# US 2020/0351339 A1 · Method and system for performance-driven load shifting

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0351339 A1
- Document ID: US20200351339A1
- Status: Published application
- Kind: A1
- Application number: 16/403,365
- Filed: 2019-05-03
- Published: 2020-11-05
- Earliest claimed: 2019-05-03
- Assignees: EMC IP Holding Company LLC
- Applicants: EMC IP Holding Company LLC
- Inventors: Amihai Savir; Avitan Gefen; Assaf Natanzon
- Web page: https://patentgrep.com/patent/US20200351339A1

## CPC

- H04L 67/1027: Persistence of sessions during load balancing
- G06F 9/45558: {Hypervisor-specific management and integration aspects}
- H04L 67/55: Push-based network services
- H04L 67/59: Providing operational support to end devices by off-loading in the network or by emulation, e.g. when they are unavailable
- G06F 2009/4557: {Distribution of virtual machine instances; Migration and load balancing}
- G06F 2009/45595: {Network integration; Enabling network access in virtual machine instances}
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method and system for performance-driven load shifting. Specifically, the method and system disclosed herein entail transferring user program workloads, for processing, between local computing resources available on a client device and cloud computing resources available on an offload domain based on the assessed performance score of the client device at any given point in time. Seamless load shifting is further guaranteed due substantively to the employment of a mobile network facilitating communications between the client device and the offload domain.

## Claims

### Claim 1

A method for performance-driven load shifting, comprising:
assessing a first client device performance, associated with a client device, while at least a foreground user program (FUP) is executing on the client device;
making a first determination that the first client device performance is low; and
shifting, based on the first determination, a workload for the FUP to an offload domain.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
prior to assessing the first client device performance:
obtaining client hardware configuration information (HCI) associated with the client device;
differentiating the client HCI against optimal HCI, to obtain gap HCI;
obtaining, respectively, a set of hardware performance scores (HPS) associated with a set of hardware components installed on the client device; and
obtaining a user discontent score (UDS) associated with the client device,
wherein the first client device performance is assessed based on the gap HCI, the HPS, and the UDS.

### Claim 3 (depends on 2)

The method of claim 2, further comprising:
prior to obtaining the client HCI:
identifying the FUP from a task management list (TML);
obtaining FUP metadata describing the FUP using a FUP identifier (ID) associated with the FUP; and
obtaining, based on at least a portion of the FUP metadata, the optimal HCI from a crowdsourcing population database (CPD).

### Claim 4 (depends on 1)

The method of claim 1, wherein the offload domain is a load shifting service (LSS) operatively connected to the client device through a mobile network.

### Claim 5 (depends on 1)

The method of claim 1, wherein shifting the workload for the FUP to the offload domain, comprises:
intercepting a first client input device output relevant to the workload, wherein the first client input device output is associated with a client input device of the client device;
redirecting the first client input device output to a virtual appliance hosted on the offload domain;
receiving, from the offload domain, graphics rendered by the virtual appliance based at least on the first client input device output; and
presenting the graphics to a client device user operating the client device.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
prior to assessing the first client device performance:
generating, of the client device, a client image comprising the FUP and user data relevant to the FUP;
submitting, to the offload domain, at least the client image and optimal hardware configuration information (HCI) for executing the FUP;
receiving, from the offload domain, virtual appliance credentials for the virtual appliance; and
establishing, through the mobile network, a connection to the virtual appliance using the virtual appliance credentials,
wherein the virtual appliance is allocated cloud resources comparable to the optimal HCI and is configured using the client image.

### Claim 7 (depends on 5)

The method of claim 5, further comprising:
assessing a second client device performance, associated with the client device, while at least the FUP is executing on the client device;
making a second determination that the second client device performance is non-low; and
releasing, based on the second determination, a second client input device output relevant to the workload, wherein the second client input device output is associated with the client input device of the client device.

### Claim 8 (depends on 1)

The method of claim 1, wherein shifting the workload for the FUP to the offload domain, comprises:
intercepting a first system call relevant to the workload, wherein the first system call is issued by the FUP;
redirecting the first system call to cloud resources available on the offload domain;
receiving, from the offload domain, a call result derived by the cloud computing resources based at least on the first system call; and
providing the call result to the FUP.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
prior to assessing the first client device performance:
submitting, to the offload domain, at least optimal hardware configuration information (HCI) for executing the FUP;
receiving, from the offload domain, cloud resource credentials for the cloud resources; and
establishing, through the mobile network, a connection to the cloud resources using the cloud resource credentials,
wherein the cloud resources made available are comparable to the optimal HCI.

### Claim 10 (depends on 8)

The method of claim 8, further comprising:
assessing a second client device performance, associated with the client device, while at least the FUP is executing on the client device;
making a second determination that the second client device performance is non-low; and
releasing, based on the second determination, a second system call relevant to the workload, wherein the second system call is issued by the FUP.

### Claim 11

A system, comprising:
a client device comprising a computer processor; and
a load shifting agent (LSA) executing on the computer processor, and programmed to:
assess a client device performance, associated with the client device, while at least a foreground user program (FUP) is further executing on the computer processor;
make a determination that the client device performance is low; and
shift, based on the determination, a workload for the FUP to an offload domain.

### Claim 12 (depends on 11)

The system of claim 11, further comprising:
a load shifting service (LSS) operatively connected to the client device,
wherein the LSS is the offload domain.

### Claim 13 (depends on 12)

The system of claim 12, wherein the client device and the LSS are operatively connected through a mobile network.

### Claim 14

A non-transitory computer readable medium (CRM) comprising computer readable program code, which when executed by a computer processor, enables the computer processor to:
assess a first client device performance, associated with a client device, while at least a foreground user program (FUP) is executing on the client device;
make a first determination that the first client device performance is low; and
shift, based on the first determination, a workload for the FUP to an offload domain.

### Claim 15 (depends on 14)

The non-transitory CRM of claim 14, further comprising computer readable program code, which when executed by the computer processor, enables the computer processor to:
prior to assessing the first client device performance:
obtain client hardware configuration information (HCI) associated with the client device;
differentiate the client HCI against optimal HCI, to obtain gap HCI;
obtain, respectively, a set of hardware performance scores (HPS) associated with a set of hardware components installed on the client device; and
obtain a user discontent score (UDS) associated with the client device,
wherein the first client device performance is assessed based on the gap HCI, the HPS, and the UDS.

### Claim 16 (depends on 15)

The non-transitory CRM of claim 15, further comprising computer readable program code, which when executed by the computer processor, enables the computer processor to:
prior to obtaining the client HCI:
identify the FUP from a task management list (TML);
obtain FUP metadata describing the FUP using a FUP identifier (ID) associated with the FUP; and
obtain, based on at least a portion of the FUP metadata, the optimal HCI from a crowdsourcing population database (CPD).

### Claim 17 (depends on 14)

The non-transitory CRM of claim 14, wherein the offload domain is a load shifting service (LSS) operatively connected to the client device through a mobile network.

### Claim 18 (depends on 14)

The non-transitory CRM of claim 14, further comprising computer readable program code, which when executed by the computer processor, enables the computer processor to:
shift the workload for the FUP to the offload domain, by:
intercepting a first client input device output relevant to the workload, wherein the first client input device output is associated with a client input device of the client device;
redirecting the first client input device output to a virtual appliance hosted on the offload domain;
receiving, from the offload domain, graphics rendered by the virtual appliance based at least on the first client input device output; and
presenting the graphics to a client device user operating the client device.

### Claim 19 (depends on 18)

The non-transitory CRM of claim 18, further comprising computer readable program code, which when executed by the computer processor, enables the computer processor to:
prior to assessing the first client device performance:
generate, of the client device, a client image comprising the FUP and user data relevant to the FUP;
submit, to the offload domain, at least the client image and optimal hardware configuration information (HCI) for executing the FUP;
receive, from the offload domain, virtual appliance credentials for the virtual appliance; and
establish, through the mobile network, a connection to the virtual appliance using the virtual appliance credentials,
wherein the virtual appliance is allocated cloud resources comparable to the optimal HCI and is configured using the client image.

### Claim 20 (depends on 14)

The non-transitory CRM of claim 14, further comprising computer readable program code, which when executed by the computer processor, enables the computer processor to:
shift the workload for the FUP to the offload domain, by:
intercepting a first system call relevant to the workload, wherein the first system call is issued by the FUP;
redirecting the first system call to cloud resources available on the offload domain;
receiving, from the offload domain, a call result derived by the cloud computing resources based at least on the first system call; and
providing the call result to the FUP.
