Muhammad Waseem Ahmad

Energy prediction models are used in buildings as a performance evaluation engine in advanced control and optimisation, and in making informed decisions by facility managers and utilities for enhanced energy efficiency. Simplified and data-driven models are often the preferred option where pertinent information for detailed simulation are not available and where fast responses are required. We compared the performance of the widely-used feed-forward back-propagation artificial neural network (ANN) with random forest (RF), an ensemble-based method gaining popularity in prediction – for predicting the hourly HVAC energy consumption of a hotel in Madrid, Spain. Incorporating social parameters such as the numbers of guests marginally increased prediction accuracy in both cases. Overall, ANN performed marginally better than RF with root-mean-square error (RMSE) of 4.97 and 6.10 respectively. However, the ease of tuning and modelling with categorical variables offers ensemble-based algorithms an advantage for dealing with multi-dimensional complex data, typical in buildings. RF performs internal cross-validation (i.e. using out-of-bag samples) and only has a few tuning parameters. Both models have comparable predictive power and nearly equally applicable in building energy applications.

Buildings are responsible for 40% of global energy use and contribute towards 30% of the total CO2 emissions. The drive to reduce energy consumption and associated greenhouse gas emissions from buildings has acted as a catalyst in the increasing installation of meters and sensors for monitoring energy use and indoor environmental conditions in buildings. This paper reviews the state-of-the-art in building energy metering and environmental monitoring, including their social, economic, environmental and legislative drivers. The integration of meters and sensors with existing building energy management systems (BEMS) is critically appraised, especially with regard to communication technologies and protocols such as ModBus, M-Bus, Ethernet, Cellular, ZigBee, WiFi and BACnet. Findings suggest that energy metering is covered in existing policies and regulations in only a handful of countries. Most of the legislations and policies on energy metering in Europe are in response to the Energy Performance of Buildings Directive (EPBD), 2002/91/EC. However, recent developments in policy are pointing towards more stringent metering requirements in future, moving away from voluntary to mandatory compliance. With regards to metering equipment, significant developments have been made in the recent past on miniaturisation, accuracy, robustness, data storage, ability to connect using multiple communication protocols, and the integration with BEMS and the Cloud – resulting in a range of available solutions, selection of which can be challenging. Developments in communication technologies, in particular in low-power wireless such as ZigBee and Bluetooth LE (BLE), are enabling cost-effective machine to machine (M2M) and internet of things (IoT) implementation of sensor networks. Privacy and data protection, however, remain a concern for data aggregators and end-users. The standardization of network protocols and device functionalities remains an active area of research and development, especially due to the prevalence of many protocols in the BEMS industry. Available solutions often lack interoperability between hardware and software systems, resulting in vendor lock-in. The paper provides a comprehensive understanding of available technologies for energy metering and environmental monitoring; their drivers, advantages and limitations; factors affecting their selection and future directions of research and development – for use a reference, as well as for generating further interest in this expanding research area.

Buildings are responsible for 40% of global energy use and contribute towards 30% of the total CO2 emissions. The drive to reduce energy use and associated greenhouse gas emissions from buildings has acted as a catalyst in the development of advanced computational methods for energy efficient design, management and control of buildings and systems. Heating, ventilation and airconditioning (HVAC) systems are the major source of energy consumption in buildings and an ideal candidate for substantial reductions in energy demand. Significant advances have been made in the past decades on the application of computational intelligence (CI) techniques for HVAC design, control, management, optimization, and fault detection and diagnosis. This article presents a comprehensive and critical review on the theory and applications of CI techniques for prediction, optimization, control and diagnosis of HVAC systems.The analysis of trends reveals the minimization of energy consumption was the key optimization objective in the reviewed research, closely followed by the optimization of thermal comfort, indoor air quality and occupant preferences. Hard-coded Matlab program was the most widely used simulation tool, followed by TRNSYS, EnergyPlus, DOE–2, HVACSim+ and ESP–r. Metaheuristic algorithms were the preferred CI method for solving HVAC related problems and in particular genetic algorithms were applied in most of the studies. Despite the low number of studies focussing on MAS, as compared to the other CI techniques, interest in the technique is increasing due to their ability of dividing and conquering an HVAC optimization problem with enhanced overall performance. The paper also identifies prospective future advancements and research directions.

Artificial lighting can increase a energy consumption. On the other hand, the availability of daylight in occupied spaces can reduce energy consumption while positively contributing to occupant wellbeing. However, daylight entering the space through windows needs to be reconciled with heat loss during winter and heat gain during summer, which may affect thermal comfort. In this research, a genetic algorithm is used to optimize the operation schedules of window blinds in a school classroom to enhance occupant visual comfort level. The objective of the optimization study was to reduce the energy consumption while maintaining the daylighting illuminance within the range of 100 lux to 2000 lux. EnergyPlus simulation software was employed as the daylighting and thermal performance calculation engine. The findings evidenced that the proposed genetic algorithm based schedule optimization reduced the HVAC and lighting energy consumption while giving preference to The results showed that the performance of the discussed method could also depend on different seasons. The genetic algorithm reduced the negative impact of solar gains on energy consumption in summer by closing the window blinds according to the solar angle.