JP2003304282A - Client server system and transmission band management apparatus - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a client server system and transmission band management apparatus in which applications are provided on a network even if a failure occurs and part of a path on the network is in out of use. <P>SOLUTION: The client server system assigns a respective transmission band in each path on the network to each application provided to a client by a server. When the failure occurs on one path on the network and the transmission band in the path having no failure is assigned to the applications of the path having the failure, the transmission band assigned to the applications of the path having no failure is changed. <P>COPYRIGHT: (C)2004,JPO

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a client / server system, and more particularly, when an application by streaming such as video distribution or two-way video communication is provided on an IP network, each application has a route on the network. The present invention relates to a client-server system that exclusively occupies a transmission band.

[0002]

2. Description of the Related Art Currently, most applications provided on a network using IP are best-effort services such as electronic mail and Web viewing. In the future, broadband will be utilized by speeding up the access network. It is expected that the service will be gradually developed.

If a service utilizing broadband is developed, the frequency of use of applications mainly for streaming such as TV telephone and VoD distribution will increase in the network.

When providing an application mainly for streaming in a network, it is desirable that each application occupy a transmission band in a certain route on the network.

Conventionally, for example, D on an IP network
By using ifserv or the like, each application is made to monopolize the transmission band in a certain route on the network.

[0006]

However, in the conventional network, although the transmission band in a certain route on the network can be monopolized for each application, a part of the route of the network is used due to an untimely failure or the like. If it becomes impossible, there is a problem that it becomes impossible to provide an application that uses this route.

In view of such circumstances, the present invention can provide an application on a network even when a failure occurs and a part of the route of the network becomes unavailable. It is an object to provide a server system and a transmission band management device.

[0008]

According to the present invention, the above problems can be solved by the means described in the claims. That is, the invention according to claim 1 is a client-server system in which a transmission band in each path on a network is allocated to each application provided by a server to a client,

When a failure occurs in a certain path on the network and the transmission band of the path in which the failure has not occurred is allocated to the application of the path in which the failure has occurred, the path of the failure-free path The client-server system is characterized in that the transmission band allocated to the application is also changed.

According to a second aspect of the present invention, there is provided a transmission band management device in a client server system, wherein a transmission band in each path on a network is assigned to each application provided by a server to a client. When a fault occurs in a certain route above and the transmission band in the route in which the fault has not occurred is allocated to the application in the route in which the fault has occurred, the application in the route in which the fault has not occurred The transmission band management device is characterized in that the allocated transmission band is also changed.

According to a third aspect of the present invention, a transmission band in each route of the network and a bypass route used when a failure occurs on the network are set in advance for each application provided by the server to the client. In the client server system,

When the failure occurs, the application of the path in which the failure has occurred and the application of the bypass path of the application are
A client-server system characterized by proportionally distributing a transmission band in the bypass route based on a transmission band pre-allocated to these applications and allocating a new transmission band (z _{i_f} ) to each application. is there.

According to a fourth aspect of the present invention, a transmission band in each route of the network and a bypass route used when a failure occurs on the network are set in advance for each application provided by the server to the client. A transmission band management device in a client-server system,

When the failure occurs, the application of the path in which the failure has occurred and the application of the bypass path of the application are
A transmission band management device characterized by proportionally distributing the transmission band in the detour path based on a transmission band pre-allocated to these applications and allocating a new transmission band (z _{i_f} ) to each application. Is.

According to a fifth aspect of the invention, a transmission band in each route of the network and a bypass route to be used when a failure occurs on the network are preset for each application provided to the client by the server. In the client server system,

When the failure occurs, for the application on the path on which the failure has occurred, a new transmission path (z) on the detour path is used for the detour path used by the application on the detour path. the total value of Do transmission band _(Σz i_f) the sum of bandwidth in use exceeds the new transmission band _{(Σ (x i -z i_f)} ) transmission band obtained by subtracting both the _(z- (Σz i_f) - Σ (x _i −
z _{i_f} )),

In the path in which the failure has occurred, the application is proportionally allocated based on the transmission band previously allocated to the application in the path in which the failure has occurred,

On the other hand, in the case of an application which is using the transmission band beyond the new transmission band (z _{i — f} ) for the application of the bypass route, the transmission band of the bypass route used by the application. Assign (x _i ),

[0019] assigned a new transmission band _(z i_f) for new transmission band _(z i_f) following application in use the transmission band,

A new transmission band is used at regular intervals.
Total value of bandwidth in use (Σ (x_i-Z_{i _f}))
Repeat the above assignment until the total value of
Is a client-server system.

In a sixth aspect of the present invention, a transmission band in each route of the network and a bypass route to be used when a failure occurs on the network are preset for each application provided to the client by the server. A transmission band management device in a client-server system,

When the failure occurs, for the application of the path in which the failure has occurred, a new transmission path (z) in the detour path is used for the detour path used by the application of the detour path. Transmission band (z− (Σz _{i_f} ) −Σ which is obtained by subtracting both the total value of the transmission band (Σz _{i_f} ) and the total value of the band in use beyond the new transmission band (Σ (x _i −z _{i_f} ). (X _i −
z _{i_f} )),

In the path in which the failure has occurred, the application is proportionally allocated based on the transmission band previously allocated to the application in the path in which the failure has occurred,

On the other hand, in the case of an application which is using the transmission band beyond the new transmission band (z _{i — f} ) for the application on the bypass path, the transmission band (x _i ) used by the application is used. ),

The allocation of new transmission band _(z i_f) for new transmission band _(z i_f) following application in use the transmission band,

A new transmission band is used at regular intervals.
Total value of bandwidth in use (Σ (x_i-Z_{i _f}))
Repeat the above assignment until the total value of
Is a transmission band management device.

According to the present invention, when an application fails to occupy the transmission band in a part of the network (for example, between routers) due to a failure on the network, another application It is possible to occupy a new transmission band on the route (detour route).

According to the present invention, when a failure or the like occurs on the network, the value of the transmission band that each application occupies on the network is determined according to the value of the transmission band used by these applications. It can be reallocated dynamically.

[0029]

BEST MODE FOR CARRYING OUT THE INVENTION [Outline of the Present Invention] FIG. 1 is a diagram showing an outline of the present invention.

The network shown in FIG. 1 is an IP network, and a plurality of servers and clients exist on this IP network.

There are a plurality of routes between the server and the client, and each application provided by the server is
It occupies the transmission band used by itself on these routes. Hereinafter, allocating the transmission band on the network to the application is referred to as allocating the transmission band to the application.

The admission control device manages the transmission band assigned to each application. Furthermore, when each application tries to use a transmission band other than the transmission band allocated to itself, the admission control device controls the permission / non-permission of this use. This permission / non-permission is performed based on the used bandwidth allocated to each application.

Regarding a specific method in which each application occupies the transmission band between each node (router, layer switch, etc.), existing techniques (for example, Diff) are used.
service etc.) is used.

FIG. 2 is a diagram showing a situation where a failure occurs on the network shown in FIG.

In FIG. 2, route A on the network
There is a network failure in. In this case, route A
The application that has been allocated the transmission band above has another path, that is, the path B, as follows.
A new transmission band is allocated above.

The admission control device calculates the final allocated bandwidth of each application by proportionally distributing the total transmission bandwidth value of the path B according to the transmission bandwidth occupied by each application before the occurrence of the network failure.

If the application whose transmission band is allocated to the route B uses the transmission band equal to or larger than the transmission band value allocated after the occurrence of the network fault before the occurrence of the fault, the admission control device uses the transmission band. The excess transmission band value is assigned to the application.

The admission control device periodically (or irregularly) reallocates the transmission band after a lapse of a certain time after the occurrence of the network failure, and the allocated bands of all the applications converge to the final allocated band. This reassignment operation is repeated until.

[Description of Embodiments] FIG. 3 is a diagram showing a network configuration of an embodiment according to the present invention, and FIG.
FIG. 7 is a diagram for explaining reassignment according to the embodiment of the present invention. Hereinafter, reassignment according to the embodiment of the present invention will be described with reference to FIGS. 3 and 4. In the present embodiment, there is shown a case where the link capacity is relatively free and the detour route of the current application can be secured.

In this embodiment, a server-client type service (application) is provided in an IP network composed of a plurality of routers and nodes. There are a plurality of routes between the server and the client on the network. Each application has
A transmission band is assigned to each route.

(Setting of pre-allocated bandwidth to each application) The route A is allocated with N applications from AP_1 to AP_N (N is a positive integer). Therefore, for AP_1 to AP_N, the route A
Is a normal link.

Here, the kth application AP_k
, The band of z _{k_i} is pre-allocated,
The sum of the pre-allocated bandwidth of AP_1~AP_N is the Z _{A_i.} The k-th application sets the transmission band actually used on the route A at a certain time t as x _k (t). All bands TA of the route _A are allocated to AP_1 to AP_N as pre-allocated bands. Therefore, T _A = Z _A — _i .

On the route B, MN applications from AP_ (N + 1) to AP_M are assigned.
That is, the route B is a normal link for AP_ (N + 1) to AP_M.

Here, the l-th application AP_
The l assumed that the bandwidth of the z _{L_i} is allocated in advance, AP_ (N + 1) Total Pre-allocated bandwidth of ~AP_M is a Z _{b_i.} The k-th application sets the transmission band actually used on the route B at a certain time t by x
_{Let l} (t). All bands TB of the route _B are allocated to AP_ (N + 1) to AP_M as pre-allocated bands. Therefore, T _B = Z _B — _i .

(Occurrence of Network Failure) It is assumed that a network failure occurs on the route A and communication between the server and the client for AP_1 to AP_N to which the transmission band is allocated on the route A is disabled.

In this case, the transmission band is reassigned on the route B to AP_1 to AP_N. Therefore, route B
Are detour links for AP_1 to AP_N. The reallocation is performed by the admission control device as follows.

(Calculation of Final Allocated Bandwidth for Each Application) The admission control device uses AP_1-A
Applications AP_1 to AP_1 based on the bandwidth that P_M occupied in the route A or the route B before the failure occurred.
The final allocation bandwidth (final allocation bandwidth) is calculated by proportionally distributing the bandwidth Z _{B_i of the} route B to AP_M.

[0048]

[Equation 1]

[0049]

[Equation 2] (Verification of allocatable bandwidth) The admission control device
The bands used by AP_ (N + 1) to AP_M on the route B are detected. The admission control device uses AP on route B
band x _l (t) used for _l [N + 1 ≦ l ≦ M]
_Is less than or equal to the final band z _{l_f} after reallocation, that is,

[0050]

[Equation 3] , The reallocation band z _l (t ₀ ) of AP_l at time t ₀ is z
_{l_f} .

On the other hand, the admission control device uses the route B
X _l used in AP_l [N + 1 ≦ l ≦ M] in
When (t) is larger than the final band z _{l_f} after the reallocation and is equal to or _smaller than the _preallocated band z _{l_i} before the reallocation, that is,

[0052]

[Equation 4] In this case, the reassigned band z _l (t ₀ ) of AP_l at time t _{0 is} the assigned band at that time, that is, x _l (t ₀ ).

After performing the reallocation to AP_ (N + 1) to AP_M as described above, the admission control device allocates the band not used by these AP_ (N + 1) to AP_M on the route B. Verify.

From here, AP_l [N + 1 ≦ l ≦
The transmission bandwidth used by M] exceeding the final allocated bandwidth is

[0055]

[Equation 5] Is.

The total final allocated bandwidth for AP_1 to AP_N is

[0057]

[Equation 6] Becomes

Therefore, the admission control device is
Allocated bandwidth z at time t ₀ of AP_1 to AP_N
_k (t ₀ )

[0059]

[Equation 7] And

Then, the admission control device is
The re-allocated band of _l (N + 1 ≦ l ≦ M) is reduced at the end of the service (for example, after disconnecting the line in the case of a TV phone).

The admission control device uses the route B in advance.
AP_l (N + 1 ≦
Reassignment is performed so that l ≦ M) maintains the transmission band used before the failure. Therefore, according to the present embodiment, the service (application) being provided on the route B
The quality of is guaranteed.

(Continuing Bandwidth Allocation) The admission control device repeats the above procedure at regular or irregular intervals. Here, for simplification of description, it is assumed that the process is repeated at regular time intervals Δt. Therefore, the admission control device operates as follows. At the time t ₀ + nΔt (n is a positive integer), the admission control device determines that the transmission band x _l (t ₀ + NΔt) used by AP_l [N + 1 ≦ l ≦ M] on the route B is the final value after the reallocation. If the band z _{1_f} or less, that is,

[0063]

[Equation 8] In case of AP_l, the allocated band z ₁ (t ₀ at time t ₀ + nΔt)
Let + NΔt) be z _{l — f} .

On the other hand, at the time t
_{At 0} + nΔt (n is a positive integer), AP_l on route B
Transmission band x _l (t ₀ + used by [N + 1 ≦ l ≦ M]
NΔt) is larger than the final band z 1 — _f after reallocation and is equal to or less than the pre-allocated band z 1 — _i before reallocation, that is,

[0065]

[Equation 9] In the case of AP_l, the allocated band z _l (t ₀ at time t ₀ + nΔt)
+ NΔt) is the allocated bandwidth at that time, that is, z
Let _l (t ₀ + NΔt).

After reassigning AP_ (N + 1) to AP_M as described above, the admission control device allocates a band not used by these AP_ (N + 1) to AP_M on the route B. Verify.

From now on, if the final allocated bandwidth is exceeded and A
The transmission band used by P_l [N + 1 ≦ l ≦ M] is

[0068]

[Equation 10] Is.

Therefore, the admission control device is
The allocated bandwidth z _k (t ₀ + NΔt) of AP_1 to AP_N at time t ₀ + nΔt is

[0070]

[Equation 11] And

(End of Band Allocation Procedure) The admission control device allocates the allocated bandwidth z of each AP_1 to AP_N.
_{When k} (t) becomes the same as the final allocated band z 1 — _f , the band allocation work is finished. As described above, according to the present embodiment, when a failure occurs in the route A,
The bandwidth is sequentially assigned to the application provided on the route A in a form in which the bandwidth value of the application whose transmission band is assigned on the route B is secured.

(Detailed Description of Embodiments) FIG. 5 is a diagram for explaining the embodiments of the present invention in detail. As shown in FIG. 5, AP_1 to AP_3 cannot use the transmission band on the route A because the network failure has occurred on the route A.

The following transmission bands were allocated to the respective applications as preliminarily secured bands before the network failure occurred.

Path A (total transmission band TA = 100 Mbp
s) AP_1 (TV phone service A 5 Mbp per call)
s) z ₁ — _i = 50 Mbps (connectable for 10 calls) AP — 2 (TV phone service B 1 Mbps per call)
s) z ₂ — _i = 25 Mbps (connectable for 25 calls) AP_3 (TV phone service C 0.5 Mb per call)
ps) z _{3_i} = 25 Mbps (25 calls can be connected)

Path B (total transmission band T _B = 100 Mbps
AP_4 (VoD service A 0.
5 Mbps) z ₄ — _i = 50 Mbps (100 streams can be connected) AP_5 (VoD service B 1M per stream)
bps) z _{5_i} = 50 Mbps (50 streams can be connected)

Here, at the time t ₀ immediately before the occurrence of the network failure, the bandwidth used by each application is AP_1 x ₁ (t ₀ ) = 30 Mbps (connection for 6 calls) AP_2 x ₂ (t ₀ ) = 20 Mbps. (Connection for 20 calls) AP_3 x ₃ (t ₀ ) = 10 Mbps (connection for 20 calls) AP_4 x ₄ (t ₀ ) = 30 Mbps (connection for 60 streams) AP_5 x ₅ (t ₀ ) = 30 Mbps (connection for 30 streams) ) Is.

In this embodiment, the route A is
The route B to AP_1 to AP_3 that occupied the transmission band in
Allocate the new transmission band above.

In this embodiment, first, AP_1 to AP_5
On the other hand, a total of 100 Mbps of the transmission band secured by AP_4 and AP_5 on the route B is proportionally allocated and assigned according to the ratio of the first reserved band.

Therefore, for AP_1 to AP_5, T _B = 100 Mbps is the ratio of the initial reserved bandwidth, 50: 25: 25: 50: 50 = 2: 1: 1: 2 :.
Assigned according to 2.

[0080] Thus, finally, the value of the transmission band (final allocation band) allocated to _{AP_1~AP_5, AP_1 z 1_f = 25Mbps,} AP_1 z 2_f = 12.5Mbps, AP_1 z 3_f = 12.5Mbps, AP_1 z _{4_f} = 25 Mbps and AP_1 z _{5_f} = 25 Mbps.

However, if the final allocated bandwidth is executed immediately, it is assumed that the available transmission bandwidth for a certain application decreases and the call or service in use is interrupted. Therefore, the following operation is performed.

Here, it is assumed that when the failure occurs in the route A, the bandwidth of AP_4 is x ₄ (t ₀ ) = 30 Mbps and the bandwidth of AP_5 is x ₅ (t ₀ ) = 30 Mbps on the route B. AP
The bandwidths used by _4 and AP_5 exceed the final allocated bandwidth, but in the present embodiment, the bandwidths used by AP_4 and AP_5 whose normal link is the route B are secured.

Therefore, regarding the allocated bandwidths of AP_4 and AP_5, AP_4 is x ₄ (t ₀ ) = 30 Mbps, AP_5
Becomes x ₅ (t ₀ ) = 30 Mbps.

On the other hand, a total bandwidth of 50 Mbps should be finally allocated to AP_1 to AP_3.
At this point, AP_4 and AP_5 total 60 Mbps
Since it is allocated, the bandwidth allocated immediately to AP_1 to AP_3 is 40 Mbps (= 100-60).

Therefore, the allocated bandwidth immediately after the occurrence of the network failure is that AP_1 is x ₁ (t ₀ ) = 2, respectively.
₀ Mbps, AP_2 is x ₂ (t ₀ ) = 10 Mbps, A
P_3 becomes x ₃ (t ₀ ) = 10 Mbps.

For the time being, the admission control device is AP_4.
And AP_5, 25 Mbp of the final allocated bandwidth
20M for AP_1 to AP_3 using s as a reference value
Admission control is performed based on bps, 10 Mbps, and 10 Mbps.

Next, after a lapse of a fixed time, at time t ₁ , AP_
4 and AP_5, the bandwidth used is AP_4 x ₄ (t ₁ ) = 25 Mbps (50 streams for VoD service A) AP_5 x ₅ (t ₁ ) = 27 Mbps (27 streams for VoD service A). At time t ₁ , AP_4 and AP_5
With regard to, the used bandwidth should decrease as soon as each service ends without adding a new stream.

Therefore, the admission control device is
_1 to AP_3, a newly generated bandwidth of 8 Mbps
Is proportionally allocated. As a result, the allocated bandwidths of AP_1 to AP_3 are AP_1 z ₁ (t ₁ ) = 18 Mbps, AP_2 z ₂ (t ₁ ) = 9 Mbps, and AP_3 z ₃ (t ₁ ) = 9 Mbps.

[0089] Furthermore, after a certain period of time has elapsed, at time t ₂ AP_
It is assumed that the bandwidth used in No. ₅ is x ₅ (t ₂ ) = 25 Mbps (25 streams for VoD service B). Time t
_{In 2} , the allocated bandwidth for AP_1 to AP_3 matches the final allocated bandwidth. That is the _{AP_1 z 1 (t 2) =} 25Mbps (= z 1_f) AP_2 z 2 (t 2) = 12.5Mbps (= z 2_f) AP_3 z 3 (t 2) = 12.5Mbps (= z 3_f) .

The allocated bandwidths for AP_4 and AP_5 are AP_4 z ₄ (t ₂ ) = 25 Mbps (= z _{4_f} ) AP_5 z ₅ (t ₂ ) = 25 Mbps (= z _{5_f} ).

Therefore, the admission control device is
At time t ₂ , the procedure for changing the allocated bandwidth is completed.

[0092]

According to the present invention, when a failure occurs in a certain route in a network in which an application occupies a transmission band in the certain route of the network,
Use a different route for the application (a detour link)
After switching to, the transmission band of the network can be newly allocated to each application according to the usage band of each application, and the band can be monopolized.

Therefore, according to the present invention, even when a failure occurs and a part of the routes of the network becomes unavailable, the application can be provided on the network.

[Brief description of drawings]

FIG. 1 is a diagram showing an outline of the present invention.

FIG. 2 is a diagram showing a situation in which a failure has occurred on the network shown in FIG.

FIG. 3 is a diagram showing a network configuration according to the embodiment of the present invention.

FIG. 4 is a diagram for explaining reassignment according to the embodiment of the present invention.

FIG. 5 is a diagram illustrating an embodiment of the present invention in detail.

─────────────────────────────────────────────────── ─── Continuation of the front page (51) Int.Cl. ⁷ Identification code FI theme code (reference) H04L 29/08 H04L 13/00 307C F term (reference) 5B045 BB11 GG01 JJ07 JJ14 JJ42 JJ46 5K030 LB08 LC09 MB01 MD02 5K034 AA17 CC02 DD03 EE10 FF01 FF13 JJ11 MM08 TT01

Claims (6)

[Claims] 1. In a client-server system in which transmission bandwidths of respective routes on a network are respectively allocated to respective applications provided by a server to a client, a fault occurs on a certain route on the network, and the fault occurs. A client, characterized in that when a transmission band in a route in which the fault has not occurred is assigned to an application in the route, the transmission band assigned to the application in the route in which the fault has not occurred is also changed. Server system. 2. A transmission band management device in a client-server system, wherein a transmission band in each route on a network is allocated to each application provided by a server to a client, and a failure occurs in a certain route on the network. When the transmission band in the route in which the fault has not occurred is allocated to the application in the route in which the fault has occurred, the transmission band also allocated to the application in the route in which the fault has not occurred A transmission band management device characterized by being changed. 3. A client-server system in which a transmission band in each path of a network and a detour path used when a failure occurs in the network are preset for each application provided by the server to the client, When an error occurs, the application of the faulty route and the application of the bypass route of the application, in each route, based on the transmission band pre-allocated to these applications, A client-server system characterized by proportionally distributing a transmission band and allocating a new transmission band ( _{zi_f} ) to each application. 4. A transmission band in a client-server system in which a transmission band in each route of the network and a detour route used when a failure occurs in the network are preset for each application provided by the server to the client. A management device, in the event of the occurrence of the failure, an application of a path in which the failure has occurred and an application of a bypass path of the application, in each path, a transmission band previously allocated to these applications Based on the above, the transmission band in the detour path is proportionally distributed, and a new transmission band (z _{i_f} ) is allocated to each application. 5. Each application provided by the server to the client
Application in each path of the network
In case of failure in transmission band and network
Client with preset detour route to use
In the server system, If the above failure occurs, For the application of the route where the failure occurred
Is From the entire transmission band (z) in the detour route, the detour
In the detour route used by the route application
Value of the new transmission band (Σz_{i_f}) And new transmission bands
The total value of the bands in use beyond the range (Σ (x_i-Z_{i_f}))
Transmission band (z- (Σz_{i_f}) −Σ
(X_i-Z_{i_f})) In the route where the failure occurred, the history of the failure
Pre-allocated for road applications
Based on the transmission band On the other hand, for the application of the bypass route, new
Tana transmission band (z_{i_f}) Above the bandwidth being used.
In case of application, the application uses
Transmission bandwidth (x_i), New transmission band (z_{i_f}) The following transmission bands are being used
New transmission band (z_{i_f})
allocation, At regular intervals, the new bandwidth is exceeded and the bandwidth
Total value (Σ (x_i-Z_{i _f})) Is calculated and this total value is 0
Is characterized by repeating the above allocation until
Client-server system. 6. Each application provided by the server to the client
Application in each path of the network
In case of failure in transmission band and network
Client with preset detour route to use
A transmission band management device in a server system, If the above failure occurs, For the application of the route where the failure occurred
Is From the entire transmission band (z) in the detour route, the detour
In the detour route used by the route application
Value of the new transmission band (Σz_{i_f}) And new transmission bands
The total value of the bands in use beyond the range (Σ (x_i-Z_{i_f})of
Transmission band (z- (Σz_{i_f}) −Σ (x_i
-Z_{i_f})) In the route where the failure occurred, the history of the failure
Pre-allocated for road applications
Based on the transmission band On the other hand, for the application of the bypass route, new
Tana transmission band (z_{i_f}) Above the bandwidth being used.
In case of application, the application uses
Transmission bandwidth (x_i), New transmission band (z_{i_f}) The following transmission bands are being used
New transmission band (z_{i_f})
allocation, At regular intervals, the new bandwidth is exceeded and the bandwidth
Total value (Σ (x_i-Z_{i _f})) Is calculated and this total value is 0
Is characterized by repeating the above allocation until
Transmission bandwidth management device.