1Phase change materials (PCM) with their high thermal storage density at almost isothermal conditions 2 and their availability at wide range of phase transitions promote an effective mode of storing thermal energy. 3Literature survey evidently shows that paraffins and salt hydrates provide better thermal performance at 4 competitive cost. This review paper is focused on the classification of various paraffins and salt hydrates. To 5 acquire long term productivity of LHS system, the thermo-physical stability of both paraffins and salt hydrates; 6 and their compatibility with various plastic and metallic container materials play a vital role. Likewise, the 7 lower thermal conductivity of PCMs affects the thermal performance of LHS system. This article reviews the 8 various thermo-physical performance enhancement techniques such as influence of container shape and its 9 orientation, employment of fins and high conductivity additives, multi-PCM approach and PCM encapsulation. 10The performance enhancement techniques are focused to improve the phase transition rate, thermal 11 conductivity, latent heat storage capacity and thermo-physical stability. This review provides an understanding 12 on how to maximize thermal utilization of PCM. This understanding is underpinned by an analysis of PCM- 13Container compatibility and geometrical configuration of the container.

Electric energy forecasting domain attracts researchers due to its key role in saving energy resources, where mainstream existing models are based on Gradient Boosting Regression, Artificial Neural Networks, Extreme Learning Machine and Support Vector Machine. These models encounter high-level of non-linearity between input data and output predictions and limited adoptability in real-world scenarios. Meanwhile, energy forecasting domain demands more robustness, higher prediction accuracy and generalization ability for real-world implementation. In this paper, we achieve the mentioned tasks by developing a hybrid sequential learning-based energy forecasting model that employs Convolution Neural Network and Gated Recurrent Units into a unified framework for accurate energy consumption prediction. The proposed framework has two major phases: (1) data refinement and (2) training, where the data refinement phase applies preprocessing strategies over raw data. In the training phase, CNN features are extracted from input dataset and fed in to GRU, that is selected as optimal and observed to have enhanced sequence learning abilities after extensive experiments. The proposed model is an effective alternative to the previous hybrid models in terms of computational complexity as well prediction accuracy, due to the representative features' extraction potentials of CNNs and effectual gated structure of multi-layered GRU. The experimental evaluation over existing energy forecasting datasets reveal the better performance of our method in terms of preciseness and efficiency. The proposed method achieved the smallest error rate on individual Appliances Energy prediction and household electric power consumption datasets, when compared to other baseline models.

Due to industrialization and the rising demand for energy, global energy consumption has been rapidly increasing. Recent studies show that the biggest portion of energy is consumed in residential buildings, i.e., in European Union countries up to 40% of the total energy is consumed by households. Most residential buildings and industrial zones are equipped with smart sensors such as metering electric sensors, that are inadequately utilized for better energy management. In this paper, we develop a hybrid convolutional neural network (CNN) with an long short-term memory autoencoder (LSTM-AE) model for future energy prediction in residential and commercial buildings. The central focus of this research work is to utilize the smart meters’ data for energy forecasting in order to enable appropriate energy management in buildings. We performed extensive research using several deep learning-based forecasting models and proposed an optimal hybrid CNN with the LSTM-AE model. To the best of our knowledge, we are the first to incorporate the aforementioned models under the umbrella of a unified framework with some utility preprocessing. Initially, the CNN model extracts features from the input data, which are then fed to the LSTM-encoder to generate encoded sequences. The encoded sequences are decoded by another following LSTM-decoder to advance it to the final dense layer for energy prediction. The experimental results using different evaluation metrics show that the proposed hybrid model works well. Also, it records the smallest value for mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE) and mean absolute percentage error (MAPE) when compared to other state-of-the-art forecasting methods over the UCI residential building dataset. Furthermore, we conducted experiments on Korean commercial building data and the results indicate that our proposed hybrid model is a worthy contribution to energy forecasting.

No abstract

This article is focused on numerical analyses of commercially available metal-oxides as potential nano-additives for paraffin in thermal storage applications. Technical and economic prospects of metal-oxides based nano-PCMs are evaluated to help formulate selection criterion for nano-additives to achieve optimum thermal performance at acceptable cost. Numerical model based on enthalpy-porosity technique is developed which incorporates natural convection and transient variations in thermo-physical properties of nano-PCM. Numerical model is simulated for charging and discharging cycles of nano-PCMs in shell and tube heat exchanger at controlled temperatures. Transient simulations help in analysing heat transfer categorisation and isotherms distributions, solid-liquid interfaces propagations, charging and discharging rates, and overall thermal enthalpy. Inclusion of nano-particles increase the effective thermal conductivity and surface area for heat transfer, which results in enhanced charging and discharging rates. The conductive heat transfer, peak heat flux, charging and discharging rates are significantly enhanced by increasing volume concentration of nano-particles. The percentage enhancement in charging rates of SiO 2 based nano-PCM samples with 1% and 5% are 29.45% and 41.04%, respectively. Likewise, the discharging rates are improved by 21.09% and 30.08%, respectively. However, an increase in volume concentration reduces natural convection and overall thermal enthalpy, and increases total cost of nano-PCM. For instance, the percentage reductions in total enthalpy of CuO based nano-PCM samples with 1% and 5% volume concentrations are 8.01% and 32.14%, respectively. Likewise, the total costs are increased from 14.26 €/kg for base paraffin to 70.89-309.33 €/kg, respectively. Hence, the significance and originality of this research lies within evaluation and identification of preferable metal-oxides with higher potential for improving thermal performance at reasonable cost. This article will help bring significant impact to large-scale utilisation of low-carbon and clean energy technology in domestic and commercial applications.

1In this article, the discharging cycles of paraffin in novel latent heat storage (LHS) unit are 2 experimentally investigated. The novel LHS unit includes shell and tube with longitudinal fins based 3 heat exchanger and paraffin as thermal energy storage material. The experimental investigations are 4 focused on identifying the transient temperature performance, effective mode of heat transfer, 5accumulative thermal energy discharge and mean discharge power of paraffin in LHS unit. Moreover, 6the influences of operating conditions such as inlet temperature and volume flow rate of heat transfer 7 fluid (HTF) on thermal behaviour of LHS unit are experimentally studied. The transient temperature 8profiles and photographic characterisation of liquid-solid transition of paraffin in LHS unit provide a 9 good understanding of temperature distribution and dominant mode of heat transfer. It is noticed that 10 during discharging cycles, natural convection has an insignificant impact on thermal performance of 11 LHS unit. However, due to inclusion of extended longitudinal fins, conduction is the dominant mode 12 of heat transfer. It is noticed that due to development of solidified paraffin around tubes and 13longitudinal fins, the overall thermal resistance is increased and thus, discharging rate is affected. 14 However, by regulating inlet temperature or volume flow rate of HTF, the influence of overall thermal 15 resistance is minimised. Mean discharge power is enhanced by 36.05% as the inlet temperature is 16reduced from 15 o C to 5 o C. Likewise, the mean discharge power is improved by 49.75% as the 17 volume flow rate is increased from 1.5 l/min to 3 l/min. Similarly, with an increase in volume flow 18 rate, the discharge time of equal amount of thermal energy 12.09 MJ is reduced by 24%. It is 19established that by adjusting operating conditions, the required demand of output temperature and 20 mean discharge power can be attained. Furthermore, this novel LHS unit can meet large scale thermal 21 energy demands by connecting several units in parallel and thus, it has potential to be employed in 22wide-ranging domestic and commercial applications. 23 24 Keywords 25 Thermal energy storage, Latent heat storage, Discharge cycle, Phase change materials, Heat transfer, 26 Shell and tube heat exchanger 27 28

Video anomaly recognition in smart cities is an important computer vision task that plays a vital role in smart surveillance and public safety but is challenging due to its diverse, complex, and infrequent occurrence in real-time surveillance environments. Various deep learning models use significant amounts of training data without generalization abilities and with huge time complexity. To overcome these problems, in the current work, we present an efficient light-weight convolutional neural network (CNN)-based anomaly recognition framework that is functional in a surveillance environment with reduced time complexity. We extract spatial CNN features from a series of video frames and feed them to the proposed residual attention-based long short-term memory (LSTM) network, which can precisely recognize anomalous activity in surveillance videos. The representative CNN features with the residual blocks concept in LSTM for sequence learning prove to be effective for anomaly detection and recognition, validating our model’s effective usage in smart cities video surveillance. Extensive experiments on the real-world benchmark UCF-Crime dataset validate the effectiveness of the proposed model within complex surveillance environments and demonstrate that our proposed model outperforms state-of-the-art models with a 1.77%, 0.76%, and 8.62% increase in accuracy on the UCF-Crime, UMN and Avenue datasets, respectively.

No abstract