• Energy Research
• 11. Sustainability close
• Sensors close

Multistep power consumption forecasting is smart grid electricity management’s most decisive problem. Moreover, it is vital to develop operational strategies for electricity management systems in smart cities for commercial and residential users. However, an efficient electricity load forecasting model is required for accurate electric power management in an intelligent grid, leading to customer financial benefits. In this article, we develop an innovative framework for short-term electricity load forecasting, which includes two significant phases: data cleaning and a Residual Convolutional Neural Network (R-CNN) with multilayered Long Short-Term Memory (ML-LSTM) architecture. Data preprocessing strategies are applied in the first phase over raw data. A deep R-CNN architecture is developed in the second phase to extract essential features from the refined electricity consumption data. The output of R-CNN layers is fed into the ML-LSTM network to learn the sequence information, and finally, fully connected layers are used for the forecasting. The proposed model is evaluated over residential IHEPC and commercial PJM datasets and extensively decreases the error rates compared to baseline models.

The air temperature increase in urban centers can lead to problems such as increased energy consumption associated to air conditioning, the intensification of pollution, human discomfort and health problems. In this context, the building envelope plays an important role in urban thermal equilibrium. Energy efficiency rating systems for buildings (LEED—Leadership in Energy and Environmental Design, AQUA—High Environmental Quality, PROCEL Edifica, etc.) stimulate energy efficiency actions in the built environment, considering, for example, the envelope and energy efficiency initiatives in buildings. Research carried out recently has shown that monitoring of buildings can provide important information about building performance, supporting building control strategies and enabling actions aimed at improving energy efficiency and thermal comfort. More specifically, wireless sensors are also being used to monitor buildings. This work proposes and presents the development of a surface temperature sensor that can support actions to enhance energy efficiency in the built environment, meeting the requirements proposed by the energy efficiency rating systems of buildings. This sensor must have characteristics such as low cost, the storage capacity of a large amount of data and the possibility of remote monitoring of the collected temperatures. Computer simulations and validation tests were carried out showing that the proposed sensor allows the remote monitoring (using a wireless transmission system) of the surface temperature in buildings, respecting the requirements of high storage capability and low cost.

The Internet of Things (IoT) is a key technology to interconnect the real and digital worlds, enabling the development of smart cities and services. The timely collection of data is essential for IoT services. In scenarios such as agriculture, industry, transportation, public safety, and health, wireless sensor networks (WSNs) play a fundamental role in fulfilling this task. However, WSNs are commonly deployed in sensitive and remote environments, thus facing the challenge of jamming attacks. Therefore, these networks need to have the ability to detect such attacks and adopt countermeasures to guarantee connectivity and operation. In this work, we propose a novel clustering-based self-healing strategy to overcome jamming attacks, in which we denominate fairness cooperation with power allocation (FCPA). The proposed strategy, aware of the presence of the jammer, clusters the network and designates a cluster head that acts as a sink node to collect information from its cluster. Then, the most convenient routes to overcome the jamming are identified and the transmit power is adjusted to the minimum value required to guarantee the reliability of each link. Finally, through the weighted use of the relays, the lifetime of each subnetwork is extended. To show the impact of each capability of FCPA, we compare it with multiple benchmarks that only partially possess these capabilities. In the proposal evaluation, we consider a WSN composed of 64 static nodes distributed in a square area. Meanwhile, to assess the impact of the jamming attack, we consider seven different locations of the attacker. All experiments started with each node’s battery full and stopped after one of these batteries was depleted. In these scenarios, FCPA outperforms all other strategies by more than 50% of the information transmitted, due to the efficient use of relay power, through the weighted balance of cooperative routes. On average, FCPA permits 967,961 kb of information transmitted and 63% of residual energy, as energy efficiency, from all the analyzed scenarios. Additionally, the proposed clustering-based self-healing strategy adapts to the change of jammer location, outperforming the rest of the strategies in terms of information transmitted and energy efficiency in all evaluated scenarios.

Smart meter (SM) deployment in the residential context provides a vast amount of data of high granularity at the individual household level. In this context, the choice of temporal resolution for describing household load profile features has a crucial impact on the results of any action or assessment. This study presents a methodology that makes two new contributions. Firstly, it proposes periodograms along with autocorrelation and partial autocorrelation analyses and an empirical distribution-based statistical analysis, which are able to describe household consumption profile features with greater accuracy. Secondly, it proposes a framework for data collection in households at a high sampling frequency. This methodology is able to analyze the influence of data granularity on the description of household consumption profile features. Its effectiveness was confirmed in a case study of four households in Spain. The results indicate that high-resolution data should be used to consider the full range of consumption load fluctuations. Nonetheless, the accuracy of these features was found to largely depend on the load profile analyzed. Indeed, in some households, accurate descriptions were obtained with coarse-grained data. In any case, an intermediate data-resolution of 5 s showed feature characterization closer to those of 0.5 s.

The growing global demand for food and the environmental impact caused by agriculture have made this activity increasingly dependent on electronics, information technology, and telecommunications technologies. In Colombia, agriculture is of great importance not only as a commercial activity, but also as a source of food and employment. However, the concept of smart agriculture has not been widely applied in this country, resulting in the high production of various types of crops due to the planting of large areas of land, rather than optimization of the processes involved in the activity. Due to its technical characteristics and the radio spectrum considered in its deployment, 5G can be seen as one of the technologies that could generate the greatest benefits for the Colombian agricultural sector, especially in the most remote rural areas, which currently lack mobile network coverage. This article provides an overview of the current 5G technology landscape in Colombia and presents examples of possible 5G/IoT applications that could be developed in Colombian fields. The results show that 5G could facilitate the implementation of the smart farm in Colombia, improving current production and efficiency. It is useful when designing 5G implementation plans and strategies, since it categorizes crops by regions and products. This is based on budget availability, population density, and regional development plans, among others.

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.