# US 8,279,782 B2 · Systems and methods for the assignment of a plurality of processors to a plurality of data servers

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 8,279,782 B2
- Document ID: US8279782B2
- Status: Granted
- Kind: B2
- Application number: 10/197,831
- Filed: 2002-07-19
- Published: 2004-01-22
- Granted: 2012-10-02
- Earliest claimed: 2002-07-19
- Assignees: Alcatel Lucent
- Inventors: Hisham S. Abdel-Ghaffar; Walid Ahmed; Sanjiv Nanda; Ashwin Sampath
- Web page: https://patentgrep.com/patent/US8279782B2

## CPC

- G06F 9/5061: {Partitioning or combining of resources}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

The present invention provides systems and methods for the assignment of a plurality of processors to a plurality of data servers. An exemplary embodiment of the present invention provides systems and methods for addressing the problem of transmitter/receiver assignment for softer handoff in CDMA systems as well as any other system that requires variable size allocation of processors in a resource sharing environment. An exemplary embodiment of a system for processing data received from data servers according to the present invention comprises a shared medium, a plurality of processors and a smaller plurality of intermediate nodes partitioned into K sets, wherein at the kth set, every “k” processors are associated with one intermediate node. The shared medium couples the data servers to the intermediate nodes. Additionally, the system may include a system controller for controlling the operation of the system and the assignment of processors to the intermediate nodes and to the data servers at the beginning of each service request and thereafter upon each modification request to the service.

## Claims

### Claim 1

A system for coupling a plurality of processors in a base station to a plurality of data servers in the base station, comprising:
a plurality of sets of intermediate nodes in the base station, each intermediate node of the plurality of sets of intermediate nodes is adapted to couple a set of processors of the plurality of processors in the base station to a data server of the plurality of data servers in the base station,
wherein the total number of intermediate node sets is greater than or equal to the number of processors in the set of processors and less than a maximum number of processors allowed per data server.

### Claim 2 (depends on 1)

The system of claim 1, further comprising: a shared medium that is adapted to couple each of the data servers to a set of intermediate nodes.

### Claim 3 (depends on 1)

The system of claim 1, wherein the number of processors is equal to the number of data servers.

### Claim 4 (depends on 1)

The system of claim 1, further comprising: a system controller that is adapted to control coupling of the data servers to the processors.

### Claim 5 (depends on 4)

The system of claim 4, wherein the system controller is further adapted to partition the plurality of processors into K sets associated with intermediate nodes according to the following equation:
N
=
∑
k
=
1
K
⁢
k
*
L
k
where Lk is the number of intermediate nodes in the kth set.

### Claim 6 (depends on 4)

The system of claim 4, wherein the system controller is further adapted to associate each set of intermediate nodes with a cost metric.

### Claim 7

A method for coupling a plurality of processors in a base station to a plurality of data servers in the base station, comprising the steps of:
coupling a set of processors of the plurality of processors in the base station to a data server of the plurality of data servers in the base station through an intermediate node in a set of intermediate nodes of a plurality of sets of intermediate nodes in the base station,
wherein the total number of intermediate node sets is greater than or equal to the number of processors in the set of processors and less than a maximum number of processors allowed per data server.

### Claim 8 (depends on 7)

The method of claim 7, further comprising the step of: coupling each of the data servers to a set of intermediate nodes through a shared medium.

### Claim 9 (depends on 7)

The method of claim 7, wherein the number of processors is equal to the number of data servers.

### Claim 10 (depends on 7)

The method of claim 7, further comprising the step of: controlling the coupling of the data servers to the processors using a system controller.

### Claim 11 (depends on 10)

The method of claim 10, wherein the step of controlling the coupling of the data servers to the processors comprises the step of: partitioning the processors into K sets associated with intermediate nodes according to the following equation:
N
=
∑
k
=
1
K
⁢
k
*
L
k
where Lk is the number of intermediate nodes in the kth set.

### Claim 12 (depends on 10)

The method of claim 10, wherein the step of controlling the coupling of the data servers to the processors comprises the step of: associating each of the intermediate nodes with a cost metric.

### Claim 13

A method for coupling a plurality of processors in a base station to a plurality of data servers in the base station through one or more sets of intermediate nodes in the base station, comprising the steps of:
determining whether there are any available data servers in response to a service request in the base station;
declining service if there are no available data servers;
assigning a data server in the base station to the service request if there is an available data server;
initiating a service context initiation routine for the service request;
verifying that the specified quality of service is satisfied; and
upon receiving a service release request associated with an active data server, unassociating the active data server from a set of intermediate nodes and a set of processors associated with the active data server.

### Claim 14 (depends on 13)

The method of claim 13, wherein the step of initiating a service, context initiation routine comprises the steps of:
computing the number of processors, J′q, for any intermediate node combination, q;
finding a subset Q={q1, q2, . . . , qC}, where c is the number of combinations within the subset;
computing the cost of all combinations “q” within the subset Q;
choosing a combination, {circumflex over (q)}, where
J
q
^
′
=
∑
k
=
1
K
⁢
a
q
^
,
k
·
k
such that;
W
q
^
=
min
c
=
1
,
…
,
C
⁢
{
W
q
c
}
mapping the combination {circumflex over (q)}≡{a{circumflex over (q)},1, . . . , a{circumflex over (q)},K} to the set {âi,1[0], . . . , âi,K[0]}; and
assigning processors to each data server according to the following equation:
j
i
′
⁡
[
0
]
=
∑
k
=
1
K
⁢
a
^
i
,
k
⁡
[
0
]
·
k
⁢
.

### Claim 15 (depends on 14)

The method of claim 14, wherein the step of computing the number of processors, J′q, for any intermediate node combination, q, is performed in accordance with the following equation:
J
q
′
=
∑
k
=
1
K
⁢
a
q
,
k
·
k
⁢
;
0≦aq,k≦L′k,
where the aq,k are the numbers of the k-processor intermediate nodes used for the combination q.

### Claim 16 (depends on 14)

The method of claim 14, wherein the step of finding a subset Q={q1, q2, . . . , qC}, is perform in accordance with the following relationship:
J′q≧ji[0]; q=q1, q2, . . . , qC.

### Claim 17 (depends on 14)

The method of claim 14, wherein the step of finding a subset Q={q1, q2, . . . , qC}, is perform in accordance with the following relationship:
J′q≧ji[t+1]; q=q1, q2, . . . , qC.

### Claim 18 (depends on 14)

The method of claim 14, wherein the step of computing the cost of all combinations “q” within the subset Q is performed in accordance with the following equation:
W
q
=
∑
k
=
1
K
⁢
⁢
a
q
,
k
·
w
k
;
q=q1, q2, . . . , qC.

### Claim 19 (depends on 14)

The method of claim 14, further comprising the step of:
if C=0 in the step of finding a subset Q={q1, q2, . . . , qC} and ji[0]>jmin, finding the subset Q={q1, q2, . . . , qC}, such that,
J′q=ji[0]−1; q=q1, q2, . . . , qC.

### Claim 20 (depends on 19)

The method of claim 19, further comprising the step of:
decrementing J′q.

### Claim 21 (depends on 14)

The method of claim 14, further comprising the steps of:
receiving a sub-service modification request;
determining whether ji[t]≦ji[t+1]≦j′i[t];
if it is determined that ji[t]≦ji[t+1]≦j′i[t], setting j′i[t+1]=j′i[t];
if it is not determined that ji[t]≦ji[t+1]≦j′i[t], updating intermediate node counters without releasing processors; initiating a sub-service HA handler algorithm.

### Claim 22

A system controller for coupling a plurality of processors in a base station to one or more data servers in the base station, where the controller is adapted to:
determine whether there are any available data servers in response to a service request in the base station;
decline service if there are no available data servers;
assign a data server in the base station to the service request if there is an available data server;
initiate a service context initiation routine for the service request;
verify that the specified quality of service is satisfied; and
upon receiving a service release request associated with an active data server, unassociate the active data server from a set of intermediate nodes and a set of processors associated with the active data server.

### Claim 23 (depends on 22)

The controller of claim 22, wherein the system controller is further adapted to:
compute the number of processors, J′q, for any intermediate node combination, q;
find a subset Q={q1, q2, . . . , qC}, where c is the number of combinations within the subset;
compute the cost of all combinations “q” within the subset Q;
choose a combination, {circumflex over (q)}, where
J
q
^
′
=
∑
k
=
1
K
⁢
⁢
a
q
^
,
k
·
k
such that;
W
q
^
=
min
c
=
1
,
…
,
C
⁢
{
W
q
c
}
map the combination {circumflex over (q)}≡{a{circumflex over (q)},1, . . . , a{circumflex over (q)},K} to the set {âi,1[0], . . . , âi,K[0]}; and
assign processors to the data server according to the following equation:
j
1
′
⁡
[
0
]
=
∑
k
=
1
K
⁢
⁢
a
^
i
,
k
⁡
[
0
]
·
k
.

### Claim 24 (depends on 23)

The controller of claim 23, wherein the system controller is further adapted to compute the number of processors, J′q, for any intermediate node combination, q, according to the following equation:
J
q
′
=
∑
k
=
1
K
⁢
⁢
a
q
,
k
·
k
;
0≦aq,k≦L′k,
where the aq,k are the numbers of the k-processor intermediate nodes used for the combination q.
