Implementing disaster recovery based on weather forecasting data

Patent metadata

Field	Value
Publication number	US-2025306240-A1
Application number	US-202418624330-A
Country	US
Kind code	A1
Filing date	Apr 2, 2024
Priority date	Apr 2, 2024
Publication date	Oct 2, 2025
Grant date	—

Abstract

Described are techniques for implementing disaster recovery. Weather forecasting data (e.g., prediction of temperature, wind speed, wind direction, etc.) for a first location (e.g., data center) is received. A prediction of the likelihood of the future severe weather event occurring at the first location where a workload is running that necessitates disaster recovery is generated based on the received weather forecasting data using a model trained to predict the likelihood of future severe weather events occurring at the first location using weather forecasting data. A determination is then made as to whether to implement disaster recovery, which involves the transfer of the processing of the workload performed at the first location to a second location based on such a prediction. For example, such a prediction, which may correspond to a value, is compared to a threshold value, in order to determine whether to implement disaster recovery.

First claim

1 . A computer-implemented method for implementing disaster recovery, the method comprising:
receiving weather forecasting data pertaining to a first location; generating a prediction of a likelihood of a future severe weather event occurring at the first location where a workload is running that necessitates disaster recovery based on the received weather forecasting data using a model trained to predict future severe weather events at the first location; and determining whether to transfer processing of the workload from the first location to a second location based on the prediction.

2 . The method as recited in claim 1 , wherein the prediction corresponds to a value, wherein the processing of the workload is transferred from the first location to the second location in response to the prediction exceeding a threshold value.

3 . The method as recited in claim 1 , wherein the first location corresponds to a first data center, wherein the second location corresponds to a second data center.

4 . The method as recited in claim 1 , wherein the prediction corresponds to a value, wherein the method further comprises:
generating a runbook using generative artificial intelligence in response to the prediction exceeding a threshold value, wherein the runbook comprises instructions for transferring the processing of the workload from the first location to the second location; and transferring the processing of the workload from the first location to the second location in accordance with the runbook.

5 . The method as recited in claim 1 further comprising:
training a generative artificial intelligence model to generate a runbook providing instructions for transferring the processing of the workload from the first location to the second location based on system architectures of data centers located at the first and second locations, and backup operations procedures.

6 . The method as recited in claim 1 further comprising:
training the model to predict future severe weather events occurring at the first location that necessitates disaster recovery based on training data consisting of situations requiring disaster recovery at the first location based on weather forecasting data for the first location.

7 . The method as recited in claim 1 , wherein the weather forecasting data comprises a prediction of one or more of the following to occur at a future time at the first location from the group consisting of: temperature, precipitation, humidity, wind speed, wind direction, cloud coverage, and air pressure.

8 . A computer program product for implementing disaster recovery, the computer program product comprising one or more computer readable storage mediums having program code embodied therewith, the program code comprising programming instructions for:
receiving weather forecasting data pertaining to a first location; generating a prediction of a likelihood of a future severe weather event occurring at the first location where a workload is running that necessitates disaster recovery based on the received weather forecasting data using a model trained to predict future severe weather events at the first location; and determining whether to transfer processing of the workload from the first location to a second location based on the prediction.

9 . The computer program product as recited in claim 8 , wherein the prediction corresponds to a value, wherein the processing of the workload is transferred from the first location to the second location in response to the prediction exceeding a threshold value.

10 . The computer program product as recited in claim 8 , wherein the first location corresponds to a first data center, wherein the second location corresponds to a second data center.

11 . The computer program product as recited in claim 8 , wherein the prediction corresponds to a value, wherein the program code further comprises the programming instructions for:
generating a runbook using generative artificial intelligence in response to the prediction exceeding a threshold value, wherein the runbook comprises instructions for transferring the processing of the workload from the first location to the second location; and transferring the processing of the workload from the first location to the second location in accordance with the runbook.

12 . The computer program product as recited in claim 8 , wherein the program code further comprises the programming instructions for:
training a generative artificial intelligence model to generate a runbook providing instructions for transferring the processing of the workload from the first location to the second location based on system architectures of data centers located at the first and second locations, and backup operations procedures.

13 . The computer program product as recited in claim 8 , wherein the program code further comprises the programming instructions for:
training the model to predict future severe weather events occurring at the first location that necessitates disaster recovery based on training data consisting of situations requiring disaster recovery at the first location based on weather forecasting data for the first location.

14 . The computer program product as recited in claim 8 , wherein the weather forecasting data comprises a prediction of one or more of the following to occur at a future time at the first location from the group consisting of: temperature, precipitation, humidity, wind speed, wind direction, cloud coverage, and air pressure.

15 . A system, comprising:
a memory for storing a computer program for implementing disaster recovery; and a processor connected to the memory, wherein the processor is configured to execute program instructions of the computer program comprising:
receiving weather forecasting data pertaining to a first location;
generating a prediction of a likelihood of a future severe weather event occurring at the first location where a workload is running that necessitates disaster recovery based on the received weather forecasting data using a model trained to predict future severe weather events at the first location; and
determining whether to transfer processing of the workload from the first location to a second location based on the prediction.

16 . The system as recited in claim 15 , wherein the prediction corresponds to a value, wherein the processing of the workload is transferred from the first location to the second location in response to the prediction exceeding a threshold value.

17 . The system as recited in claim 15 , wherein the first location corresponds to a first data center, wherein the second location corresponds to a second data center.

18 . The system as recited in claim 15 , wherein the prediction corresponds to a value, wherein the program instructions of the computer program further comprise:
generating a runbook using generative artificial intelligence in response to the prediction exceeding a threshold value, wherein the runbook comprises instructions for transferring the processing of the workload from the first location to the second location; and transferring the processing of the workload from the first location to the second location in accordance with the runbook.

19 . The system as recited in claim 15 , wherein the program instructions of the computer program further comprise:
training a generative artificial intelligence model to generate a runbook providing instructions for transferring the processing of the workload from the first location to the second location ba

Assignees

• IBM

Inventors

• Saha Shyamal Kuhar
• Deshpande Amit
• Anand Vishal
• Mangla Utpal

Classifications

• G01W1/10 Primary

  Devices for predicting weather conditions (computers per se G06; display devices G09) · CPC title