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: A method of determining occupancy of a building using a hidden Markov model.

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: Pixels representing attributes of data records are into discrete rings of a graphical visualization, where the discrete rings correspond to respective ones of the attributes, and where the pixels are arranged in each of the discrete rings according to time intervals of the data records. A correlation ring is provided in the graphical visualization in addition to the discrete rings, where the correlation ring has visual indicators for indicating degrees of correlation between at least two of the attributes.

Abstract: In a method for managing energy demand in an infrastructure, a coefficient of performance (COP) of the infrastructure as a function of time is determined. The COP is a measure of efficiency of the infrastructure. In addition, an energy demand on the infrastructure as a function of time is determined and an energy demand schedule for the infrastructure that temporally reallocates the energy demand based upon the determined COP of the infrastructure is determined.

Abstract: A system and article are disclosed for annotating resource variation. In one example, the system discloses an installation 102, having a device 128 associated with a user 118, and a resource manager 107, 120 programmed with executable instructions, which detect a resource 104 variation 308 associated with the device 128, and label the resource variation with a user annotation 316 generated by the user. In another example, the system discloses a network resource manager service 107 programmed with executable instructions, which interface with an installation 102, having a set of sensors 126 and a set of devices 128 associated with a user 118, receive data from at least one of the sensors which detects a resource 104 variation 308 associated with at least one of the devices; and label the detected resource variation with a user annotation 316.

Abstract: Data points contain data values in respective time intervals. Pixels representing data points for time periods (each time period including multiple time intervals) are placed in corresponding discrete rings in a graphical visualization, wherein the pixels are user accessible to allow viewing of information of the corresponding data points. The pixels are temporally aligned in the corresponding discrete rings, and the pixels in the corresponding discrete rings are variably sized depending on a number of data points in the respective time periods.

Abstract: Determining a sustainability impact for available data center architectures. A data center is accessed by a computer. Two or more functional parameters of the data center are then evaluated by the computer. Then, the computer combines the two or more evaluated functional parameters into a quantified judgment to determine a sustainability impact of available architectures of the data center.

Abstract: Multivariate time-series prediction is combined with motif discovery. Multivariate time-series prediction is performed on measured (past) data points to generate or determine predicted data points. One or more motifs are discovered or determined within the combined measured data points and the predicted data points. The motifs within the measured data points are associated with the motifs within the predicted data points to permit inferences of the motifs within the measured data points to be applied to the motifs within the predicted data points. The measured data points, the predicted data points, and the motifs are displayed. User interaction with this display of the measured data points, the predicted data points, and the motifs is permitted.

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 analyzing energy consumption using node similarity are disclosed. An example of a method may be carried out by program code stored on non-transient computer-readable medium and executed by a processor. The method includes assigning a similarity score to a plurality of nodes using at least one of: domain based rules, attribute based similarity metrics, and machine learning. The method also includes identifying a similar node from the plurality of nodes, for a node under consideration, based on the similarity score. The method also includes determining energy consumption of the node under consideration based on energy consumption of the similar node.

Abstract: A power model that relates the settings of resource actuators to power consumption levels of the resource actuators and a condition model that relates the settings of the resource actuators to an environmental condition at the location of the at least one entity and a power consumption level of the at least one entity are developed. A constraint optimization problem having an objective function and at least one constraint is formulated, where the objective function computes at least a proportional quantity of a total power consumption level of the resource actuators and the at least one constraint comprises a setpoint environmental condition at a location of the at least entity. A solution to the constraint optimization problem is determined, where the solution provides optimal values for the resource actuator settings.

Abstract: In a method for distributing cooling resources to a plurality of locations using a plurality of hierarchically identified cooling microgrids, conditions detected at the plurality of locations are received. Each level of the hierarchically identified cooling microgrids is a plurality of resource actuators configured to vary distribution of the cooling resources. Settings for the plurality of resource actuators in each of the levels in the cooling microgrid hierarchy that substantially maintain conditions at the plurality of locations within predetermined ranges are determined using a processor, while substantially optimizing at least one measure of performance associated with supplying the cooling resources to the plurality of locations.

Abstract: In one implementation, an interactive service management system includes a performance profile module and a performance evaluation module. The performance profile modules defines a performance measure of an interactive service based on a quality assessment associated with the interactive service. The performance evaluation module compares the performance measure with performance target associated with the interactive service, and modifies the performance target associated with the interactive service based on the comparison of the performance measure and the performance target.

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.

Abstract: Example methods, apparatus and articles of manufacture to provision data center resources are disclosed. An example method includes provisioning a first portion of data center resources to operate during time intervals based on a base workload for the respective time intervals, the base workload being based on data patterns of a data center and configuring a second portion of the data center resources to operate when an actual workload exceeds a threshold corresponding to the base workload.

Abstract: An embodiment includes gathering input data including observed utilizations of allocations and business service response times. The input data is partitioned into a plurality of data sets that include at least one training data set and at least one test data set. A model is generated that predicts responsiveness using the at least one training data set. The model is evaluated using the at least one test data set, and a business service response time distribution is predicted using the model. An embodiment may use a trace-based capacity planning methodology to estimate the impact of planning alternatives on business service responsiveness.

Abstract: A method for detecting events based upon attributes read by a plurality of entities includes receiving data pertaining to the read attributes from the plurality of entities, performing a correlation analysis on the data to identify a number of independent variables existing among the read attributes for each of a plurality of groupings of the plurality of entities in a first hierarchical level of the plurality of hierarchical levels, comparing the identified number of independent variables with a nominal number of independent variables for each of the plurality of groupings in the first hierarchical level, and determining that an event has been detected in response to the identified number of independent variables falling outside of a predetermined value of the nominal number of independent variables for a particular grouping in the first hierarchical level.

Abstract: Systems and methods of determining sub-tree similarity for component substitution. An example of a method may be carried out by program code stored on non-transient computer-readable medium and executed by a processor. The method includes assigning a similarity metric to a plurality of trees stored in computer-readable media. The method also includes constructing a distance matrix in computer-readable media, the distance being between sub-trees. The method also includes correlating sub-trees in the computer-readable media based on the distance matrix.

Abstract: System deconstruction systems and methods for component substitution. An example method is carried out by program code stored on non-transient computer-readable medium and executed by a processor. The method includes deconstructing a system tree in computer-readable medium, the system tree deconstructing into a plurality of constituent nodes, each node in the system tree representing a characteristic of a component of a system under consideration. The method also includes searching within a band of variability in other trees for similar nodes. The method also includes qualifying the other trees based on a frequency of the similar nodes in the other trees. The method also includes selecting most relevant nodes from the other trees by at least one of: prioritizing the similar nodes, terminating nodes, and searching nodes hierarchically.