US 12,254,184 B1
Response time estimation using sequence-to-sequence deep neural networks
Krzysztof Misan, Cracow (PL); Ron Arnan, Nes Ziona (IL); Hagay Dagan, Karkur (IL); and Gil Ratsaby, Jerusalem (IL)
Assigned to Dell Products L.P., Round Rock, TX (US)
Filed by Dell Products L.P., Round Rock, TX (US)
Filed on Jan. 24, 2024, as Appl. No. 18/421,263.
Int. Cl. G06F 3/00 (2006.01); G06F 3/06 (2006.01)
CPC G06F 3/0611 (2013.01) [G06F 3/0655 (2013.01); G06F 3/067 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving an input, the input including a first workload data set, the first workload data set specifying a cache hit outcome distribution that is associated with a plurality of input-output (I/O) operations;
identifying a plurality of workload portions of the first workload data set, each of the workload portions identifying: (i) a rate of a cache hit outcome that is associated with a respective I/O operation, and (ii) a data size that is associated with the respective I/O operation;
generating a plurality of initial vectors, each of the initial vectors being generated based on a different one of the plurality of workload portions, each of the initial vectors being generated by a different sub-network of a correlation neural network;
generating a context vector at least in part by concatenating the plurality of initial vectors;
processing the context vector with a decoder to generate a plurality of data points in a response time curve of a storage system, wherein the decoder is configured to use autoregression to generate each of the plurality of data points, wherein the decoder is executed iteratively until the plurality of data points is generated, and wherein each of the plurality of data points is generated as a result of a different execution of the decoder; and
outputting the set of data points for presentation to a user.