Rohinton Emmanuel

Design and Implementation of a Cloud Enabled Random Neural Network-Based Decentralized Smart Controller With Intelligent Sensor Nodes for HVAC

Building energy management systems (BEMSs) monitor and control the heating ventilation and air conditioning (HVAC) of buildings in addition to many other building systems and utilities. Wireless sensor networks (WSNs) have become the integral part of BEMS at the initial implementation phase or latter when retro fitting is required to upgrade older buildings. WSN enabled BEMS, however, have several challenges which are managing data, controllers, actuators, intelligence, and power usage of wireless components (which might be battery powered). The wireless sensor nodes have limited processing power and memory for embedding intelligence in the sensor nodes. In this paper, we present a random neural network (RNN)-based smart controller on a Internet of Things (IoT) platform integrated with cloud processing for training the RNN which has been implemented and tested in an environment chamber. The IoT platform is modular and not limited to but has several sensors for measuring temperature, humidity, inlet air coming from the HVAC duct and PIR. The smart RNN controller has three main components: 1) base station; 2) sensor nodes; and 3) the cloud with embedded intelligence on each component for different tasks. This IoT platform is integrated with cloud processing for training the RNN. The RNN-based occupancy estimator is embedded in sensor node which estimates the number of occupants inside the room and sends this information to the base station. The base station is embedded with RNN models to control the HVAC on the basis of setpoints for heating and cooling. The HVAC of the environment chamber consumes 27.12% less energy with smart controller as compared to simple rule-based controllers. The occupancy estimation time is reduced by our proposed hybrid algorithm for occupancy estimation that combines RNN-based occupancy estimator with door sensor node (equipped with PIR and magnetic reed switch). The results show that accuracy of hybrid RNN occupancy estimator is 88%.

Comparison of the Robustness of RNN, MPC and ANN Controller for Residential Heating System

In this paper, a novel random neural network (RNN) controller is proposed to maintain a comfortable indoor environment in a single storey residential building having four rooms fitted with radiators for heating. This controller considers the effect of outside temperature and solar radiations on the building and is capable of maintaining a comfortable indoor environment on the basis of a PMV-based set point. The RNN controller is trained with a 30 day dataset from the living room of the building and the performance of the controller is evaluated by testing the controller in all four rooms of the building for 100 days. It is found that the RNN controller is not only capable of maintaining comfortable indoor environment as suggested by PMV-based set point but can also adjust the room temperature to a lower set point (not included in the training set) required by the user for unoccupied rooms. The RNN controller is further compared with similar artificial neural network (ANN) controller and model predictive control (MPC) controller. The results show that for maintaining comfortable indoor environment, the performance of the RNN controller is approximately equivalent to the MPC controller for the set points not covered in the training set, while ANN controller failed to maintain accurate comfortable environment for the operating points not covered in the training phase.

Assessment of predicted versus measured thermal comfort and optimal comfort ranges in the outdoor environment in the temperate climate of Glasgow, UK

In a warming world, the risk of overheating is significant in temperate climate areas such as Glasgow, UK where adaptation to overheating is low. An easy-to-use thermal comfort evaluation is therefore a necessary first step towards developing effective coping mechanisms. In this study, we explore the effectiveness of Predicted Mean Vote, Predicted Percentage of Dissatisfied and Physiologically Equivalent Temperature, together with air temperature in mimicking actual thermal sensation votes of street users obtained in 2011 in Glasgow City Centre. The Predicted Mean Vote/Predicted Percentage of Dissatisfied indices developed for controlled indoors show a surprising similarity to actual thermal sensation votes derived from outdoor surveys, than the Physiologically Equivalent Temperature developed specifically for the outdoors. The method of calculation of mean radiant temperature is the key to improved performance of Physiologically Equivalent Temperature, with fish-eye lens photographs improving its performance. The results also show air temperature alone has nearly equal predictive power of the actual thermal sensation. A preliminary comfort range for Glasgow is also derived and its limitations are explored. Practical application : The strong relation between thermal sensation votes and air temperature (Ta) enables future thermal comfort studies to predict the thermal comfort using easy-to-access Ta only. A current thermal comfort study in Glasgow aiming at developing a link between urban morphology and Ta is already using this strong relation to predict outdoor thermal comfort in the city centre. This helps to establish a correlation between these three factors.

Estudo de conforto em espaços abertos em região de clima temperado: o caso de Glasgow, Reino Unido

O estudo da sensacao de conforto termico em espacos abertos deve ser entendido como primordial para o planejamento climaticamente adequado de areas urbanas. Atraves do aumento da atratividade das areas abertas e do incentivo as atividades ao ar livre, o planejamento urbano norteado pelas preferencias termicas da populacao torna-se um agente facilitador do uso desses espacos. O presente trabalho analisa a sensacao termica de moradores de Glasgow, Reino Unido, localizada em regiao temperada, comparando respostas obtidas por meio de entrevistas estruturadas a indices utilizados pela meteorologia (Wind Chill e THSW) e em estudos de conforto (PET e PMV). Os dados foram coletados em 19 campanhas de monitoramento, no periodo do inverno ao verao de 2011. Para a coleta de dados, foi utilizada uma estacao Davis Vantage Pro2, contendo sensores de temperatura e umidade relativa, anemometro e piranometro. Foi confeccionado um termometro de globo, utilizado para obtencao da temperatura radiante media (TRM), equipado com um data logger (Tinytag-TGP-4500). Os resultados indicam que os indices THSW e PET foram os que mais se aproximaram da resposta termica dos entrevistados, podendo ser aplicados no entendimento das condicoes do clima na cidade e entorno de Glasgow.

Could refurbishment of “traditional” buildings reduce carbon emissions?

Purpose – Evaluate the post occupancy performance of a typical “traditional” building using multiple post occupancy evaluation (PoE) protocols against design intents to learn lessons about their suitability in meeting UKs climate change reduction targets. The paper aims to discuss these issues. Design/methodology/approach – PoE studies of a single case study, Norton Park, using three PoE methodologies. Gaps and overlaps between the PoE protocols are assessed and their role in improving energy and carbon emission performance of traditional buildings is explored. Findings – Refurbishment of the type undertaken in this case study could halve the energy use in traditional buildings with comparable savings in CO2 emission. Research limitations/implications – Traditional buildings could positively contribute to achieving climate change reduction targets; regular feedback loops improve performance over time. Practical implications – Quantification of the likely national benefit of focusing retrofit actions on t...

Energy demand prediction through novel random neural network predictor for large non-domestic buildings

Buildings are among the largest consumers of energy in the world. In developed countries, buildings currently consumes 40% of the total energy and 51% of total electricity consumption. Energy prediction is a key factor in reducing energy wastage. This paper presents and evaluates a novel RNN technique which is capable to predict energy utilization for a non-domestic large building comprising of 562 rooms. Initially, a model for the 562 rooms is developed using Integrated Environment Solutions Virtual Environment (IES-VE) software. The IES-VE model is simulated for one year and 10 essential data inputs i.e., air temperature, dry resultant temperature, internal gain, heating set point, cooling set point, plant profile, relative humidity, moisture content, heating plant sensible load, internal gain and number of people are measured. Datasets are generated from the measured data. RNN model is trained with this datasets for the energy demand prediction. Experiments are used to identify the accuracy of prediction. The results show that the proposed RNN based energy model achieves 0.00001 Mean Square Error (MSE) in just 86 epochs via Gradient Decent (GD) algorithm.

Planning for resilience

We live in a rapidly changing world characterised by increasing unpredictability and its associated risks. Many forces combine to add complexity to our once ordinary twentieth century pathways. Extremes of weather, climate change, costs of food, raw materials and energy and a destabilised global economy pile unprecedented pressures onto our lives. A plethora of factors affect the ways in which plan, design and build buildings and cities in a multiply-changing climate. Scotland is leading in many aspects of climate change research and this chapter on Planning for Climate Change is very timely, reflecting rapid changes in the field, in pace with the changing climate and the knock-on socio-economic impacts. Never since the emergence of the UK Planning Profession has there been a time when so much change has been imposed on the profession. The lessons contained in this chapter are key to the evolution of Planning here and around the world. The chapter starts with a brief overview of the background science of climate change and touch on the impacts of a warming world and more extreme weather on the following topics:

Effects of atmospheric stability and urban morphology on daytime intra-urban temperature variability for Glasgow, UK

This study investigates the joint effect of atmospheric conditions and urban morphology, expressed as the Sky View Factor (SVF), on intra-urban variability. The study has been carried out in Glasgow, UK, a shrinking city with a maritime temperate climate type, and findings could guide future climate adaptation plans in terms of morphology and services provided by the municipality to overcome thermal discomfort in outdoor settings. In this case, SVF has been used as an indicator of urban morphology. The modified Pasquill-Gifford-Turner (PGT) classification system was adopted for classifying the temperature monitoring periods according to atmospheric stability conditions. Thirty two locations were selected on the basis of SVF with a wide variety of urban shapes (narrow streets, neighbourhood green spaces, urban parks, street canyons and public squares) and compared to a reference weather station during a total of twenty three transects during late spring and summer in 2013. Maximum daytime intra-urban temperature differences were found to be strongly correlated with atmospheric stability classes. Furthermore, differences in air temperature are noticeable in urban canyons, with a direct correlation to the sites SVF (or sky openness) and with an inverse trend under open-air conditions.

Connecting the realms of urban form, density and microclimate

The effects of urban form on local climate, thermal comfort and energy consumption have been well researched during the past 50 years. Starting with Olgyay’s (1963) work on bio-regionalism, researc...

Interdependent energy relationships between buildings at the street scale

ABSTRACT Regulated energy loads of buildings are typically explored at the scale of individual buildings, often in isolated (and idealized) circumstances. By comparison, little research currently exists on the performance of building groups that accounts for the interactions between buildings. Consequently, the energy efficiency (or penalty) of different urban configurations (such as a city street) is overlooked. The present paper examines the energy demand of a city street in London, UK, which is comprised of typical office buildings with internal energy gains associated with daytime occupancy. Simulations are performed for office buildings placed in urban canyons that are defined by the ratio of building height (H) to street width (W). The results show the annual energy demand is dominated by the cooling load, which can be significantly reduced through street design that provides shading by increasing H/W. However, the ‘best’ street design for modern office buildings may be incompatible with that for residences or, for that matter, outdoor climates.