Abstract: Determining sensor placement in distributed networks includes identifying measurement locations in a distributed network with a tree topology and selecting a subset of the measurement locations for sensor placement with a mutual information function.

Abstract: Described herein are techniques for identifying anomalous behavior of a monitored entity. Features can be extracted from data related to operation of an entity. The features can be mapped to a plurality of states to generate a state sequence. An observed value of a metric can be compared to an expected value of the metric based on the state sequence.

Abstract: Systems and methods of managing workload at a data center are disclosed. An example method may include actively managing workload at a data center to realize energy savings. The method may also include providing excess power generated for the data center onto a utility grid.

Abstract: A method for detecting power consumption anomalies. The method obtains two different time power series and compares them to generate a dissimilarity matrix. A dimensionality reduction equation is applied to the dissimilarity matrix to obtain a low dimensional embedding of the power data. A probability score of each of the time series being anomalous is then calculated.

Abstract: According to an example, synthetic time series data generation may include receiving time series data for a plurality of users, and applying dimensionality reduction to transform the time series data from a high dimensional space n of the time series data to a low dimensional space m, where m<n. The transformed time series data may be used to estimate a time series data density in the low dimensional space m by generating a density function. The density function may be sampled for data, and the sampled data may be transformed back to the high dimensional space n to generate the synthetic time series data.

Abstract: Characterizing risks in resource distribution systems includes collecting measurements from multiple end users in a resource distribution system and identifying a subset of the end users that pose a greater than average risk to the resource distribution system with a risk identification engine.

Abstract: Detecting fraud in resource distribution systems includes determining a meter of a resource in a resource distribution system exhibits a characteristic indicative of fraud and increasing a collection frequency of measurements of a usage of the resource of the meter per unit of time.

Abstract: According to an example, an application performance measurement for an application for a current time interval, a performance specification for the application, and a resource consumption metric for a resource of a plurality of resources that are to process the application for the current time interval may be accessed. In addition, the application performance measurement, the performance specification, and the resource consumption metric may be used to determine a resource specification for a next time interval for the resource of the plurality of resources. Moreover, the resource specification may be used to determine, by a processor, a resource weight for the resource of the plurality of resources for the next time interval.

Abstract: A method of maximizing server utilization within a datacenter comprising collocating a number of workloads to a subset of a number of physical servers within a datacenter, adjusting access to resources by critical and non-critical workloads, isolating a number of critical workloads that share resources to the subset of resource instances, and controlling resource utilization of the collocated workloads. A system for collocating workloads in a datacenter, the system comprising a number of servers communicatively coupled to each other and a collocation module that receives information from each server and decides whether to leave a workload running on one of any of the servers on that server, or migrate a workload running on one of the number of servers to another server.

Abstract: In an implementation, a method for managing an entity may include establishing of a framework for characterization of the entity, in which the framework abstracts operation of the entity to a state machine. In addition, each state in the state machine may be characterized in terms of distributions of a performance metric associated with the entity. The method may also include implementing of the framework for characterization of the entity to manage the entity.

Abstract: A method of maximizing server utilization within a datacenter comprising collocating a number of workloads to a subset of a number of physical servers within a datacenter, adjusting access to resources by critical and non-critical workloads, isolating a number of critical workloads that share resources to the subset of resource instances, and controlling resource utilization of the collocated workloads. A system for collocating workloads in a datacenter, the system comprising a number of servers communicatively coupled to each other and a collocation module that receives information from each server and decides whether to leave a workload running on one of any of the servers on that server, or migrate a workload running on one of the number of servers to another server.

Abstract: Systems and automated methods for predicting photovoltaic (PV) generation are provided. Weather forecast data and present-day and historical PV generation data are provided to respective predictors. The predictors derive weighted predictions that are used to calculate a Bayesian model average. Near-future generation by the PV system is predicted using the Bayesian model average. Production rates, worker scheduling, hours of operation and other planning decisions can be made in accordance with the predicted near-future generation.

Abstract: Examples of meter data management testing are disclosed. In one example implementation according to aspects of the present disclosure, a computing device may include one or more processors, a memory for storing machine readable instructions, and a data store. The computing device may further include a meter data management testing module stored in the memory and executing on at least one of the one or more processors to test a meter data management system using a data set of representative metering data and a user-generated test scenario specifying a plurality of metering parameters.

Abstract: Example embodiments relate to device monitoring. In one example implementation according to aspects of the present disclosure, a computing device may include one or more processors, a memory for storing machine readable instructions, and a data store. Additionally, the computing device may include a utility device monitoring module stored in the memory and executing on at least one of the one or more processors to passively monitor network information and power information from a utility device communicatively coupled to a network and a power source.

Abstract: According to an example, synthetic time series data generation may include receiving empirical meter data for a plurality of users, and using the empirical meter data to estimate parameters of a Markov chain. The Markov chain may be used to generate the synthetic time series data having statistical properties similar to the statistical properties of the empirical meter data.

Abstract: According to an example, synthetic time series data generation may include receiving time series data for a plurality of users, and applying dimensionality reduction to transform the time series data from a high dimensional space n of the time series data to a low dimensional space m, where m<n. The transformed time series data may be used to estimate a time series data density in the low dimensional space m by generating a density function. The density function may be sampled for data, and the sampled data may be transformed back to the high dimensional space n to generate the synthetic time series data.

Abstract: In a method for managing a facility that is to receive resources from a first resource supply, a supply of resources available from the first resource supply is predicted for a predetermined period of time. In addition, a demand for resources in the facility during the predetermined period of time is predicted. A capacity schedule for the facility is planned to meet a predefined operational goal, in which the plan of the capacity schedule uses as inputs, the predicted supply of resources available from the first resource supply and the predicted demand for resources in the facility during the predetermined period of time. Moreover, a determination as to whether the planned capacity schedule meets the predefined operational goal is made.

Abstract: According to an example, an application performance measurement for an application for a current time interval, a performance specification for the application, and a resource consumption metric for a resource of a plurality of resources that are to process the application for the current time interval may be accessed. In addition, the application performance measurement, the performance specification, and the resource consumption metric may be used to determine a resource specification for a next time interval for the resource of the plurality of resources. Moreover, the resource specification may be used to determine, by a processor, a resource weight for the resource of the plurality of resources for the next time interval.

Abstract: In an embodiment, a device characterization system includes a sensor to sense an attribute of a device, a processor, and an algorithm executable on the processor to collect time series data of the attribute from the sensor, detect edges in the data, identify clusters from the edges, label the clusters based on input from a supervisor, and estimate device characterization parameters from the clusters.

Abstract: Systems and methods of disaggregating power load are provided. An example of a method is carried out by program code stored on non-transient computer-readable medium and executed by a processor. The method includes receiving time series data representing total energy consumption. The method also includes identifying distinguishing features in the time series data. The method also includes identifying energy consumption constituents of the total energy consumption based on the features.