The purpose of this paper is to provide a source of information on thermal energy use in buildings, its drivers, and their past, present and future trends on a global and regional basis. Energy use in buildings forms a large part of global and regional energy demand. The importance of heating and cooling in total building energy use is very diverse with this share varying between 18% and 73%. Biomass is still far the dominant fuel when a global picture is considered; the role of electricity is substantially growing, and the direct use of coal is disappearing from this sector, largely replaced by electricity and natural gas in the most developed regions. This paper identifies the different drivers of heating and cooling energy demand, and decomposes this energy demand into key drivers based on a Kaya identity approach: number of households, persons per household, floor space per capita and specific energy consumption for residential heating and cooling; and GDP, floor space per GDP, and specific energy consumption for commercial buildings. This paper also reviews the trends in the development of these drivers for the present, future – and for which data were available, for the past – in 11 world regions as well as globally. Results show that in a business-as-usual scenario, total residential heating and cooling energy use is expected to more or less stagnate, or slightly decrease, in the developed parts of the world. In contrast, commercial heating and cooling energy use will grow in each world region. Finally, the results show that per capita total final residential building energy use has been stagnating in the vast majority of world regions for the past three decades, despite the very significant increases in energy service levels in each of these regions.

Heating and cooling energy trends and drivers in buildings

• Review of applications of transfer learning (TL) for smart buildings. • Identification of main application areas of TL in smart buildings. • Insights on the most-effective TL techniques for each application area. • Discussion on current research gaps and future opportunities. Smart buildings play a crucial role toward decarbonizing society, as globally buildings emit about one-third of greenhouse gases. In the last few years, machine learning has achieved a notable momentum that, if properly harnessed, may unleash its potential for advanced analytics and control of smart buildings, enabling the technique to scale up for supporting the decarbonization of the building sector. In this perspective, transfer learning aims to improve the performance of a target learner exploiting knowledge in related environments. The present work provides a comprehensive overview of transfer learning applications in smart buildings, classifying and analyzing 77 papers according to their applications, algorithms, and adopted metrics. The study identified four main application areas of transfer learning: (1) building load prediction, (2) occupancy detection and activity recognition, (3) building dynamics modeling, and (4) energy systems control. Furthermore, the review highlighted the role of deep learning in transfer learning applications that has been used in more than half of the analyzed studies. The paper also discusses how to integrate transfer learning in a smart building’s ecosystem, identifying, for each application area, the research gaps and guidelines for future research directions. 

Transfer learning for smart buildings: A critical review of algorithms, applications, and future perspectives

Hourly energy consumption prediction of an office building based on ensemble learning and energy consumption pattern classification

Photovoltaic (PV) systems are subject to failures during their operation due to the aging effects and external/environmental conditions. These faults may affect the different system components such as PV modules, connection lines, converters/inverters, which can lead to a decrease in the efficiency, performance, and further system collapse. Thus, a key factor to be taken into consideration in high-efficiency grid-connected PV systems is the fault detection and diagnosis (FDD). The performance of the FDD method depends mainly on the quality of the extracted features including real-time changes, phase changes, trend changes, and faulty modes. Thus, the data representation learning is the core stage of intelligent FDD techniques. Recently, due to the enhancement of computing capabilities, the increase of the big data use, and the development of effective algorithms, the deep learning (DL) tool has witnessed a great success in data science. Therefore, this paper proposes an extensive review on deep learning based FDD methods for PV systems. After a brief description of the DL-based strategies, techniques for diagnosing PV systems proposed in recent literature are overviewed and analyzed to point out their differences, advantages and limits. Future research directions towards the improvement of the performance of the DL-based FDD techniques are also discussed. This review paper aims to systematically present the development of DL-based FDD for PV systems and provide guidelines for future research in the field.

/pdf/deep-learning-based-fault-diagnosis-of-photovoltaic-systems-4km4iu1kry.pdf

Deep Learning-Based Fault Diagnosis of Photovoltaic Systems: A Comprehensive Review and Enhancement Prospects

The high proportion of energy consumed in buildings has engendered the manifestation of many environmental problems which deploy adverse impacts on the existence of mankind. The prediction of building energy use is essentially proclaimed to be a method for energy conservation and improved decision-making towards decreasing energy usage. Also, the construction of energy efficient buildings will aid the reduction of total energy consumed in newly constructed buildings. Machine Learning (ML) method is recognised as the best suited approach for producing desired outcomes in prediction task. Hence, in several studies, ML has been applied in the field of energy consumption of operational building. However, there are not many studies investigating the suitability of ML methods for forecasting the potential building energy consumption at the early design phase to reduce the construction of more energy inefficient buildings. To address this gap, this paper presents the utilization of several machine learning techniques namely Artificial Neural Network (ANN), Gradient Boosting (GB), Deep Neural Network (DNN), Random Forest (RF), Stacking, K Nearest Neighbour (KNN), Support Vector Machine (SVM), Decision tree (DT) and Linear Regression (LR) for predicting annual building energy consumption using a large dataset of residential buildings. This study also examines the effect of the building clusters on the model performance. The novelty of this paper is to develop a model that enables designers input key features of a building design and forecast the annual average energy consumption at the early stages of development. This result reveals DNN as the most efficient predictive model for energy use at the early design phase and this presents a motivation for building designers to utilize it before construction to make informed decision, manage and optimize design.

Building energy consumption prediction for residential buildings using deep learning and other machine learning techniques

Transfer learning-based strategies for fault diagnosis in building energy systems

Quantitative evaluation of the building energy performance based on short-term energy predictions

Artificial intelligence shows powerful capacity in modern building fault detection and diagnosis (FDD) systems. Existing data-driven-based FDD models are typically developed based on experimental data or simulation data and their performance highly depend on the data quality. Nevertheless, the available data in real buildings are often uncertain due to innate measurement errors, discontinuous sampling, sensor aging, etc. Accordingly, existing data-driven-based approaches may not present sufficient values for practical applications. This paper investigates the impacts of data uncertainty on data-driven-based building FDD model from two levels. At the high level, the impacts of data uncertainty on performance of FDD model are examined under different input feature numbers, i.e., 3, 8, 22 and 36. At the low level, the impacts of data uncertainty under various input features are evaluated at four uncertainty levels. The Coefficient of Performance Degradation (CPD) index is designed to quantify the impacts of data uncertainty. The chiller operation data of the ASHRAE 1043-RP project is employed as a case study. Diagnosis results reveal that the performance of FDD model will decline as the reduction of feature number under uncertain inputs. Besides, the diagnostic accuracy dramatically descends with increases of uncertainty level. The maximum accuracy decline is 20.9% when uncertainty level of kW increased from ±0.0 to ±1.0. Moreover, results show the data uncertainties cause greater effects on diagnosing global fault rather than diagnosing local fault.

Xin Li

Papers

Hourly energy consumption prediction of an office building based on ensemble learning and energy consumption pattern classification

Transfer learning-based strategies for fault diagnosis in building energy systems

Quantitative evaluation of the building energy performance based on short-term energy predictions

Impacts of data uncertainty on the performance of data-driven-based building fault diagnosis

A statistical-based online cross-system fault detection method for building chillers