Self-organizing intelligent network architecture and methodology

• US 20030217129A1
• Filed: 05/15/2002
• Published: 11/20/2003
• Est. Priority Date: 05/15/2002
• Status: Abandoned Application

• Current Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Original Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Inventors: Moganti, Madhav, Knittel, Steven F.
• Application Number:
  US10/146,422
• Publication Number:
  US 20030217129A1
• Time in Patent Office: Days
• US Class Current: 709/223
• CPC Class Codes: H04L 41/0856 by backing up or archiving configuration information
• CPC Class Codes: H04L 41/0893 Assignment of logical groups to network elements
• CPC Class Codes: H04L 41/0894 Policy-based network configuration management
• CPC Class Codes: H04L 41/22 comprising specially adapted graphical user interfaces [GUI]
• CPC Class Codes: H04L 41/5003 Managing SLA; Interaction between SLA and QoS
• CPC Class Codes: H04L 41/5029 Service quality level-based billing, e.g. dependent on measured service level customer is charged more or less
• CPC Class Codes: H04L 43/0852 Delays
• CPC Class Codes: H04L 43/087 Jitter
• CPC Class Codes: H04Q 3/0029 Provisions for intelligent networking

Abstract

An intelligent network including a plurality of hierarchal intelligent layers, each layer responsive to communications from at least one of a superior layer and a subordinate layer. A plurality of nodes form each layer, where each of the plurality of nodes have intelligence modules that are interconnected horizontally within each layer, as well as interconnected to intelligence modules of the subordinate and superior hierarchal layers, wherein the intelligence is provided end-to-end of the hierarchal self-organizing intelligent network.

Claims

1. An intelligent network, comprising:

a plurality of hierarchal intelligent layers, each layer responsive to communications from at least one of a superior layer and a subordinate layer;

a plurality of nodes forming each layer, each of the plurality of nodes having intelligence modules and interconnected horizontally within each layer and interconnected to intelligence modules of the subordinate and superior hierarchal layers, wherein the intelligence is provided end-to-end of the hierarchal self-organizing intelligent network.

2. The intelligent network of claim 1, further comprising feedback loops between the superior and subordinate layers.

3. The intelligent network of claim 1, wherein the hierarchal intelligent layers comprise layers selected from the group consisting of at least two of a network management layer, an infrastructure provider layer, a programmable technology layer, a service provider layer, a subscriber layer, an application layer, a content layer, and an end-user layer.

4. The intelligent network of claim 1, wherein each of intelligence module comprises an input processing module, response processing module, a communications world model (CWM) module, a behavioral generation (BG) module, and a value assessment (VA) module in communication with each other.

5. The intelligent network of claim 4, wherein said input processing module receives inputs to the intelligent network system, compares input observations with expectations generated by the CWM module, and communicates observed entities, events, and perceived situations to the VA modules.

6. The intelligent network of claim 5, wherein the BG module hypothesizes plans, the CWM module predicts results of such plans, and the VA module evaluates those results.

7. The intelligent network of claim 6, wherein said CWM module further comprises a database for storing information regarding about the network and network environment.

8. The intelligent network of claim 7, wherein the CWM module provides current status of said network and network environment from automated planners and executors of the BG modules.

9. The intelligent network of claim 7, wherein said CWM module generates expectations and predictions about network resources, operations, usage;

and

responds to requests for information about present, past, and probable future states of the world.

10. The intelligent network of claim 9, wherein said CWM module performs simulation functions of actions hypothesized by the BG modules;

predicted results are sent to the VA module for evaluation; and

said evaluation results are sent to said CWM module to answer hypothetical queries from automated planners and executors of the BG modules.

11. The intelligent network of claim 7, wherein said CWM module generates predictions enabling the IRP module to perform correlation and predictive filtering, where said CWM model database is updated based on said correlations and differences between said CWM module predictions and observations of input data at each intelligent network node.

12. The intelligent network of claim 6, wherein said BG module

selects for execution, said plans with highest evaluations:

monitors execution of said selected plans; and

modifies existing plans in response to changes in said network and network environment.

13. The intelligent network of claim 1, wherein the intelligence modules at each node utilize historical information gathered as each node to formulate decisions for future actions.

14. The intelligent network of claim 13, wherein the intelligence modules select goals and plans, and executes tasks, said tasks are recursively decomposed into subtasks, and said subtasks are sequenced to achieve said goals.

15. The intelligent network of claim 7, wherein said input processing, response processing, WM, BG and VA modules at each node of each network layer aggregately define a hierarchal intelligence across the network.

16. The intelligent network of claim 15, wherein said BG modules at each network layer:

decompose tasks commands into subtask commands;

input commands and priorities from other BG modules at a higher network layer, evaluations from VA modules, and information regarding past, present, and predicted future states of said network environment from CWM modules;

provide subtask commands to BG modules at lower network layers; and

provide status reports regarding current and future states of the network and network environment to the CWM modules.

17. The intelligent network of claim 7, wherein said VA modules determine importance, risk, and probability associated with events and actions involved in said intelligent network.

18. The intelligent network of claim 17, wherein said VA modules:

evaluates observed states of said network and network environment and hypothesized plans;

costs, risks, and benefits are computed for the observed state and said hypothesized plans,

probability and correctness of state variables are determined;

credibility and uncertainty values are assigned to said state variables; and

said evaluated plans are sent to said BG module for subsequent selection.

19. A method of providing intelligence to a network having a plurality of network layers, at each layer said method comprising:

a) establishing goals to be performed by a first layer;

b) providing input to a database storing information regarding the network and network environment;

c) hypothesizing plans to accomplish said goals at said first layer;

d) predicting results of said hypothesized plans;

e) evaluating said predicted results;

f) selecting plans with the highest evaluations for execution;

g) updating said database;

h) sending an output response to at least one of a superior and subordinate layer to said first layer;

i) repeating steps a through h for all of the network layers; and

j) executing said selected plans.

20. The method of claim 19, further comprising:

monitoring said selected plans; and

modifying said selected plans as required.

21. The method of claim 19, further comprising:

defining a plurality of tasks defining said selected plans.

22. The method of claim 21, further comprising:

decomposing said plurality of tasks into subtasks that become task commands for a subordinate network layer.

23. The method of claim 22, further comprising:

providing feedback regarding completion of said tasks and subtasks from subordinate network layers up to superior network layers.

24. A system architecture, comprising:

a plurality of functional layers for providing respective functions within a hierarchy of functions, each of said functional layers including a respective agent for vertically propagating information between hierarchically adjacent layers, each of said functional layers including at least one element for implementing at least one respective layer function;

wherein

each functional layer agent, in response to a respective task-indicative subset of said vertically propagated information, horizontally propagating to respective functional layer elements at least that information necessary to perform an indicated task; and

each functional layer agent vertically propagating information pertaining to said indicated task.

25. The system architecture of claim 24, wherein:

in the case of a multiple layer task, each of said plurality of functional layers responding to a respective task-indicative subset of propagated information associated with said multiple layer task.

26. The system architecture of claim 24, wherein said system architecture defines an intelligent communications system to provide an automated network planning function.

27. The system architecture of claim 26, wherein said automated network planning function comprises an intelligent network management for optimal utilization of network resources.

28. A system architecture, comprising:

a plurality of functional layers for providing respective functions within a hierarchy of functions, each of said functional layers including a respective agent for vertically propagating information between hierarchically adjacent layers, each of said functional layers including at least one element for implementing at least one respective layer function;

wherein

each functional layer agent, in response to a respective task-indicative subset of said vertically propagated information, horizontally propagating to respective functional layer elements at least that information necessary to perform an indicated task; and

each functional layer agent vertically propagating information pertaining to said indicated task.

29. A method of managing a communication network, comprising:

establishing a plurality of traffic matrices arranged in a temporally hierarchical order, each of said traffic matrices comprising a corresponding plurality of elements for storing risk probability data associated with respective traffic parameters;

adapting an operating parameter of said communications network in response to changes in traffic patterns associated with risk probability as a function of time.

30. The method of claim 29, wherein said risk probability data associated with respective traffic patterns comprises traffic distribution data.

31. A system, comprising:

a plurality of functional layers for providing respective functions within a hierarchy of functions, each of said functional layers including a respective plurality of functional elements, each of said functional elements being associated with one of a plurality of element types;

wherein

each of said functional elements communicates horizontally with functional element within the same functional layer and communicates vertically with functional elements of the same type within hierarchically adjacent functional layers, said horizontal communications being processed by said functional elements in a manner tending to improve at least one of an individual element function and a system function.

32. The system of claim 31, wherein said vertical communication includes facilitating communications between functional elements of the same type within hierarchically nonadjacent functional layers.

33. The system of claim 31, wherein said system function comprises at least one of a network organizational hierarchy model and a network behavioral hierarchy model.

34. The system of claim 31, wherein each functional element comprises:

a communications system model, for storing data indicative of a hierarchical model of a system within which the functional element operates, said communications system model being updated in response to input events and changes in value assessments.

35. The system of claim 34, wherein each functional element further comprises:

an input processing module to processes observed input events and predicted input to responsively produce perceived situation data, said predicted input provided by said communications system model;

a value assessment module, to process said perceived situation data and plan result data to responsively produce plan evaluation data, said plan result data provided by said communications system model; and

a behavioral generation module, to process said plan evaluation data to responsively produce a command adapted to be execution by an entity other than the functional element.