Search

In this paper we present a novel methodology, referenced as ORFEO (Ordinal classifier and Regressor Fusion for Estimating an Ordinal categorical target), to enhance the performance in ordinal classification problems for which the latent variable is observable. ORFEO is an artificial neural network model incorporating two outputs, one for ordinal classification, using the cumulative link model, and one for regression, using a linear model. Both outputs are simultaneously optimised considering a loss function that linearly combines both classification and regression losses. The main motivation behind developing the proposed approach is to enhance the performance of a standard ordinal classifier. This improvement is facilitated by considering the regression output, which allows the model to differentiate between patterns within the same category. The ORFEO model is applied to two problems in the field of marine and ocean engineering: short-term prediction of both significant wave height and flux of energy. Both problems are addressed considering four different coastal zones of the United States of America, using 13 datasets formed by buoys measurements and reanalysis data. A comprehensive comparison against 20 methodologies, including regression and nominal/ordinal classification approaches is performed, by using diverse nominal and ordinal performance metrics. Ranks achieved indicate that ORFEO outperforms all the compared methodologies in terms of all the performance measures, demonstrating the efficacy and robustness of the proposal. Finally, a statistical analysis is conducted, concluding that there are statistically significant differences across ordinal and nominal performance metrics in favour of the proposed ORFEO model. [ABSTRACT FROM AUTHOR]

Frequency regulation (FR) is the electric grid service responsible for maintaining the system frequency at its nominal value of 60 Hz in the United States — an indicator of energy balance on the grid. In cases of mismatch between power supply and demand, FR resources either on the generation or the demand side, responding rapidly to restore system frequency to its nominal value. Due to the limited responsiveness of generators, fast and accurate demand side resources (DSR) have recently been encouraged to participate in FR. However, the tested DSRs typically require high initial equipment investment (e.g., flywheels and batteries). Large commercial buildings can provide effective load shaping with little impact to occupants’ comfort and have significant amount of available capacity for FR participation. In addition, commercial buildings are characterized by numerous interdependent HVAC subsystems and control systems. Therefore, a high-level supervisory control strategy is needed that directs the interdependent HVAC systems for FR with strengthened interactions and depressed counteractions. Simulation results suggest that large commercial buildings can provide significant FR capacity and high performance scores. Dynamic building-to-grid integration automatically and continuously provides solutions maintaining energy balance on the gird. The benefit to the power system reliability would be significant. [ABSTRACT FROM AUTHOR]

Examines the performance-based regulation (PBR) in the electricity sector in the U.S. Overview on the development of PBR; Number of electric utility companies operating under the PBR; Utilization of incentive plans in the electric utility industries with PBR.