Recommending waste reductions and credit purchases for business units

• US 7,873,552 B2
• Filed: 08/30/2007
• Issued: 01/18/2011
• Est. Priority Date: 08/30/2007
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Franco, Lucas Goncalves, Campo, Camilo Yamauchi, Leitão, Breno Henrique, dos Santos Moschetta, Wainer
• Primary Examiner(s): Trammell; James P
• Assistant Examiner(s): MILEF, ELDA G
• Application Number:
  US11/847,417
• Publication Number:
  US 20090063231A1
• Time in Patent Office: 1,237 Days
• Field of Search: 705 35- 40, 705/30, 705/7, 705/1
• US Class Current: 705/30
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/0631 Resource planning, allocation, distributing or scheduling for enterprises or organisations
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G06Q 40/12 Accounting
• CPC Class Codes: G06Q 50/04 Manufacturing
• CPC Class Codes: Y02P 90/30 Computing systems specially adapted for manufacturing

Abstract

In an embodiment, revenue loss functions associated with business units are determined and waste credit constraints associated with the business units are received. A recommended waste credit purchase amount and recommended waste credit reduction amounts associated with the business units are calculated by minimizing a sum of the revenue loss functions and a purchase function, subject to the waste credit constraints, a purchase constraint, and a reduction goal constraint. In various embodiments, the recommended waste credit purchase amount and the recommended waste credit reduction amounts are presented, the amount of waste credits specified by the recommended waste credit purchase amount are purchased, and the business units reduce their waste emissions by their respective recommended waste credit reduction amounts. In an embodiment, the minimization is perfumed via a quadratic programming algorithm.

Claims

1. A method comprising:

determining using a computer, a plurality of revenue loss functions associated with a plurality of respective business units, wherein the plurality of revenue loss functions calculate an amount of revenue that each of the plurality of respective business units loses from reducing emissions by the plurality of business units and wherein the plurality of revenue loss functions are functions of a plurality of recommended waste credit reduction amounts, wherein the plurality of recommended waste credit reduction amounts are unknown at a time of the determining the plurality of revenue loss functions, and wherein the plurality of revenue loss functions are different for each of the plurality of respective business units, wherein the determining the plurality of revenue loss functions further comprises reading a plurality of historical data associated with the plurality of business units, wherein each of the plurality of historical data comprises historical waste credits saved and associated historical revenue losses that were caused by actions taken to save the historical waste credits and creating the plurality of revenue loss functions that describe a plurality of curves that fit the historical waste credits saved and the historical revenue losses;

receiving a plurality of waste credit constraints associated with the plurality of respective business units;

calculating a recommended waste credit purchase amount and the plurality of recommended waste credit reduction amounts associated with the plurality of respective business units, wherein the calculating further comprises minimizing a sum of the plurality of the revenue loss functions and a purchase function, subject to the waste credit constraints, a purchase constraint, and a reduction goal constraint and storing the recommended waste credit purchase amount in computer memory; and

presenting the recommended waste credit purchase amount and the plurality of recommended waste credit reduction amounts via an output device.

2. The method of claim 1, further comprising:

receiving the reduction goal constraint and the purchase constraint from a user interface.

3. The method of claim 1, wherein the determining the plurality of revenue loss functions further comprises:

creating the plurality of revenue loss functions by a least squares algorithm.

4. The method of claim 1, wherein the determining the plurality of revenue loss functions further comprises:

creating the plurality of revenue loss functions by a basis spline algorithm.

5. The method of claim 1, wherein the minimizing further comprises:

performing a quadratic programming algorithm on the sum of the plurality of the revenue loss functions and the purchase function, subject to the waste credit constraints, the purchase constraint, and the reduction goal constraint.

6. The method of claim 1, further comprising:

purchasing an amount of waste credits specified by the recommended waste credit purchase amount.

7. The method of claim 1, further comprising:

reducing waste emissions from the plurality of business units by the plurality of respective recommended waste credit reduction amounts.

8. A storage medium encoded with instructions, wherein the instructions when executed comprise:

determining a plurality of revenue loss functions associated with a plurality of respective business units, wherein the plurality of revenue loss functions calculate an amount of revenue that each of the plurality of respective business units loses from reducing emissions by the plurality of business units and wherein the plurality of revenue loss functions are functions of a plurality of recommended waste credit reduction amounts, wherein the plurality of recommended waste credit reduction amounts are unknown at a time of the determining the plurality of revenue loss functions, and wherein the plurality of revenue loss functions are different for each of the plurality of respective business units, wherein the determining the plurality of revenue loss functions further comprises reading a plurality of historical data associated with the plurality of business units, wherein each of the plurality of historical data comprises historical waste credits saved and associated historical revenue losses that were caused by actions taken to save the historical waste credits and creating the plurality of revenue loss functions that describe a plurality of curves that fit the historical waste credits saved and the historical revenue losses;

receiving a plurality of waste credit constraints associated with the plurality of respective business units;

determining a purchase function;

calculating a recommended waste credit purchase amount and the plurality of recommended waste credit reduction amounts associated with the plurality of respective business units, wherein the calculating further comprises minimizing a sum of the plurality of the revenue loss functions and the purchase function, subject to the waste credit constraints, a purchase constraint, and a reduction goal constraint and storing the recommended waste credit purchase amount in computer memory; and

presenting the recommended waste credit purchase amount and the plurality of recommended waste credit reduction amounts.

9. The storage medium of claim 8, wherein the determining the plurality of revenue loss functions further comprises:

creating the plurality of revenue loss functions by a least squares algorithm.

10. The storage medium of claim 9, wherein the determining the plurality of revenue loss functions further comprises:

creating the plurality of revenue loss functions by a basis spline algorithm.

11. The storage medium of claim 8, wherein the minimizing further comprises:

performing a quadratic programming algorithm on the sum of the plurality of the revenue loss functions and the purchase function, subject to the waste credit constraints, the purchase constraint, and the reduction goal constraint.

12. The storage medium of claim 8, further comprising:

purchasing an amount of waste credits specified by the recommended waste credit purchase amount.

13. The storage medium of claim 8, further comprising:

reducing waste emissions from the plurality of business units by the plurality of respective recommended waste credit reduction amounts.

14. A computer system comprising:

a processor; and

memory connected to the processor, wherein the memory encodes instructions that when executed by the processor comprise;

determining a plurality of revenue loss functions associated with a plurality of respective business units, wherein the plurality of revenue loss functions calculate an amount of revenue that each of the plurality of respective business units loses from reducing emissions by the plurality of business units and wherein the plurality of revenue loss functions are functions of a plurality of recommended waste credit reduction amounts, wherein the plurality of recommended waste credit reduction amounts are unknown at a time of the determining the plurality of revenue loss functions, and wherein the plurality of revenue loss functions are different for each of the plurality of respective business units, wherein the determining the plurality of revenue loss functions further comprises reading a plurality of historical data associated with the plurality of business units, wherein each of the plurality of historical data comprises historical waste credits saved and associated historical revenue losses that were caused by actions taken to save the historical waste credits and creating the plurality of revenue loss functions that describe a plurality of curves that fit the historical waste credits saved and the historical revenue losses,

receiving a plurality of waste credit constraints associated with the plurality of respective business units,

determining a purchase function,

calculating a recommended waste credit purchase amount and the plurality of recommended waste credit reduction amounts associated with the plurality of respective business units, wherein the calculating further comprises minimizing a sum of the plurality of the revenue loss functions and the purchase function, subject to the waste credit constraints, a purchase constraint, and a reduction goal constraint, and

purchasing an amount of waste credits specified by the recommended waste credit purchase amount.

15. The computer system of claim 14, wherein the determining the plurality of revenue loss functions further comprises:

creating the plurality of revenue loss functions by a least squares algorithm.

16. The computer system of claim 15, wherein the determining the plurality of revenue loss functions further comprises:

creating the plurality of revenue loss functions by a basis spline algorithm.

17. The computer system of claim 14, wherein the minimizing further comprises:

performing a quadratic programming algorithm on the sum of the plurality of the revenue loss functions and the purchase function, subject to the waste credit constraints, the purchase constraint, and the reduction goal constraint.

18. The computer system of claim 14, wherein the instructions further comprise:

reducing waste emissions from the plurality of business units by the plurality of respective recommended waste credit reduction amounts.

19. The computer system of claim 14, wherein the minimizing further comprises:

finding a combination of the plurality of recommended waste credit reduction amounts and the recommended waste credit purchase amount that cause the sum of plurality of the revenue loss functions and the purchase function to achieve a minimum, where the plurality of recommended waste credit reduction amounts meet the plurality of respective waste credit constraints, the recommended waste credit purchase amount meets the purchase constraint, and a sum of the plurality of recommended waste credit reduction amounts and the recommended waste credit purchase amount meets the reduction goal constraint.