Emc IP Holding Company LLC

Emc Corporation

Dell Products Inc.

Vinícius Michel Gottin

Tiago Salviano Calmon

Jonas Furtado Dias

Eduardo Vera Sousa

Angelo E M Ciarlini

Alex Laier Bordignon

Daniel Sadoc Menasché

Rômulo Teixeira De Abreu Pinho

Adriana Bechara Prado

Hugo De Oliveira Barbalho

André De Almeida Maximo

Edward José Pacheco Condori

Fábio André Machado Porto

Yania Molina Souto

Monica Barros

Manuel Ramón Vargas Avila

Owen Martin

John T Cardente

Paulo De Figueiredo Pires

Roberto Nery Stelling Neto

Diego Salomone Bruno

Rodrigo Dias Arruda Senra

Wagner Dos Santos Vieira

Bruno Carlos Da Cunha Costa

Angelo Ernani Maia Ciarlini

Fábio A M Porto

Rodrigo De Souza Lima Espinha

Amit Bhaya

Oumar Diene

Jonathan Ferreira Passoni

Methods and apparatus are provided for real-time anomaly detection over sets of time-series data. One method comprises: obtaining a state-space representation of a plurality of states and transitions between said states based on sets of historical time-series data; obtaining an anomaly detection model trained using a supervised learning technique, wherein the anomaly detection model associates sequences of states in the state-space representation with annotated anomalies in the sets of historical time-series data and assigns a probability to said sequences of states; and, for incoming real-time time-series data, determining a likelihood of a current state belonging to a plurality of possible states in the state-space representation; and determining a probability of incurring said annotated anomalies based on a plurality of likely current state sequences that satisfy a predefined likelihood criteria. Anomalous behavior is optionally distinguished from previously unknown behavior based on a predefined likelihood threshold.

Methods and apparatus for real-time anomaly detection over sets of time-series data

Techniques are provided for allocating resources for one or more workloads. One method comprises obtaining a current performance of a workload; determining an adjustment to a current allocation of a resource allocated to the workload by evaluating a representation of a relationship between: (i) the current allocation of the resource allocated to the workload, (ii) a performance metric, and (iii) the current performance of the workload; and initiating an application of the determined adjustment to the current allocation of the resource for the workload. The performance metric may comprise a nominal value of a predefined service metric and the current performance of the workload may comprise a current value of a variable that tracks a given predefined service metric of the workload. An amount (or percentage) of the adjustment permitted for each iteration may be controlled. A sum of allocated resources can be constrained to an amount of available resources.

Resource adaptation using nonlinear relationship between system performance metric and resource usage

Techniques are provided for assigning workloads in a multi-node processing environment using resource allocation feedback from each node. One method comprises obtaining feedback from distributed nodes that process workloads, wherein the feedback for a given node indicates (i) an allocation of resources, and (ii) a number of executing workloads. In response to receiving a given workload to be processed, candidate nodes are identified to execute the given workload; and the given workload is assigned to a given candidate node based on an amount of available resources on each candidate node and/or a stability of resource adjustments made for each candidate node. The stability of the resource adjustments made for each candidate node can be evaluated based on a maximum resource adjustment made for a given candidate node relative to a maximum resource adjustment made for each of the candidate nodes.

Assigning workloads in a multi-node processing environment using feedback from each node

Techniques are provided for adaptive resource allocation for multiple workloads. One method comprises obtaining a dynamic system model based on a relation between an amount of a resource for multiple iterative workloads and a predefined service metric; obtaining an instantaneous value of the predefined service metric; applying to a given controller associated with a given iterative workload of the multiple iterative workloads: (i) the dynamic system model, (ii) an interference effect of one or more additional iterative workloads on the given iterative workload, and (iii) a difference between the instantaneous value and a target value for the predefined service metric. The given controller applies an adjustment to the amount of the resource for the given iterative workload based at least in part on the difference. The resource allocation for the multiple iterative workloads can be performed in a sequence substantially in parallel with an execution of the iterative workloads.

Adaptation of resource allocation for multiple workloads using interference effect of resource allocation of additional workloads on performance

Deep reinforcement learning techniques are provided for resource allocation in a shared computing environment. An exemplary method comprises: obtaining a specification of a workflow of a plurality of concurrent workflows in a shared computing environment, wherein the specification comprises a plurality of workflow states and one or more control variables for the workflow in the shared computing environment; evaluating values of the control variables for an execution of the concurrent workflows using a reinforcement learning agent by (i) observing the states, including a current state, and (ii) obtaining an expected utility score for combinations of the control variables for the execution of the concurrent workflows given an allocation of resources of the shared computing environment corresponding to the combination of control variables in the current state; and providing an allocation of the resources of the shared computing environment reflecting the combination having the expected utility score that satisfies a predefined score criteria.

Deep reinforcement learning for workflow optimization

Reinforcement learning agents for resource allocation for iterative workloads, such as training Deep Neural Networks, are configured. One method comprises obtaining a specification of an iterative workload comprising multiple states and a set of available actions for each state, and a domain model of the iterative workload relating allocated resources with service metrics; adjusting weights of a reinforcement learning agent by performing iteration steps for each simulated iteration of the iterative workload and using variables from the simulated iteration to refine the reinforcement learning agent; and determining a dynamic resource allocation policy for the iterative workload. The exemplary iteration steps comprise: (a) selecting an action for a current state, obtaining a reward for the selected action and selecting a next state based on the current state and/or the selected action; (b) updating a function that evaluates a quality of a plurality of state-action combinations; and (c) repeating steps (a) and (b) with a new allocation of resources.

Building neural networks for resource allocation for iterative workloads using reinforcement learning

Techniques are provided for adaptive resource allocation for workloads with initial condition setting. One method comprises obtaining a dataset comprising data from previous executions of a workload, wherein the data comprises a plurality of different resource allocations and parameterizations of the workload; determining an initial allocation of an amount of a resource for the workload based on a regression model characterizing a behavior of the workload, the data, a predefined service metric and a characterization of a target infrastructure; and initiating an application of the determined initial allocation of the amount of the resource for the workload. A performance of one or more of the plurality of workloads can be evaluated based on a percentage of time within a predefined error range. The regression model can be updated and/or replaced over time with new data for additional executions of the at least one workload.

Initialization of resource allocation for a workload characterized using a regression model

A method for characterizing workload sequentiality for cache policy optimization includes maintaining an IO trace data structure having a rolling window of IO traces describing access operations on addresses of a storage volume. A page count data structure is maintained that includes a list of all of the addresses of the storage volume referenced by the IO traces in the IO trace data structure. A list of sequences data structure is maintained that contains a list of all sequences of the addresses of the storage volume that were accessed by the IO traces in the IO trace data structure. A sequence lengths data structure is used to correlate each sequence in the list of sequences data structure with a length of the sequence, and a histogram data structure is used to correlate sequence lengths and a number of how many of sequences of each length are maintained in the sequence lengths data structure.

Method and apparatus for characterizing workload sequentiality for cache policy optimization

Techniques are provided for workflow simulation using provenance data similarity and sequence alignment. An exemplary method comprises: obtaining a state of workflow executions of concurrent workflows with multiple resource allocation configurations, wherein the state comprises provenance data of the concurrent workflows; obtaining execution traces of the concurrent workflows representing different resource allocation configurations; identifying a set of states in a first execution trace and a set of states in a second execution trace as corresponding anchor states; mapping a first intermediate state to a second intermediate state between a pair of anchor states using the provenance data; generating a simulation model of the workflow executions representing the different configurations of the resource allocation; and generating new simulation traces of the workflow executions with resource allocation configurations that are not represented in the provenance data.

Workflow simulation using provenance data similarity and sequence alignment

Techniques are provided for characterizing and quantifying a sequentiality of workloads using sequentiality profiles and signatures. One exemplary method comprises obtaining telemetry data for an input/output workload; evaluating a distribution over time of sequence lengths for input/output requests in the telemetry data by the input/output workload; and generating a sequentiality profile for the input/output workload to characterize the input/output workload based at least in part on the distribution over time of the sequence lengths. Multiple sequentiality profiles for one or more input/output workloads may be clustered into a plurality of clusters. A sequentiality signature may be generated to represent one or more sequentiality profiles within a given cluster. A performance of data movement policies may be evaluated with respect to the sequentiality signature of the given cluster.

Sequentiality characterization of input/output workloads

Techniques are provided for online anomaly detection using pairwise agreement in a heterogeneous model ensemble. An exemplary contextual model agreement network comprises nodes and transition edges between the nodes, where each node corresponds to a machine learning model and the transition edges between corresponding pairwise machine learning models encode a level of historical agreement between the pairwise machine learning models. In response to an availability of new data observations: features present in the data observations are extracted; a subset of the machine learning models is selected from the machine learning models based on the extracted features; the historical agreement between the selected machine learning models is compared with a current agreement of the selected machine learning models; and an anomaly is detected in the data observations based on the comparison. The contextual model agreement network is optionally updated based on new data observations.

Online anomaly detection using pairwise agreement in heterogeneous model ensemble

The sizes of cache partitions, in a partitioned cache, are dynamically adjusted by determining, for each request, how many cache misses will occur in connection with implementing the request against the cache partition. The cache partition associated with the current request is increased in size by the number of cache misses and one or more other cache partitions is decreased in size causing cache evictions to occur from the other cache partitions rather than from the current cache partition. The other cache partitions, that are to be decreased in size, may be determined by ranking the cache partitions according to frequency of use and selecting the least frequently used cache partition to be reduced in size.

Method and apparatus for dynamically adapting sizes of cache partitions in a partitioned cache

Techniques are provided for detecting resource bottlenecks in workflow task executions using provenance data. An exemplary method comprises: obtaining a state of multiple workflow executions of multiple concurrent workflows performed with different resource allocation configurations in a shared infrastructure environment; obtaining first and second signature execution traces of a task representing first and second resource allocation configurations, respectively; identifying first and second corresponding sequences of time intervals in the first and second signature execution traces for the task, respectively, based on a similarity metric; and identifying a given time interval as a resource bottleneck of a resource that differs between the first and second resource allocation configurations based on a change in execution time for the given time interval between the first and second signature execution traces. The first signature execution trace may be obtained by disaggregating data related to batches of workflow executions.

Detection of resource bottlenecks in execution of workflow tasks using provenance data

Methods and apparatus are provided for evaluating combinatorial processes using simulation techniques and multiple parallel statistical analyses of real-world data. A simulation model is generated that simulates one or more steps of a combinatorial process. The simulation model comprises key features of the combinatorial process. A plurality of first data mining tasks are performed in parallel over real data of the combinatorial process to obtain key feature prediction models that estimate the key features. The key feature prediction models are bound to the simulation model. Query types to be supported are identified and a plurality of simulation runs are generated in parallel, comprising simulated data for the supported query types. A plurality of second data mining tasks are performed in parallel over the plurality of simulation runs to build global prediction models to answer queries of each supported query type. An answer to a user query is determined using the global prediction models.

Methods and apparatus for evaluation of combinatorial processes using simulation and multiple parallel statistical analyses of real data

Techniques are provided for adaptive resource allocation for workloads with early-convergence detection. One method comprises obtaining a dynamic system model based on a relation between an amount of a resource for multiple workloads and a predefined service metric; obtaining an instantaneous value of the predefined service metric; obtaining an adjustment to the amount of the resource for a given workload based on a difference between the instantaneous value and a target value of the predefined service metric; determining whether the given workload has converged based on an evaluation of one or more predefined convergence criteria; and removing the given workload from a controlled workload list when the given workload has converged. The given workload can be reinserted in the controlled workload list when the given one of the plurality of workloads fails to satisfy a predefined divergence threshold.

Growing community of inventors

Rio de Janeiro, Brazil

Vinícius Michel Gottin