Transaction-enabled systems to forecast a forward market value and adjust an operation of a task system in response
A transaction-enabling system is disclosed. The system may include a controller to interpret a behavioral data source and a resource utilization requirement for a task system having at least one of a compute task, a network task, or a core task. The controller may then operate a machine to forecast a forward market value for a resource in response to the resource utilization requirement and the behavioral data source. The controller then adjusts an operation of the task system or executes a transaction in response to the forecast of the forward market value for the resource.
1. A system, comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the system to:
interpret a resource utilization requirement for a task system having at least one of: a compute task, a network task, or a core task, the resource utilization requirement including a first resource, the resource utilization requirement including at least one of: a compute resource, a network bandwidth resource, a spectrum resource, a data storage resource, an energy resource, or an energy credit resource, wherein the data storage resource is a digital data storage resource;
interpret a behavioral data source;
operate a machine learning component, wherein the machine learning component is configured to:
forecast a forward market value for a resource in response to the resource utilization requirement and the behavioral data source, the resource of the forward market value including at least one of: the first resource, or a second resource that can be substituted for the first resource,
wherein the first resource is the data storage resource, and
wherein the second resource is the compute resource;
determine to adjust, using an iteratively trained model, an operation of the task system to substitute utilization of the data storage resource for utilization of the compute resource in response to the forecast of the forward market value for the resource; and
update the iteratively trained model used to adjust the operation of the task system based on feedback that the machine learning component receives related to attributes of the iteratively trained model and an outcome of the iteratively trained model; and
adjust the operation of the task system to substitute utilization of the data storage resource for utilization of the compute resource by changing a process of the task system to operate a less efficient algorithm that results in increased data storage but reduced computing.
2. The system of claim 1 , wherein the forward market value for the resource comprises a forward market for the compute resource.
3. The system of claim 2 , wherein the behavioral data source comprises an automated agent behavioral data source.
4. The system of claim 2 , wherein the behavioral data source comprises a human behavioral data source.
5. The system of claim 2 , wherein the behavioral data source comprises a business entity behavioral data source.
6. The system of claim 1 , wherein the forward market value for the resource comprises a forward market for the data storage resource.
7. The system of claim 6 , wherein the behavioral data source comprises an automated agent behavioral data source.
8. The system of claim 6 , wherein the behavioral data source comprises a human behavioral data source.
9. The system of claim 6 , wherein the behavioral data source comprises a business entity behavioral data source.
10. The system of claim 1 , wherein the instructions, when executed by the one or more processors, further cause the system to:
operate the machine learning component to determine a substitution cost of the second resource; and
perform the adjusting the operation of the task system further in response to the substitution cost of the second resource.
11. The system of claim 10 , wherein the machine learning component is further configured to determine at least a portion of the substitution cost of the second resource as an operational change cost for the task system.
12. The system of claim 1 , wherein the instructions, when executed by the one or more processors, further cause the system to execute a transaction, wherein the transaction comprises at least one of purchasing or selling one of the first resource or the second resource on a market for at least one of the first resource or the second resource.
13. The system of claim 12 , wherein the transaction further comprises at least one of purchasing or selling the resource on a market for the resource.
14. The system of claim 13 , wherein the market for the resource comprises a forward market for the resource.
15. The system of claim 13 , wherein the market for the resource comprises a spot market for the resource.
16. The system of claim 1 , wherein the instructions, when executed by the one or more processors, further cause the system to perform executing a transaction in response to the forecast of the forward market value for the resource.
17. The system of claim 1 , wherein the adjusting the operation of the task system further comprises adjusting operations of the task system to time shift at least a portion of the resource utilization requirement.
18. The system of claim 1 , wherein:
the first resource is a first type of resource; and
the second resource is a second type of resource that is different from the first type of resource.
19. The system of claim 1 , wherein the machine learning component is further configured to determine to adjust, using the iteratively trained model, the operation of the task system to directly substitute utilization of the first resource for utilization of the second resource in response to the forecast of the forward market value for the resource.
20. The system of claim 1 , wherein the machine learning component includes a robotic process automation component that is trained by a training data set created by observing interactions with graphical user interfaces of one or more computer programs used to manage an energy management facility.
21. A method, comprising:
interpreting a resource utilization requirement for a task system having at least one of a compute task, a network task, or a core task, the resource utilization requirement including a first resource,
wherein the resource utilization requirement includes at least one resource type including at least one of: a compute resource, a network bandwidth resource, a spectrum resource, a data storage resource, an energy resource, or an energy credit resource, wherein the data storage resource is a digital data storage resource;
interpreting a behavioral data source;
forecasting, by a machine learning component, a forward market value for a resource in response to the resource utilization requirement and the behavioral data source, the resource of the forward market value including at least one of: the first resource, or a second resource that can be substituted for the first resource, the first resource having a different resource type from the second resource,
wherein the first resource is the data storage resource and the second resource is the compute resource;
determining to adjust, by the machine learning component, an operation of the task system to substitute utilization of the data storage resource for utilization of the compute resource in response to the forecast of the forward market value for the resource;
adjusting the operation of the task system to substitute utilization of the data storage resource for utilization of the compute resource by changing a process of the task system to operate an algorithm requiring increased data storage but reduced computing; and
updating, by the machine learning component, an iteratively trained model used to adjust the operation of the task system based on feedback that the machine learning component receives related to attributes of the iteratively trained model and an outcome of the iteratively trained model.
22. The method of claim 21 , further comprising:
determining a substitution cost of the second resource; and
performing the adjusting the operation of the task system further in response to the substitution cost of the second resource.
23. The method of claim 21 , further comprising:
executing a transaction,
wherein the transaction comprises at least one of: purchasing or selling one of the first resource or the second resource on a market for at least one of the first resource or the second resource.
24. The method of claim 21 , wherein the adjusting the operation of the task system further comprises adjusting operations of the task system to time shift at least a portion of the resource utilization requirement.
25. The method of claim 21 , further comprising determining to adjust, using the iteratively trained model, the operation of the task system to directly substitute utilization of the first resource for utilization of the second resource in response to the forecast of the forward market value for the resource.
26. The method of claim 21 , wherein the machine learning component includes a robotic process automation component that is trained by a training data set created by observing interactions with graphical user interfaces of one or more computer programs used to manage an energy management facility.
27. The method of claim 21 , wherein the algorithm is a less efficient algorithm than a first algorithm operated by the process of the task system prior to substitution of the data storage resource for the compute resource.
28. A system, comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the system to:
interpret a resource utilization requirement for a task system having at least one of: a compute task, a network task, or a core task, the resource utilization requirement including a first resource, the resource utilization requirement including at least one of: a compute resource, a network bandwidth resource, a spectrum resource, a data storage resource, an energy resource, or an energy credit resource, wherein the data storage resource is a digital data storage resource;
interpret a behavioral data source;
operate a machine learning component, wherein the machine learning component is configured to:
forecast a forward market value for a resource in response to the resource utilization requirement and the behavioral data source, the resource of the forward market value including at least one of: the first resource, or a second resource that can be substituted for the first resource,
wherein the first resource is the compute resource and the second resource is the data storage resource;
determine to adjust, using an iteratively trained model, an operation of the task system to substitute utilization of the compute resource for utilization of the data storage resource in response to the forecast of the forward market value for the resource; and
update the iteratively trained model used to adjust the operation of the task system based on feedback that the machine learning component receives related to attributes of the iteratively trained model and an outcome of the iteratively trained model; and
adjust the operation of the task system to substitute utilization of the compute resource for utilization of the data storage resource by changing a process of the task system to operate a more efficient algorithm that results in decreased data storage but increased computing.
29. The system of claim 28 , wherein the forward market value for the resource comprises a forward market for the compute resource.
30. The system of claim 29 , wherein the behavioral data source comprises at least one of an automated agent behavioral data source, a human behavioral data source, or a business entity behavioral data source.
31. The system of claim 28 , wherein the forward market value for the resource comprises a forward market for the data storage resource.
32. The system of claim 31 , wherein the behavioral data source comprises at least one of an automated agent behavioral data source, a human behavioral data source, or a business entity behavioral data source.
33. The system of claim 31 , wherein the instructions, when executed by the one or more processors, further cause the system to:
operate the machine learning component to determine a substitution cost of the second resource; and
perform the adjusting the operation of the task system further in response to the substitution cost of the second resource.
34. The system of claim 33 , wherein the machine learning component is further configured to determine at least a portion of the substitution cost of the second resource as an operational change cost for the task system.
35. The system of claim 33 , wherein: the instructions, when executed by the one or more processors, further cause the system to execute a transaction, wherein the transaction comprises at least one of purchasing or selling one of the first resource or the second resource on a market for at least one of the first resource or the second resource.