilization of said resource, wherein said parameters further specify that an amount of extra capacity above said predicted future utilization is to vary based on a volatility in said predicted future utilization of said resource; and controlling, by the power management system, power to said resource, based at least in part on said predicted future utilization of said resource and said input parameters. Appeal 2009-007983 Application 11/058,554 3 C. REJECTION The prior art relied upon by the Examiner in rejecting the claims on appeal is: Fung US 2002/004912 A1 Jan. 10, 2002 O’Connor US 2003/0056126 A1 Mar. 20, 2003 Odhner US 6,862,623 B1 Mar. 01, 2005 Claims 1-28, 30-38, 40-45, and 48-51stand rejected under 35 U.S.C. § 103(a) as being unpatentable over O’Connor in view of Odhner. Claim 29 stands rejected under 35 U.S.C. § 103(a) as being unpatentable over O’Connor in view of Odhner and Fung. II. ISSUE The issue is whether the Examiner has erred in determining that the references would have suggested a method of power management that enables a user to input parameters specifying “an amount of extra capacity above said predicted future utilization is to vary based on a volatility in said predicted future utilization of said resource.” In particular, the issue turns on whether Odhner teaches or suggests that a user is able to enter in an amount that represents an extra capacity above the predicted future utilization of a resource. Appeal 2009-007983 Application 11/058,554 4 III. FINDINGS OF FACT The following Findings of Fact (FF) are shown by a preponderance of the evidence. O’Connor 1. O’Connor teaches a system and method for strategic power reduction in a computer system, wherein a resource management engine 14 uses information stored in capacity tables 24 regarding processors 16 and power supplies 22 to determine when additional processors 16 should be brought online, offline, or reduced to a lower power state to efficiently satisfy the demand on server 12 (Fig. 1; ¶ [0030]). Odhner 2. Odhner discloses a power management system and historical method that projects future capacity based on real data reflecting the current capacity (col. 8, ll. 56-61; col. 9, ll. 20-27), wherein a manual method uses estimated data to manage the power of the resources supplied to handle the workload of the system (id.) 3. A calculation module 230 uses the server parameter values and the server resource utilizations to recommend a plan to the user on user interface 300 that displays server resource utilizations (Fig. 3; col. 8, ll.40- 55). The plan advises the user of necessary configuration changes to the server cluster 200 to ensure that the specified load will be adequately handled (id.). For example, if the processor utilization is greater than 90%, the calculation module 230 displays a message to the user that recommends that an additional processor be powered on (id.). 4. The manual method enables the user to manually enter the current load handled by the server cluster 200, the desired percentage Appeal 2009-007983 Application 11/058,554 5 increase of resource availability for the server cluster 200 to support, the number of servers currently in the server cluster 200, and the available bandwidth (Fig. 6; col. 9, ll. 7-15). IV. ANALYSIS Claims 1-28, 30-38, 40-45, and 48-51 Appellants contend that “O’Conn[o]r and Odhner, individually or combined, do not teach or suggest inputting parameters that specify an amount of extra capacity above the predicted utilization, or a parameter specifying extra capacity that varies based on volatility in the predicted fixture utilization” (App. Br. 12 ). In particular, Appellants argue that although Odhner teaches “the system will display a message to the user recommending an additional processor [when the projected processor utilization exceeds 90%,] … the parameter being input is just desired capacity, not a parameter specifying extra capacity” (App. Br. 13). Though the Examiner finds that Odhner teaches that “calculating module 230 calculate[s] future capacity and recommend[s] through [a] recommendation module … [that the user] add extra capacity (additional processor)” (Ans. 16, emphasis omitted), we agree with Appellants. In particular, we find no teaching or suggestion in the portions of O’Connor and Odhner of a user-entered amount that represents an extra capacity above the predicted future utilization of a resource, as required by claim 1. O’Connor is directed to strategic power reduction in a computer system that tracks the demand on a server and powers on additional processors when the demand reaches a certain predetermined level, wherein the system also powers down processors when the demand drops (FF 1). Appeal 2009-007983 Application 11/058,554 6 Accordingly, O’Connor teaches that the power of the resources is adjusted based upon the current demand (FF 1). Further, Odhner teaches power reduction in a computer system that has both a manual method and a historical method (FF 2), wherein the manual method enables the user to manually enter the current load, the desired percentage increase in resource utilization, the number of servers currently in the server cluster, and the available bandwidth (FF 4). During the historical method, a calculation module uses server parameter values and server resource utilizations to recommend a plan to the user; wherein, for example, if the current processor utilization exceeds 90%, a message is displayed to the user that recommends that an additional processor be powered on (FF 3). Thus, the historical method of Odhner projects future capacity based on current processor capacity (FF 2). However, we find that the portions of O’Connor and Odhner referenced by the Examiner do not teach or suggest providing “inputting parameters … [that specify] an amount of extra capacity above said predicted future utilization” as specifically required by claim 1 (emphasis added). In particular, although the system of Odhner alerts the user that another processor should be powered on, the extra capacity is not above the predicted future utilization; rather, the extra capacity is above the current processor utilization (FF 3). Accordingly, we find that Appellants have shown that the Examiner erred in rejecting representative claim 1, independent claims 15, 30, 41, and 44 falling therewith and claims 2-14, 16-29, 31-38, 40, 42, 43, 45, and 48-51 depending respectively therefrom under 35 U.S.C. § 103(a) over O’Connor in view of Odhner alone or in combination with Fung. Appeal 2009-007983 Application 11/058,554 7 V. CONCLUSION AND DECISION The Examiner’s rejection of claims 1-38, 40-45, and 48-51under 35 U.S.C. § 103(a) is reversed. REVERSED peb