Holistic Measures for Evaluating Prediction Models in Smart Grids

The performance of prediction models is often based on ``abstract metrics'' that estimate the model's ability to limit residual errors between the observed and predicted values. However, meaningful evaluation and selection of prediction models for end-user domains requires holistic and application-sensitive performance measures. Inspired by energy consumption prediction models used in the emerging ``big data'' domain of Smart Power Grids, we propose a suite of performance measures to rationally compare models along the dimensions of scale independence, reliability, volatility and cost. We include both application independent and dependent measures, the latter parameterized to allow customization by domain experts to fit their scenario. While our measures are generalizable to other domains, we offer an empirical analysis using real energy use data for three Smart Grid applications: planning, customer education and demand response, which are relevant for energy sustainability. Our results underscore the value of the proposed measures to offer a deeper insight into models' behavior and their impact on real applications, which benefit both data mining researchers and practitioners.

Applicability of Statistical Learning Algorithms for Spatial Variability of Rock Depth

Two algorithms are outlined, each of which has interesting features for modeling of spatial variability of rock depth. In this paper, reduced level of rock at Bangalore, India, is arrived from the 652 boreholes data in the area covering 220 sqa <.km. Support vector machine (SVM) and relevance vector machine (RVM) have been utilized to predict the reduced level of rock in the subsurface of Bangalore and to study the spatial variability of the rock depth. The support vector machine (SVM) that is firmly based on the theory of statistical learning theory uses regression technique by introducing epsilon-insensitive loss function has been adopted. RVM is a probabilistic model similar to the widespread SVM, but where the training takes place in a Bayesian framework. Prediction results show the ability of learning machine to build accurate models for spatial variability of rock depth with strong predictive capabilities. The paper also highlights the capability ofRVM over the SVM model.

Grain Floatation During Equiaxed Solidification of an Al-Cu Alloy in a Side-Cooled Cavity: Part II-Numerical Studies

In this article, a single-phase, one-domain macroscopic model is developed for studying binary alloy solidification with moving equiaxed solid phase, along with the associated transport phenomena. In this model, issues such as thermosolutal convection, motion of solid phase relative to liquid and viscosity variations of the solid-liquid mixture with solid fraction in the mobile zone are taken into account. Using the model, the associated transport phenomena during solidification of Al-Cu alloys in a rectangular cavity are predicted. The results for temperature variation, segregation patterns, and eutectic fraction distribution are compared with data from in-house experiments. The model predictions compare well with the experimental results. To highlight the influence of solid phase movement on convection and final macrosegregation, the results of the current model are also compared with those obtained from the conventional solidification model with stationary solid phase. By including the independent movement of the solid phase into the fluid transport model, better predictions of macrosegregation, microstructure, and even shrinkage locations were obtained. Mechanical property prediction models based on microstructure will benefit from the improved accuracy of this model.

Time dependent deformations in concrete: A multi-scale approach

Estimation of creep and shrinkage are critical in order to compute loss of prestress with time in order to compute leak tightness and assess safety margins available in containment structures of nuclear power plants. Short-term creep and shrinkage experiments have been conducted using in-house test facilities developed specifically for the present research program on 35 and 45 MPa normal concrete and 25 MPa heavy density concrete. The extensive experimental program for creep, has cylinders subject to sustained levels of load typically for several days duration (till negligible strain increase with time is observed in the creep specimen), to provide the total creep strain versus time curves for the two normal density concrete grades and one heavy density concrete grade at different load levels, different ages at loading, and at different relative humidity’s. Shrinkage studies on prism specimen for concrete of the same mix grades are also being studied. In the first instance, creep and shrinkage prediction models reported in the literature has been used to predict the creep and shrinkage levels in subsequent experimental data with acceptable accuracy. While macro-scale short experiments and analytical model development to estimate time dependent deformation under sustained loads over long term, accounting for the composite rheology through the influence of parameters such as the characteristic strength, age of concrete at loading, relative humidity, temperature, mix proportion (cement: fine aggregate: coarse aggregate: water) and volume to surface ratio and the associated uncertainties in these variables form one part of the study, it is widely believed that strength, early age rheology, creep and shrinkage are affected by the material properties at the nano-scale that are not well established. In order to understand and improve cement and concrete properties, investigation of the nanostructure of the composite and how it relates to the local mechanical properties is being undertaken. While results of creep and shrinkage obtained at macro-scale and their predictions through rheological modeling are satisfactory, the nano and micro indenting experimental and analytical studies are presently underway. Computational mechanics based models for creep and shrinkage in concrete must necessarily account for numerous parameters that impact their short and long term response. A Kelvin type model with several elements representing the influence of various factors that impact the behaviour is under development. The immediate short term deformation (elastic response), effects of relative humidity and temperature, volume to surface ratio, water cement ratio and aggregate cement ratio, load levels and age of concrete at loading are parameters accounted for in this model. Inputs to this model, such as the pore structure and mechanical properties at micro/nano scale have been taken from scanning electron microscopy and micro/nano-indenting of the sample specimen.

A study of vertical cloud structure of the Indian summer monsoon using CloudSat data

Precise specification of the vertical distribution of cloud optical properties is important to reduce the uncertainty in quantifying the radiative impacts of clouds. The new global observations of vertical profiles of clouds from the CloudSat mission provide opportunities to describe cloud structures and to improve parameterization of clouds in the weather and climate prediction models. In this study, four years (2007-2010) of observations of vertical structure of clouds from the CloudSat cloud profiling radar have been used to document the mean vertical structure of clouds associated with the Indian summer monsoon (ISM) and its intra-seasonal variability. Active and break monsoon spells associated with the intra-seasonal variability of ISM have been identified by an objective criterion. For the present analysis, we considered CloudSat derived column integrated cloud liquid and ice water, and vertically profiles of cloud liquid and ice water content. Over the South Asian monsoon region, deep convective clouds with large vertical extent (up to 14 km) and large values of cloud water and ice content are observed over the north Bay of Bengal. Deep clouds with large ice water content are also observed over north Arabian Sea and adjoining northwest India, along the west coast of India and the south equatorial Indian Ocean. The active monsoon spells are characterized by enhanced deep convection over the Bay of Bengal, west coast of India and northeast Arabian Sea and suppressed convection over the equatorial Indian Ocean. Over the Bay of Bengal, cloud liquid water content and ice water content is enhanced by similar to 90 and similar to 200 % respectively during the active spells. An interesting feature associated with the active spell is the vertical tilting structure of positive CLWC and CIWC anomalies over the Arabian Sea and the Bay of Bengal, which suggests a pre-conditioning process for the northward propagation of the boreal summer intra-seasonal variability. It is also observed that during the break spells, clouds are not completely suppressed over central India. Instead, clouds with smaller vertical extent (3-5 km) are observed due to the presence of a heat low type of circulation. The present results will be useful for validating the vertical structure of clouds in weather and climate prediction models.

A novel gene THSD7A is associated with obesity

Body mass index (BMI) is a non-invasive measurement of obesity. It is commonly used for assessing adiposity and obesity-related risk prediction. Genetic differences between ethnic groups are important factors, which contribute to the variation in phenotypic effects. India inhabited by the first out-of-Africa human population and the contemporary Indian populations are admixture of two ancestral populations; ancestral north Indians (ANI) and ancestral south Indians (ASI). Although ANI are related to Europeans, ASI are not related to any group outside Indian-subcontinent. Hence, we expect novel genetic loci associated with BMI. In association analysis, we found eight genic SNPs in extreme of distribution (P <= 3.75 x 10(-5)), of which WWOX has already been reported to be associated with obesity-related traits hence excluded from further study. Interestingly, we observed rs1526538, an intronic SNP of THSD7A; a novel gene significantly associated with obesity (P = 2.88 x 10(-5), 8.922 x 10(-6) and 2.504 x 10(-9) in discovery, replication and combined stages, respectively). THSD7A is neural N-glycoprotein, which promotes angiogenesis and it is well known that angiogenesis modulates obesity, adipose metabolism and insulin sensitivity, hence our result find a correlation. This information can be used for drug target, early diagnosis of obesity and treatment.

Hydrologic drought prediction under climate change: Uncertainty modeling with Dempster-Shafer and Bayesian approaches

Representation and quantification of uncertainty in climate change impact studies are a difficult task. Several sources of uncertainty arise in studies of hydrologic impacts of climate change, such as those due to choice of general circulation models (GCMs), scenarios and downscaling methods. Recently, much work has focused on uncertainty quantification and modeling in regional climate change impacts. In this paper, an uncertainty modeling framework is evaluated, which uses a generalized uncertainty measure to combine GCM, scenario and downscaling uncertainties. The Dempster-Shafer (D-S) evidence theory is used for representing and combining uncertainty from various sources. A significant advantage of the D-S framework over the traditional probabilistic approach is that it allows for the allocation of a probability mass to sets or intervals, and can hence handle both aleatory or stochastic uncertainty, and epistemic or subjective uncertainty. This paper shows how the D-S theory can be used to represent beliefs in some hypotheses such as hydrologic drought or wet conditions, describe uncertainty and ignorance in the system, and give a quantitative measurement of belief and plausibility in results. The D-S approach has been used in this work for information synthesis using various evidence combination rules having different conflict modeling approaches. A case study is presented for hydrologic drought prediction using downscaled streamflow in the Mahanadi River at Hirakud in Orissa, India. Projections of n most likely monsoon streamflow sequences are obtained from a conditional random field (CRF) downscaling model, using an ensemble of three GCMs for three scenarios, which are converted to monsoon standardized streamflow index (SSFI-4) series. This range is used to specify the basic probability assignment (bpa) for a Dempster-Shafer structure, which represents uncertainty associated with each of the SSFI-4 classifications. These uncertainties are then combined across GCMs and scenarios using various evidence combination rules given by the D-S theory. A Bayesian approach is also presented for this case study, which models the uncertainty in projected frequencies of SSFI-4 classifications by deriving a posterior distribution for the frequency of each classification, using an ensemble of GCMs and scenarios. Results from the D-S and Bayesian approaches are compared, and relative merits of each approach are discussed. Both approaches show an increasing probability of extreme, severe and moderate droughts and decreasing probability of normal and wet conditions in Orissa as a result of climate change. (C) 2010 Elsevier Ltd. All rights reserved.

Prediction of Ultimate Capacity of Laterally Loaded Piles in Clay: A Relevance Vector Machine Approach

This study investigates the potential of Relevance Vector Machine (RVM)-based approach to predict the ultimate capacity of laterally loaded pile in clay. RVM is a sparse approximate Bayesian kernel method. It can be seen as a probabilistic version of support vector machine. It provides much sparser regressors without compromising performance, and kernel bases give a small but worthwhile improvement in performance. RVM model outperforms the two other models based on root-mean-square-error (RMSE) and mean-absolute-error (MAE) performance criteria. It also stimates the prediction variance. The results presented in this paper clearly highlight that the RVM is a robust tool for prediction Of ultimate capacity of laterally loaded piles in clay.

Prediction of inplane damping from deterministic and stochastic models

This paper reviews computational reliability, computer algebra, stochastic stability and rotating frame turbulence (RFT) in the context of predicting the blade inplane mode stability, a mode which is at best weakly damped. Computational reliability can be built into routine Floquet analysis involving trim analysis and eigenanalysis, and a highly portable special purpose processor restricted to rotorcraft dynamics analysis is found to be more economical than a multipurpose processor. While the RFT effects are dominant in turbulence modeling, the finding that turbulence stabilizes the inplane mode is based on the assumption that turbulence is white noise.

Prediction of load-deflection behaviour using fracture energy GF: A comparative study of two fracture models for concrete

Load-deflection curves for a notched beam under three-point load are determined using the Fictitious Crack Model (FCM) and Blunt Crack Model (BCM). Two values of fracture energy GF are used in this analysis: (i) GF obtained from the size effect law and (ii) GF obtained independently of the size effect. The predicted load-deflection diagrams are compared with the experimental ones obtained for the beams tested by Jenq and Shah. In addition, the values of maximum load (Pmax) obtained by the analyses are compared with the experimental ones for beams tested by Jenq and Shah and by Bažant and Pfeiffer. The results indicate that the descending portion of the load-deflection curve is very sensitive to the GF value used.

Bayesian parameter identification in dynamic state space models using modified measurement equations

When Markov chain Monte Carlo (MCMC) samplers are used in problems of system parameter identification, one would face computational difficulties in dealing with large amount of measurement data and (or) low levels of measurement noise. Such exigencies are likely to occur in problems of parameter identification in dynamical systems when amount of vibratory measurement data and number of parameters to be identified could be large. In such cases, the posterior probability density function of the system parameters tends to have regions of narrow supports and a finite length MCMC chain is unlikely to cover pertinent regions. The present study proposes strategies based on modification of measurement equations and subsequent corrections, to alleviate this difficulty. This involves artificial enhancement of measurement noise, assimilation of transformed packets of measurements, and a global iteration strategy to improve the choice of prior models. Illustrative examples cover laboratory studies on a time variant dynamical system and a bending-torsion coupled, geometrically non-linear building frame under earthquake support motions. (C) 2015 Elsevier Ltd. All rights reserved.