Distributed computation system incorporating agent network, paths and associated probes

• US 9,577,911 B1
• Filed: 03/21/2016
• Issued: 02/21/2017
• Est. Priority Date: 03/21/2016
• Status: Expired due to Fees

• Current Assignee: Black Cloud Analytics, Inc.
• Original Assignee: Black Cloud Analytics, Inc.
• Inventors: Castleman, Robert L.
• Primary Examiner(s): Lai, Michael C
• Application Number:
  US15/076,604
• Time in Patent Office: 337 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/30 Monitoring
• CPC Class Codes: G06F 2209/5017 Task decomposition
• CPC Class Codes: G06F 9/46 Multiprogramming arrangements
• CPC Class Codes: G06F 9/5038 considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration scheduling strategies G06F9/4881 and subgroups
• CPC Class Codes: H04L 41/046 comprising network management agents or mobile agents therefor
• CPC Class Codes: H04L 41/142 using statistical or mathematical methods
• CPC Class Codes: H04L 41/22 comprising specially adapted graphical user interfaces [GUI]
• CPC Class Codes: H04L 43/12 Network monitoring probes
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/34 involving the movement of software or configuration parameters network booting or remote initial program loading [RIPL] G06F9/4416

Abstract

A system and method of distributed computation based upon a novel partitioning of computer networks. In the distributed computing system of the present invention, instructions are disseminated to select agents on a computer network, each of which is a member of at least one “path,” a path being an ordered set of one or more connected agents within the network. The computation is then performed by the agents along the path, and any results then returned. A computation to be performed is broken down into instructions executed on a unique ordered sequence of agents making up a path. This vastly increases the expressive power of a single network to be not only the sum of its parts, but the sum of all possible configurations of those parts on a graph. The basic components of the computing system are agents, probes and paths. The agents are interconnected forming a network and a path is an ordered sequence of agents. Information is exchanged between agents by the sending and receiving of probes between the agents in the network.

Claims

1. A distributed computing system, comprising:

a plurality of interconnected host computing devices one or more of which are in communication with a control mechanism;

a plurality of agents, each agent implemented on a host computing device wherein each host computing device is operative to implement one or more agents, each agent in communication with neighboring agents on a defined ordered path thereby forming a distributed computing network and operative to receive, process and dispatch probes among said agents;

wherein probes are generated by agents and said control mechanism, contain data and/or code, and traverse said distributed computing network in accordance with one or more defined ordered paths, each path consisting of a unique ordered sequence of connected agents;

each agent comprising;

one or more probe queues operative to receive and hold probes for processing by a respective agent;

at least one task to be performed by said respective agent;

wherein communication among agents occurs only through an exchange of probes on a path;

wherein information is exchanged among agents, and tasks are distributed to agents in a particular path by sending and receiving probes among the agents in the particular path; and

wherein a computation is broken down into a sequence of tasks distributed via probes to agents along the particular path, the computation performed by combined action of all agents on the particular path.

2. The system according to claim 1, wherein each agent further comprises host metrics including at least one of data and functions that define a current state of an agent'"'"'s host.

3. The system according to claim 1, wherein agent and probe IDs are managed utilizing one or more lists on an agent or probe.

4. The system according to claim 1, wherein each agent further comprises:

a fitness indication operative to represent an agent'"'"'s overall health; and

a fitness function operative to manage the fitness of an agent.

5. The system according to claim 1, wherein each probe further comprises a path comprising a sequence of values specifying vertices visited by a particular probe, wherein each value specifies a vertex representing a location of an agent in a graph.

6. The system according to claim 1, wherein each probe further comprises a payload consisting of at least one of data, data structure, executable code, agent and/or probe.

7. The system according to claim 1, wherein each probe further comprises a type consisting of an identifier used to encapsulate specific behavior of said probe.

8. The system according to claim 1, wherein each probe further comprises an ownership field indicating which agent owns the particular probe.

9. The system according to claim 1, wherein each host may comprise at least one of a physical device, virtual device and software.

10. The system according to claim 1, wherein said one or more probe queues comprises a general queue operative to receive probes of any type and process probes in a predetermined order.

11. The system according to claim 1, wherein said one or more probe queues comprises a control queue operative to receive and process control probes.

12. The system according to claim 1, wherein said one or more probe queues comprises a message queue operative to store message probes received by an agent.

13. The system according to claim 1, wherein said one or more probe queues comprises an inactive queue operative to store probes deactivated by an agent, wherein probes in said inactive queue are deactivated, reactivated or destroyed by an agent based on at least one of a state of the agent and a directive issued by said control mechanism.

14. The system according to claim 1, wherein said control mechanism is operative to host any or all of a user interface, zero or more databases for data collected by said agents and software for implementing visualization and analytics functions.

15. The system according to claim 1, wherein said plurality of agents and said probes are configured to generate one or more deterministic logic circuits.

16. The system according to claim 1, wherein said plurality of agents and said probes are configured to generate one or more Turing machines.

17. A method of distributed computing, the method comprising:

providing a plurality of interconnected host computing devices one or more of which are in communication with a control mechanism;

providing a plurality of agents, each agent implemented on a host computing device wherein each host computing device is operative to implement one or more agents, each agent in communication with neighboring agents on a defined ordered path thereby forming a distributed computing network;

receiving, processing and dispatching probes containing at least one of data, object code and source code among said agents, wherein probes are generated by said agents, contain data and/or code, and traverse said distributed computing network in accordance with one or more defined ordered paths, each path consisting of a unique ordered sequence of agents;

wherein communication among agents occurs only through an exchange of probes on a path;

breaking down a computation into a sequence of tasks to be performed by the agents on a path, the computation performed by combined action of all agents on the path;

wherein information is exchanged among agents, and said tasks are distributed to agents in a particular path by sending and receiving probes among the agents in the particular path;

performing said computation by the agents within the particular path and returning any results;

controlling said distributed computing network utilizing said control mechanism in communication with at least one agent; and

generating control probes and injecting said control probes into said distributed computing network via an agent in communication with said control mechanism.