# US 12,182,449 B2 · Systems and methods for managing a storage system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,182,449 B2 - Document ID: US12182449B2 - Status: Granted - Kind: B2 - Application number: 18/200,249 - Filed: 2023-05-22 - Published: 2023-12-21 - Granted: 2024-12-31 - Earliest claimed: 2022-05-25 - Assignees: Samsung Electronics Co., Ltd. - Applicants: Samsung Electronics Co., Ltd. - Inventors: Qirui Yang; Bridget Davis; Devasena Inupakutika; Adam Manzanares - Web page: https://patentgrep.com/patent/US12182449B2 ## CPC - G06F 3/0659: {Command handling arrangements, e.g. command buffers, queues, command scheduling} - G06F 3/0611: {in relation to response time} - G06F 3/0649: {Lifecycle management} - G06F 3/0685: {Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract One or more embodiments of the present disclosure describe a storage system comprising a first storage medium, a second storage medium, and a controller configured to communicate with the first storage medium and the second storage medium. The controller is configured to receive a first request generated by a process associated with first data; determine that the first data is stored in the first storage medium; generate a signal based on the controller being configured to determine; identify a criterion based on the signal; select, based on the criterion, at least one of a first procedure or a second procedure for loading second data from the second storage medium to the first storage medium; and output the second data based on a second request generated by the process for the second data. ## Claims ### Claim 1 A storage system comprising: a first storage medium; a second storage medium; a controller configured to communicate with the first storage medium and the second storage medium, the controller being configured to: receive a first request generated by a process associated with first data; search for the first data in the first storage medium and generate a fault signal based on the search; identify a criterion based on the fault signal; select, based on the criterion, at least one of a first procedure or a second procedure for loading second data from the second storage medium to the first storage medium; and output the second data based on a second request generated by the process for the second data. ### Claim 2 (depends on 1) The storage system of claim 1, wherein a latency associated with accessing the first storage medium is lower than a latency associated with accessing the second storage medium. ### Claim 3 (depends on 1) The storage system of claim 1, wherein the fault signal is generated based on determining absence of the first data in the first storage medium. ### Claim 4 (depends on 3) The storage system of claim 3, wherein the controller is configured to: load the first data from the second storage medium to the first storage medium. ### Claim 5 (depends on 1) The storage system of claim 1, wherein the criterion includes a success metric associated with the second data. ### Claim 6 (depends on 5) The storage system of claim 5, wherein the success metric is based on success of loading the second data from the second storage medium to the first storage medium. ### Claim 7 (depends on 1) The storage system of claim 1, wherein the controller is further configured to: add a second memory location associated with the second data to a log; and update the log to indicate success of fulfilling the second request from the first storage medium. ### Claim 8 (depends on 1) The storage system of claim 1, wherein the criterion includes an availability of a computing resource. ### Claim 9 (depends on 1) The storage system of claim 1, wherein the first procedure is configured to identify a second memory location storing the second data based on an identified access pattern. ### Claim 10 (depends on 1) The storage system of claim 1, wherein the second procedure includes a neural network configured to predict a second memory location storing the second data based on input features to the neural network. ### Claim 11 A method comprising: receiving a first request generated by a process associated with first data; searching for the first data in a first storage medium and generating a fault signal based on the searching; identifying a criterion based on the fault signal; selecting, based on the criterion, at least one of a first procedure or a second procedure for loading second data from a second storage medium to the first storage medium; and outputting the second data based on a second request generated by the process for the second data. ### Claim 12 (depends on 11) The method of claim 11, wherein a latency associated with accessing the first storage medium is lower than a latency associated with accessing the second storage medium. ### Claim 13 (depends on 11) The method of claim 11, wherein the fault signal is generated based on determining absence of the first data in the first storage medium. ### Claim 14 (depends on 13) The method of claim 13 further comprising: loading the first data from the second storage medium to the first storage medium. ### Claim 15 (depends on 11) The method of claim 11, wherein the criterion includes a success metric associated with the second data. ### Claim 16 (depends on 15) The method of claim 15, wherein the success metric is based on success of loading the second data from the second storage medium to the first storage medium. ### Claim 17 (depends on 11) The method of claim 11 further comprising: adding a second memory location associated with the second data to a log; and updating the log to indicate success of fulfilling the second request from the first storage medium. ### Claim 18 (depends on 11) The method of claim 11, wherein the criterion includes an availability of a computing resource. ### Claim 19 (depends on 11) The method of claim 11, wherein the first procedure identifies a second memory location storing the second data based on an identified access pattern. ### Claim 20 (depends on 11) The method of claim 11, wherein the second procedure includes a neural network that predicts a second memory location storing the second data based on input features to the neural network.