Abstract

Forecasting energy consumption enables users to plan their resource utilization optimally. For this, it is essential to make reliable forecasting of consumption profile in real-time which is very challenging and still emerging. In this study, we focus on forecasting HVAC cooling energy consumption at sub-hourly forecasting horizon which enables us to analyze and control the demand in real-time. With the aid of energy meters and adaptation of BACnet technology in the target building, we collected real building cooling energy consumption data and HVAC systems usage at a higher resolution. In this methodology, weather data from Weather Underground of Gachibowli, Hyderabad location has been used. These recorded weather parameters are being used as explanatory variables. Along with the weather parameters, many other feature-engineered explanatory variables which are discussed in the paper has been used to capture the trend and variation of energy consumption. Required pre-processing and data analysis is performed on the raw data to obtain meaningful information for modeling. We have implemented one-step ahead static forecasting using Gradient Boosting Regression Trees (GBRT), where we forecast for single-time-step ahead in each iteration then update the training data at the end of each iteration with actual data available next time-step in order to assess how well the model forecasts one-step-ahead. Our results show that we could improve forecast accuracy by almost 45% by including feature engineered variables. We achieved a Mean Absolute Percentage Error (MAPE) of 14.7% with GBRT.

Abstract

A well-designed mixed mode building allows natural ventilation when the outside weather conditions are favorable and deploys air-conditioning when natural ventilation is not able to provide sufficient comfort. In this study, a methodology is proposed to enable real time control of operable windows for mixed mode ventilation building. EnergyPlus is used for building energy simulations. A real-time simulation is performed using Building Controls Virtual Test Bed (BCVTB). In this methodology, AERIS Weather Data is used to forecast hourly weather parameters. Seasonal Autoregressive Integrated Moving Average (SARIMA) Models are used to model a day-ahead prediction for the lighting load, electric load and the occupancy profiles. Cosimulation of EnergyPlus is carried out with BCVTB to enable real-time simulation wherein; the EnergyPlus weather file parameters and input building loads are updated every hour. Based on the indoor and outdoor conditions, EnergyPlus calculates the schedule for opening/closing of windows. A simulation based case study for Hyderabad, India is performed to demonstrate the working of the proposed methodology. Reduction of 25% in cooling energy demand was estimated in a mixed mode building as compared to the fully air-conditioned building during the study period.

Abstract

In tropical climates, glass windows are important for a building's energy efficiency. By providing shading on a glass window, direct solar incident radiation can be restricted. This lowers the cooling energy consumption in buildings. The most commonly used method to provide shading is by using fixed shades such as overhangs and fins. Another method is to provide dynamic shades that can be controlled based on incident solar radiation on the façade. Shading is a method to control the solar heat gain coefficient (SHGC) and visible light transmission (VLT) of a vertical fenestration. This study is performed to obtain the equivalent SHGC of vertical fenestration with fixed and dynamic shading. Prescriptive requirements of energy codes, such as ASHRAE 90.1 and ECBCIndia, limit the maximum SHGC value of fenestration. The effective SHGC with fixed shading is defined as the equivalent SHGC. The energy codes define tabular methods for the calculation of the equivalent SHGC that is generally given as a function of overhangs/fins depth, glass orientation, and latitude of the building. This tabular method generally does not cover all orientations, shading depths, and locations. Further, the equivalent SHGC for dynamic shade is either not defined in most of the codes or regarded as the minimum SHGC of the fenestration system. Herein, a simulation-based approach is proposed to calculate the equivalent SHGC for fixed and dynamic shades. A tool has been developed that uses EnergyPlus, the weather file of the building location, window and shading dimensions, and set point for dynamic shades, to perform parametric energy simulations to calculate the equivalent SHGC.

Abstract

The buildings are conventionally operated to maintain homogeneous indoor ambient conditions to maintain comfortable thermal and visual environments. However, maintaining these homogeneous conditions throughout the building leads to unnecessary energy consumption, and does not address the varying thermal and visual comfort needs of the individual occupants. This has led the building science community to pursue personal environmental control (PEC) systems that work in tandem with adaptive centralized ambient comfort systems. These PEC systems create favorable environmental conditions around each occupant, employing specialized equipment, such as a personal thermal conditioning system, task lighting, plug load monitoring and control, window shade control system, and similar systems. Coordinating among personal control systems and with centralized building management systems allows the optimal provision of services such as cooling, lighting, and other such services where they are needed, potentially leading to significant energy efficiency and improved occupant satisfaction. This paper provides an overview of the state of research associated with personalized thermal conditioning and lighting systems. In addition, presents a survey of controls and communication systems that operate these devices. Finally, the paper considers the energy savings potential from a personal thermal comfort and lighting comfort.

Abstract

In early stage of building design, design team has to consider and simulate energy consumption for several combinations of various input parameters to analyze the building energy consumption. In a scenario considering five parameters, each with ten variations, one has to simulate hundred thousand combinations. It requires a lot of computation to simulate energy consumption for all the input combinations. This paper aims at reducing the computation required to compute the energy consumption of all the combinations. This is done by identifying appropriate training samples, computing their energy consumption using EnergyPlus and estimating energy consumption of the rest of the data using machine learning techniques. This paper presents two sampling methods along with various regression techniques to predict energy consumption of a building in the early phase. It involves usage of efficient sampling methods for identifying the training data. The key contribution of this method of surrogate modeling is saving a lot of computation by reducing the computation by ~100-fold. This method is tested for Jaipur and Hyderabad cities of India. Approximately hundred thousand simulations are performed for each location using parallel computation. By simulating approximately one percent of the input combinations, annual energy consumption for the large set of combinations are predicted using SVR and kmeans clustering for Jaipur with accuracy greater than 93% for 99.8% of the input combinations. When the same model is trained for Hyderabad, it produced accuracy greater than 93% for 98% of the input combinations.

Abstract

Based on recent strategies in peak demand reduction for HVAC systems, simple measures like increasing cooling set-point temperatures serves as an effective Demand Response (DR). Majority of the past studies in demand response focus majorly on developing strategies that reduce peak demand and on demand side energy management to optimize energy consumption with the help of renewable energy resources. Research in estimating the potential of DR programs is required and is gaining momentum. It is essential to develop reliable estimation models that can be applied in realtime. We therefore focus on developing a model that predicts the impact of change in HVAC set-point temperature on cooling energy demand. During model evaluation, we made an observation that after a DR event when the set-points are back to normal schedule, sudden and rapid peaks occur in the demand while it is ramping up as set-point temperatures are reduced. For buildings which have a prescribed demand limit, these peaks cause huge demand penalty. We further propose a strategy to enable a stable ramping up process.

Abstract

he dry evergreen forest of Kondapalli (Andhra Pradesh state, India) is declared as a forest reserve, but, despite of this, it is subjected to degradation resulting in loss of biodiversity. Thus, the current study was carried out to investigate the tree diversity of Kondapalli forest. A total of 566 ±16 trees (≥10 cm) representing 46±8 species from 40 genera and 21 families were recorded from the 0.36 ha area of Kondapalli forest. Mimosaceae was the most species rich family, while Rutaceae was the most abundant family. Atalantia monophylla was most frequent and abundant species and, with respect to basal area, Melia azedarach and Syzygium cumini were the dominant taxa. The recorded stem density was 1572 stems ha−1 and the mean forest basal area was 47.17 m2 ha−1. The results of cluster analysis revealed that Atalantia monophylla, characterised by a high ecological amplitude, had a wide distribution and was associated with species forming different communities. The study showed that Kondapalli forest is characterised by a fairly high species richness, which provides the baseline data on the floristic structure and diversity of this forest for better management and conservation.

Abstract

The use of in situ hyperspectral reflectance and bio-physical measurements has been increasing in forestry. Due to limited physical accessibility in a forest environment, most of the reflectance measurements of trees are acquired at a leaf or bunch of leaves level. A few radiative transfer models are available for upscaling leaf spectra to canopy level. While these models are sophisticated, they retrieve canopy spectra based on certain assumptions. We propose ‘semi-empirical model for upscaling leaf spectra (SEMULS)’ which upscales in situ leaf spectra to canopy level based on the relationship between leaf spectra and its bio-physical parameters. The performance of the model has been quantitatively validated by comparing the upscaled canopy spectra with spectra from – CHRIS hyperspectral imagery acquired concurrently and from the PROSAIL model. Results indicate that the SEMULS retrievals are …

Abstract

Sexism, an injustice that subjects women and girls to enormous suffering, manifests in blatant as well as subtle ways. In the wake of growing documentation of experiences of sexism on the web, the automatic categorization of accounts of sexism has the potential to assist social scientists and policy makers in utilizing such data to study and counter sexism better. The existing work on sexism classification, which is different from sexism detection, has certain limitations in terms of the categories of sexism used and/or whether they can co-occur. To the best of our knowledge, this is the first work on the multi-label classification of sexism of any kind(s), and we contribute the largest dataset for sexism categorization. We develop a neural solution for this multilabel classification that can combine sentence representations obtained using models such as BERT with distributional and linguistic word embeddings using a flexible, hierarchical architecture involving recurrent components and optional convolutional ones. Further, we leverage unlabeled accounts of sexism to infuse domain-specific elements into our framework. The best proposed method outperforms several deep learning as well as traditional machine learning baselines by an appreciable margin.

Abstract

Analysis of high variability of inter-state land use land cover change using remote sensing and GIS techniques primarily agriculture in Krishna river basin, India.