Wang, Zhikui et al.

Patent Trials and Appeals Board

Jul 27, 2020

13362942 - (D) (P.T.A.B. Jul. 27, 2020)

UNITED STATES PATENT AND TRADEMARK OFFICE
UNITED STATES DEPARTMENT OF COMMERCE
United States Patent and Trademark Office
Address: COMMISSIONER FOR PATENTS
P.O. Box 1450
Alexandria, Virginia 22313-1450
www.uspto.gov
APPLICATION NO. FILING DATE FIRST NAMED INVENTOR ATTORNEY DOCKET NO. CONFIRMATION NO.
13/362,942 01/31/2012 Zhikui Wang 82833807 9996
56436 7590 07/27/2020
Hewlett Packard Enterprise
3404 E. Harmony Road
Mail Stop 79
Fort Collins, CO 80528
EXAMINER
LUU, CUONG V
ART UNIT PAPER NUMBER
2129
NOTIFICATION DATE DELIVERY MODE
07/27/2020 ELECTRONIC
Please find below and/or attached an Office communication concerning this application or proceeding.
The time period for reply, if any, is set in the attached communication.
Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the
following e-mail address(es):
chris.mania@hpe.com
hpe.ip.mail@hpe.com
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte ZHIKUI WANG,
ALAN L. GOODRUM, and DANIEL MORAN GALVAN
Appeal 2019-0002109
Application 13/362,942
Technology Center 2100
BEFORE JEREMY J. CURCURI, IRVIN E. BRANCH, and
MICHAEL J. ENGLE, Administrative Patent Judges.
CURCURI, Administrative Patent Judge.
DECISION ON APPEAL
STATEMENT OF THE CASE
Pursuant to 35 U.S.C. § 134(a), Appellant appeals from the
Examiner’s decision to reject claims 1–3 and 5–15.1 We have jurisdiction
under 35 U.S.C. § 6(b).
We AFFIRM.

1 We use the word Appellant to refer to “applicant” as defined in 37 C.F.R.
§ 1.42(a). Appellant identifies Hewlett Packard Enterprise Development LP
as the real party in interest. Appeal Br. 3.
Appeal 2019-002109
Application 13/362,942

2
CLAIMED SUBJECT MATTER
The claims are directed to “adapting a performance controller for [a]
server to operational characteristics of the server based on [a] real-time
model.” Abstract. Claim 1, reproduced below, is illustrative of the claimed
subject matter:
1. A method for real-time server management, the
method comprising:
determining a server architecture model offline based on
an offline analysis of performance characteristics of a
component of a server running on AC power, wherein the
server architecture model is determined from a function
selected from a group of functions consisting of a linear
function, a polynomial function, and an exponential function;
determining, by a processor, a real-time model of the
server from the server architecture model based on server
operation data capturing the server’s configuration and
operational conditions measured by sensors in real-time and
input into a performance controller for the server; and
adapting the performance controller for the server to
operational characteristics of the server based on the real-time
model.
Appeal 2019-002109
Application 13/362,942

3
REFERENCES
The prior art relied upon by the Examiner is:
Name Reference Date
Pate et al.
(“Pate”)
US 5,944,831 Aug. 31, 1999
McAdam et al.
(“McAdam”)
US 2004/0199559 A1 Oct. 7, 2004
Singh US 7,222,245 B2 May 22, 2007
Green et al.
(“Green”)
US 2008/0320322 A1 Dec. 25, 2008
Chen US 2009/0276638 A1 Nov. 5, 2009

Intel, The Problem of Power Consumption in Servers, QCon, Software
Development Conference, InfoQ Homepage Articles, 2009, 4–12,
https://www.infoq.com/articles/power-consumption-servers, last visited
July 2, 2020 (“Intel”).

REJECTIONS
Claims 1–3, 5, and 11–14 are rejected under pre-AIA 35 U.S.C. § 103
as obvious over Singh and Intel. Final Act. 3–7.
Claim 6 is rejected under pre-AIA 35 U.S.C. § 103 as obvious over
Singh, Intel, and Chen. Final Act. 7–8.
Claim 7 is rejected under pre-AIA 35 U.S.C. § 103 as obvious over
Singh, Intel, Chen, and McAdam. Final Act. 8–9.
Claim 8 and 9 is rejected under pre-AIA 35 U.S.C. § 103 as obvious
over Singh, Intel, and Green. Final Act. 9–10.
Claim 10 is rejected under pre-AIA 35 U.S.C. § 103 as obvious over
Singh, Intel, Green, and Pate. Final Act. 10–11
Appeal 2019-002109
Application 13/362,942

4
Claim 15 is rejected under pre-AIA 35 U.S.C. § 103 as obvious over
Singh, Intel, and Green. Final Act. 11–13.
OPINION
The Obviousness Rejection of Claims 1–3, 5, and 11–14 over Singh and Intel
The Examiner finds Singh and Intel teach all limitations of claim 1.
Final Act. 3–4; see also Ans. 3–5.
The Examiner finds Singh teaches most limitations of claim 1. See
Final Act. 3–4. The Examiner finds Intel teaches
determining a server architecture model offline based on
an offline analysis of performance characteristics of a component
of a server running on AC power, wherein the server architecture
model is determined from a function selected from a group of
functions consisting of a linear function, a polynomial function,
and an exponential function
as recited in claim 1. Final Act. 4 (citing Intel 7–11).
The Examiner reasons as follows:
Singh and Intel are analogous art because they work with
modeling power consumption of a computer system. At the time
of the invention, it would have been obvious to one of ordinary
skill in the art to combine the teachings of Singh and Intel. Intel’s
teachings would have helped estimate power consumption over
a defined period of time with simple arithmetic operation based
on known power consumption information.
Final Act. 4 (citing Intel 8).
Appellant presents the following principal arguments:
“[T]he Examiner fails to explain where Intel teaches or suggests an
‘offline’ analysis of a server, and moreover, any allegations by the
Examiner[] in this regard are unsupported by the teachings of Intel.” Appeal
Appeal 2019-002109
Application 13/362,942

5
Br. 11; see also Appeal Br. 10 (citing Spec. ¶¶ 26, 32) (discussing offline
analysis of a server).
There is no teaching or suggestion whatsoever in Intel that the
processor energy efficiency is related to an ‘offline’ operation of
the server. In fact, the indication of a ‘typical workload’ suggests
that the processor energy efficiency is related to a real-time
operation of the server. Nothing in Intel teaches or implies any
type of offline analysis of a server.
Appeal Br. 11–12 (citing Intel 8 (Fig. 4)).
The same reasoning [that program applications running on a
server do not teach offline analysis] applies to Intel which
pertains to real-time utilization (e.g., ‘applications continually
seek more memory’ based on increasing use of virtualization (see
second bullet point on page 9), usages by Internet Protocol Data
Centers (see third bullet point on page 9), etc.).
Appeal Br. 12.
In response, in pertinent part, the Examiner explains
Intel teaches estimation of power consumption, Pn, of a
processor using a formula, which is a linear function of
parameters, which would be provided, for calculation. This
formula Pn is a model for the processor component based on
provided parameters Pmax, Pidle, and n. Pn is not measured
while the processor is operating in real time but based on a
formula, so it is a performance characteristic[] of an offline
architecture model of the processor.
Ans. 4 (citing Intel 8).
In reply, Appellant argues
Intel clearly utilizes power consumption values that are
determined during operation of the server (e.g., “power
consumption at maximum performance (Pmax) and at idle (Pidle)”)
to determine power consumption (P) at “any specific processor
utilization (n%)”, each of which pertain to analysis of a server
Appeal 2019-002109
Application 13/362,942

6
during operation thereof, and not while the server is offline as
alleged by the Examiner.
Reply Br. 7.
We do not see any error in the contested Examiner’s findings. We
concur with the Examiner’s conclusion of obviousness.
Appellant’s Specification discloses
Figure 2B shows an example of a power loss graph 123 for
the power supply of Figure 2A, for changes in DC load and line
voltage. Thus, the power supply model may include a second-
order polynomial (i.e., a*Load2 + b*Load + c) as determined by
the offline modeler module 101 for controlling the power
capping controller 103, with the coefficients (a, b, c) being
determined by the real-time modeler module 107. Based on the
power supply model, the performance optimizer module 110
may reconfigure individual related performance controllers (i.e.,
the power capping controller 103) so that the performance
controllers adapt to the changes in the server operational
characteristics.
Spec. ¶ 33.
Thus, according to Appellant’s Specification, an example of a model
determined offline is a polynomial written as an algebraic expression. See
Spec. ¶ 33. Further, an example of a real-time model is the polynomial with
numerical coefficients. See Spec. ¶ 33.
Intel discloses “[m]any server workloads scale linearly from idle to
maximum power. When you know the power consumption of a server at
peak usage and at idle it becomes a simple arithmetic operation to estimate
power usage at any utilization rate.” Intel 8.
Intel further discloses
An estimate of power consumption (P) at any specific processor
utilization (n%) can be calculated if power consumption at
Appeal 2019-002109
Application 13/362,942

7
maximum performance (Pmax) and at idle (Pidle) are known. Use
the following formula:
𝑃𝑃𝑛𝑛 = (𝑃𝑃𝑚𝑚𝑎𝑎𝑎𝑎 − 𝑃𝑃𝑖𝑖𝑖𝑖𝑖𝑖𝑖𝑖) ×
𝑛𝑛
100
+ 𝑃𝑃𝑖𝑖𝑖𝑖𝑖𝑖𝑖𝑖
Intel 8.
Thus, we find Intel discloses
determining a server architecture model offline based on
an offline analysis of performance characteristics of a component
of a server running on AC power, wherein the server architecture
model is determined from a function selected from a group of
functions consisting of a linear function, a polynomial function,
and an exponential function
as recited in claim 1 because Intel’s power consumption formula (Intel 8) is
a polynomial written as an algebraic expression (the variable is n, Pmax and
Pidle determine the coefficients). Further, we find Intel’s power consumption
formula is determined “based on an offline analysis of performance
characteristics of a component of a server running on AC power” (claim 1).
See Intel 8 (“Many server workloads scale linearly from idle to maximum
power.”).
Regarding Appellant’s arguments with respect to Intel’s power
consumption formula, and in particular, Appellant’s arguments that Intel’s
Pmax and Pidle are determined during operation of the server, these arguments
do not show any error because Intel’s power consumption formula, as an
algebraic expression, is encompassed by the claim language. See Reply Br.
7; see also Intel 8.
Further, the Examiner articulated a reason to combine the references
that is rational on its face and supported by evidence drawn from the record.
See Final Act. 4 (citing Intel 8, para. 2). Appellant has not presented any
Appeal 2019-002109
Application 13/362,942

8
particularized arguments as to why this reasoning is incorrect. See Appeal
Br. 8–13; see also Reply Br. 4–12.
We, therefore, sustain the Examiner’s rejection of claim 1.
We also sustain the Examiner’s rejection of claims 2, 3, 5, and 11,
which depend from claim 1 and are not separately argued with particularity.
See Appeal Br. 18.
Regarding independent claim 12, Appellant presents the same
principal arguments as presented for claim 1. See Appeal Br. 13–18; see also
Reply Br. 12–13.
We, therefore, sustain the Examiner’s rejection of claim 12 for the
same reasons discussed above with respect to claim 1.
We also sustain the Examiner’s rejection of claims 13 and 14, which
depend from claim 12 are not separately argued with particularity. See
Appeal Br. 18.

The Obviousness Rejection of Claim 6 over Singh, Intel, and Chen
Appellant argues Chen does not cure the deficiency of Singh and
Intel. See Appeal Br. 19. We do not agree Singh and Intel are deficient. We,
therefore, sustain the Examiner’s rejection of claim 6.

The Obviousness Rejection of Claim 7 over Singh, Intel, Chen, and McAdam
Appellant argues McAdam does not cure the deficiency of Singh,
Intel, and Chen. See Appeal Br. 19–20. We do not agree Singh, Intel, and
Chen are deficient. We, therefore, sustain the Examiner’s rejection of claim
7.

Appeal 2019-002109
Application 13/362,942

9
The Obviousness Rejection of Claims 8 and 9 over Singh, Intel, and Green
Appellant argues Green does not cure the deficiency of Singh and
Intel. See Appeal Br. 20–21. We do not agree Singh and Intel are deficient.
We, therefore, sustain the Examiner’s rejection of claims 8 and 9.

The Obviousness Rejection of Claim 10 over Singh, Intel, Green, and Pate
Appellant argues Pate does not cure the deficiency of Singh, Intel, and
Green. See Appeal Br. 21. We do not agree Singh, Intel, and Green are
deficient. We, therefore, sustain the Examiner’s rejection of claim 10.

The Obviousness Rejection of Claim 15 over Singh, Intel, and Green
Claim 15 is rejected under pre-AIA 35 U.S.C. § 103 as obvious over
Singh, Intel, and Green. Final Act. 11–13.
Regarding independent claim 15, Appellant presents the same
principal arguments as presented for claim 1. See Appeal Br. 22–27; see also
Reply Br. 14.
We, therefore, sustain the Examiner’s rejection of claim 15 for the
same reasons discussed above with respect to claim 1.
DECISION
The Examiner’s decision to reject claims 1–3 and 5–15 is affirmed.
CONCLUSION
In summary:
Claims
Rejected
35 U.S.C. § Reference(s)/Basis Affirmed Reversed
1–3, 5, 11–
14
103 Singh, Intel 1–3, 5, 11–
14

Appeal 2019-002109
Application 13/362,942

10
6 103 Singh, Intel, Chen 6
7 103 Singh, Intel, Chen,
McAdam
7
8, 9 103 Singh, Intel, Green 8, 9
10 103 Singh, Intel, Green,
Pate
10
15 103 Singh, Intel, Green 15
Overall
Outcome
103 1–3, 5–15

No time period for taking any subsequent action in connection with
this appeal may be extended under 37 C.F.R. § 1.136(a). See 37 C.F.R.
§ 1.136(a)(1)(iv).
AFFIRMED