IP Library Granted Patent US 12,619,476
Granted Patent B2
US 12,619,476 · App. 18/215,534 · Granted May 5, 2026

Optimization of cloud egress tasks

Inventors: Dharma Teja Atluri (Hyderabad, IN); Neelamadhav Gantayat (Bangalore, IN); Avirup Saha (Kolkata, IN); Sampath Dechu (Acton, MA)
Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
G06F9/5083G06F9/48G06F9/4806G06F9/4843G06F9/4881G06F9/50G06F9/5061G06F9/5072
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,619,476
App. No.
18/215,534
Granted
May 5, 2026
Kind
B2
Abstract

An embodiment includes computing a computational cost of a job, using a first machine learning algorithm. The job may include an original amount of an egress of data from a cloud computing environment. The embodiment includes determining, using a second machine learning algorithm, the amount of the egress of data corresponding to the job has a computer business criticality that exceeds a threshold level of business criticality. The embodiment includes analyzing a current egress plan used in computing the computational cost of the job. The embodiment includes reconfiguring the current plan to a second egress plan to reduce the computational cost of the job. The embodiment includes implementing a second plan such responsive to execution of the job, the second plan causes data egress behavior to change from the original egress of data behavior. A modified egress behavior causes an effective reduction in the egress cost of the job.

Claims (36)

1 . A computer-implemented method comprising:

computing a computational cost of a job, using a first machine learning component, the job comprising an original amount of an egress of data from a cloud computing environment;

determining, using a second machine learning component, the amount of the egress of data corresponding to the job has a computed criticality that exceeds a threshold level of criticality for a cycle wherein the computed criticality comprises computing an impact of the amount of the egress of data corresponding to the job from the cloud computing environment for the cycle;

responsive to the amount of the egress of data corresponding to the job has the computed criticality that exceeds the threshold level of criticality for the cycle, causing to keep a current egress plan or to reconfigure the current egress plan to a second egress plan, analyzing a current egress plan used in computing the cost of the job and reconfiguring the current egress plan to the second egress plan to reduce an egress cost of the job; and

implementing a second plan such that responsive to execution of the job, the second plan causes data egress behavior to change from the original egress of data behavior, wherein a modified egress behavior causes an effective reduction in the egress cost of the job.

2 . The computer-implemented method of claim 1 , wherein the first machine learning component takes into account historical data and a set of user defined factors.

3 . The computer-implemented method of claim 1 , wherein reconfiguring the current plan comprises an alternate time for the job.

4 . The computer-implemented method of claim 1 , wherein the first machine learning component comprises historical data stored in a job repository comprising a priority and an impact.

5 . The computer-implemented method of claim 1 , further comprising comparing the original egress of data job to a threshold of the criticality.

6 . The computer-implemented method of claim 1 , further comprising optimizing the cost the computational cost in relation to a threshold of the criticality.

7 . The computer-implemented method of claim 1 , wherein the second egress plan comprises predicting the impact wherein predicting the impact is based on seasonality and revenue of past jobs in the cycle.

8 . The computer-implemented method of claim 1 , wherein the second egress plan comprises an alternative cloud storage provider.

9 . The computer-implemented method of claim 1 , further comprising providing an option to choose the original egress of data job or the second egress plan wherein the second egress plan having an excess cost over the original egress of data job is chosen.

10 . A computer program product comprising one or more computer readable storage medium, and program instructions collectively stored on the one or more computer readable storage medium, the program instructions executable by a processor to cause the processor to perform operations comprising:

computing a computational cost of a job, using a first machine learning component, the job comprising an original amount of an egress of data from a cloud computing environment;

determining, using a second machine learning component, the amount of the egress of data corresponding to the job has a computed criticality that exceeds a threshold level of criticality for a cycle wherein the computed criticality comprises computing an impact of the amount of the egress of data corresponding to the job from the cloud computing environment for the cycle;

responsive to the amount of the egress of data corresponding to the job has the computed criticality that exceeds the threshold level of criticality for the cycle, causing to keep a current egress plan or to reconfigure the current egress plan to a second egress plan, analyzing a current egress plan used in computing the cost of the job and reconfiguring the current egress plan to the second egress plan to reduce an egress cost of the job; and

implementing a second plan such that responsive to execution of the job, the second plan causes data egress behavior to change from the original egress of data behavior, wherein a modified egress behavior causes an effective reduction in the egress cost of the job.

11 . The computer program product of claim 10 , wherein the stored program instructions are stored in a computer readable storage device in a data processing system, and wherein the stored program instructions are transferred over a network from a remote data processing system.

12 . The computer program product of claim 10 , wherein the stored program instructions are stored in a computer readable storage device in a server data processing system, and wherein the stored program instructions are downloaded in response to a request over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system, further comprising:

comparing the original amount of egress of data job to a threshold of the criticality.

13 . The computer program product of claim 10 , wherein the stored program instructions are stored in a computer readable storage device in a server data processing system, and wherein the stored program instructions are downloaded in response to a request over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system, further comprising:

providing an option to choose the original amount of the egress of data job or the second egress plan wherein the second egress plan having an excess cost over the original egress of data job is chosen.

14 . The computer program product of claim 10 , wherein the stored program instructions are stored in a computer readable storage device in a server data processing system, and wherein the stored program instructions are downloaded in response to a request over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system, further comprising:

optimizing the computation cost in relation to a threshold of the criticality.

15 . The computer usable program product of claim 13 , wherein the computer usable code is stored in a computer readable storage device in a server data processing system, and wherein the computer usable code is downloaded over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system.

16 . A computer system comprising a processor and one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by the processor to cause the processor to perform operations comprising:

computing a computational cost of a job, using a first machine learning component, the job comprising an original amount of an egress of data from a cloud computing environment;

determining, using a second machine learning component, the amount of the egress of data corresponding to the job has a computed criticality that exceeds a threshold level of criticality for a cycle wherein the computed criticality comprises computing an impact of the amount of the egress of data corresponding to the job from the cloud computing environment for the cycle;

responsive to the amount of the egress of data corresponding to the job has the computed criticality that exceeds the threshold level of criticality for the cycle, causing to keep a current egress plan or to reconfigure the current egress plan to a second egress plan, analyzing a current egress plan used in computing the cost of the job and reconfiguring the current egress plan to the second egress plan to reduce an egress cost of the job; and

implementing a second plan such that responsive to execution of the job, the second plan causes data egress behavior to change from the original egress of data behavior, wherein a modified egress behavior causes an effective reduction in the egress cost of the job.

17 . The computer system of claim 16 , wherein the first machine learning component takes into account historical data and a set of user defined factors.

18 . The computer system of claim 16 , wherein reconfiguring the current plan comprises an alternate time for the job.

19 . The computer system of claim 16 , further comprising:

further comprising optimizing the cost in relation to a threshold of the criticality.

20 . The computer system of claim 16 , further comprising providing an option to choose the original egress of data job or the second egress plan wherein the second egress plan having an excess cost over the original egress of data job is chosen.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 28, 2023
From: ATLURI, DHARMA TEJA; GANTAYAT, NEELAMADHAV; SAHA, AVIRUP; DECHU, SAMPATH
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 064099/0276 →
Continuity (1)
Related Publication 20250004860A1 · Jan 2, 2025
References Cited (23)
US 8171115B2 · Hamilton · 2012 [cited by examiner]
US 10666702B1 · Nielsen · 2020 [cited by examiner]
US 11929838B1 · Singhal · 2024 [cited by examiner]
US 20170366467A1 · Martin · 2017 [cited by examiner]
US 20210203587A1 · Sidebottom · 2021 [cited by examiner]
US 20220100578A1 · Moreira Martins · 2022 [cited by examiner]
US 20220210075A1 · Musleh · 2022 [cited by examiner]
US 20220374276A1 · Mitra · 2022 [cited by examiner]
US 20230284083A1 · Tesanovic · 2023 [cited by examiner]
Liu et al., Cost- and Throughput-aware Bulk Data Replication in the Cloud, Dec. 16, 2022. [cited by applicant]
Nops, Understanding AWS Egress Costs and How to Avoid Them, 2023, https://www.nops.io/aws-egress-costs-and-how-to-avoid/. [cited by applicant]
Shaer et al., Efficient execution plan for egress traffic engineering, Computer Networks, vol. 190, May 8, 2021. [cited by applicant]
Faction, Cloud Egress Charges: How to Prevent These Creeping Costs, Jul. 12, 2021, https://www.factioninc.com/blog/it-challenges/egress-charges-how-to-prevent-costs/. [cited by applicant]
Smith, Comparing Data Egress Fees Among Cloud Providers, Jan. 31, 2022, https://www.hostdime.com/blog/data-egress-fees-cloud/. [cited by applicant]
Jain et al., Skyplane: Optimizing Transfer Cost and Throughput Using Cloud-Aware Overlays, Oct. 13, 2022. [cited by applicant]
Jiang et al., A Cloud-Agnostic Framework to Enable Cost-Aware Scheduling of Applications in a Multi-Cloud Environment, NOMS 2020—2020 IEEE/IFIP Network Operations and Management Symposium, Apr. 20-24, 2020. [cited by applicant]
Shmookler et al., Calculate AWS Egress Fees Proactively for VMware Cloud on AWS, Apr. 16, 2018. [cited by applicant]
Techtarget, Finally, a Path to Reducing Public Cloud Egress Fees, 2023, https://www.techtarget.com/searchcloudcomputing/MulticloudStrategy/Finally-a-Path-to-Reducing-Public-Cloud-Egress-Fees. [cited by applicant]
Mcguinness, Four Easy Ways to Lower Your Microsoft Azure Egress Fees, Mar. 18, 2022, https://www.megaport.com/blog/four-easy-ways-to-lower-your-microsoft-azure-egress-fees/. [cited by applicant]
Xu et al., Resource Allocation vs. Business Process Improvement: How They Impact on Each Other, Sep. 2008. [cited by applicant]
11:11 Systems, “Leading Automation. Optimizing Performance”, available online at <https://web.archive.org/web/20220406103237/https://1111systems.com/>, Apr. 6, 2022, 3 pages. [cited by applicant]
James, Orme, “Size of aws data transfer-costs-revealed-in-leaked-internal-documents”, available online at <https://www.techerati.com/news-hub/size-of-aws-data-transfer-costs-revealed-in-leaked-internal-documents/>, Oct.… [cited by applicant]
McKendrick et al., “Cloud computing sticker shock is now a monthly occurrence at many companies”, available online at <https://www.zdnet.com/article/cloud-computing-sticker-shock-is-now-a-monthly-occurrence-for-many-com… [cited by applicant]