Machine learning based system for managing energy efficiency of public sector as an approach towards smart cities

Contributions to Power Grid System Analysis Based on Clustering Techniques

The topic addressed in this article is part of the current concerns of modernizing power systems by promoting and implementing the concept of smart grid(s). The concepts of smart metering, a smart home, and an electric car are developing simultaneously with the idea of a smart city by developing high-performance electrical equipment and systems, telecommunications technologies, and computing and infrastructure based on artificial intelligence algorithms. The article presents contributions regarding the modeling of consumer classification and load profiling in electrical power networks and the efficiency of clustering techniques in their profiling as well as the simulation of the load of medium-voltage/low-voltage network distribution transformers to electricity meters.

Digital economy, energy efficiency, and carbon emissions: Evidence from provincial panel data in China

Improving energy efficiency and lowering carbon emissions are of great importance to realize the "dual carbon" goal of carbon peak and carbon neutrality. Digital economy is a new engine of economic development, but whether or how it affects energy efficiency and carbon emissions are unclear. Utilizing panel data of China's 30 provinces from 2012 to 2019, this study empirically explores the relationships among digital economy, energy efficiency, and carbon emissions. Meanwhile, from the perspective of energy efficiency, applying mediation models and panel threshold model, it analyzes the direct, indirect, and nonlinear influencing mechanisms of digital economy on carbon emissions. The results reflect that the development of digital economy in China intensifies carbon emissions. Energy efficiency serves as a vital partial mediator between the two. The enhancement of energy efficiency can lower carbon emissions. However, the development of digital economy is not conducive to improving energy efficiency, thereby, indirectly increasing carbon emissions. The mediating effect of energy efficiency accounts for 30.58 % of the total effect of digital economy on carbon emissions. Meanwhile, taking energy efficiency into account, the impact of digital economy on carbon emissions has a significant double-threshold effect and presents an N-shaped trend. [0.824, 0.912] is the optimal range of energy efficiency, within which the growth of the digital economy can empower carbon emission abatement to some extent. In addition, the expansion of population size, the coal-based energy consumption structure, and the industrial structure significantly increase carbon emissions. The improvements in living standards and environmental regulations can help to decrease carbon emissions, but the emission abatement effects are not significant. Those conclusions reveal the importance of optimizing the level and quality of digital economy and adopting differentiated digital economy development policies based on energy efficiency to achieve carbon emission reduction.

Smart City Applications to Promote Citizen Participation in City Management and Governance: A Systematic Review

This systematic review aimed to provide a comprehensive view of (1) the purposes of research studies using smart city infrastructures to promote citizen participation in the cities’ management and governance, (2) the characteristics of the proposed solutions in terms of data sources, data quality, and data security and privacy mechanisms, as well, as strategies to incentivize citizen participation, and (3) the development stages of the applications being reported. An electronic search was conducted combining relevant databases and keywords, and 76 studies were included after a selection process. The results show a current interest in developing applications to promote citizen participation to identify urban problems and contribute to decision-making processes. Most of the included studies considered citizens as agents able to report issues (e.g., issues related to the maintenance of urban infrastructures or the mobility in urban spaces), monitor certain environmental parameters (e.g., air or acoustic pollution), and share opinions (e.g., opinions about the performance of local authorities) to support city management. Moreover, a minority of the included studies developed collaborative applications to involve citizens in decision-making processes in urban planning, the selection of development projects, and deepening democratic values. It is possible to conclude about the existence of significant research related to the topic of this systematic review, but also about the need to deepen mechanisms to guarantee data quality and data security and privacy, to develop strategies to incentivize citizen participation, and to implement robust experimental set-ups to evaluate the impact of the developed applications in daily contexts.

Energy Efficiency through the Implementation of an AI Model to Predict Room Occupancy Based on Thermal Comfort Parameters

Room occupancy prediction based on indoor environmental quality may be the breakthrough to ensure energy efficiency and establish an interior ambience tailored to each user. Identifying whether temperature, humidity, lighting, and CO2 levels may be used as efficient predictors of room occupancy accuracy is needed to help designers better utilize the readings and data collected in order to improve interior design, in an effort to better suit users. It also aims to help in energy efficiency and saving in an ever-increasing energy crisis and dangerous levels of climate change. This paper evaluated the accuracy of room occupancy recognition using a dataset with diverse amounts of light, CO2, and humidity. As classification algorithms, K-nearest neighbors (KNN), hybrid Adam optimizer–artificial neural network–back-propagation network (AO–ANN (BP)), and decision trees (DT) were used. Furthermore, this research is based on machine learning interpretability methodologies. Shapley additive explanations (SHAP) improve interpretability by estimating the significance values for each feature for classifiers applied. The results indicate that the KNN performs better than the DT and AO-ANN (BP) classification models have 99.5%. Though the two classifiers are designed to evaluate variations in interpretations, we must ensure that they have accurate detection. The results show that SHAP provides successful implementation following these metrics, with differences detected amongst classifier models that support the assumption that model complexity plays a significant role when predictability is taken into account.

Management of Smart and Sustainable Cities in the Post-COVID-19 Era: Lessons and Implications

Nowadays, the concept of smart sustainable governance is wrapped around basic principles such as: (i) transparency, (ii) accountability, (iii) stakeholders’ involvement, and iv) citizens’ participation. It is through these principles that are influenced by information and communication technologies (ICT), Internet of Things (IoT), and artificial intelligence, that the practices employed by citizens and their interaction with electronic government (e-government) are diversified. Previously, the misleading concepts of the smart city implied only the objective of the local level or public officials to utilize technology. However, the recent European experience and research studies have led to a more comprehensive notion that refers to the search for intelligent solutions which allow modern sustainable cities to enhance the quality of services provided to citizens and to improve the management of urban mobility. The smart city is based on the usage of connected sensors, data management, and analytics platforms to improve the quality and functioning of built-environment systems. The aim of this paper is to understand the effects of the pandemic on smart cities and to accentuate major exercises that can be learned for post-COVID sustainable urban management and patterns. The lessons and implications outlined in this paper can be used to enforce social distancing community measures in an effective and timely way, and to optimize the use of resources in smart and sustainable cities in critical situations. The paper offers a conceptual overview and serves as a stepping-stone to extensive research and the deployment of sustainable smart city platforms and intelligent transportation systems (a sub-area of smart city applications) after the COVID-19 pandemic using a case study from Russia. Overall, our results demonstrate that the COVID-19 crisis encompasses an excellent opportunity for urban planners and policy makers to take transformative actions towards creating cities that are more intelligent and sustainable.

Feature Extraction of Anomaly Electricity Usage Behavior in Residence Using Autoencoder

Due to the climate crisis, energy-saving issues and carbon reduction have become the top priority for all countries. Owing to the increasing popularity of advanced metering infrastructure and smart meters, the cost of acquiring data on residential electricity consumption has substantially dropped. This change promotes the analysis of residential electricity consumption, which features both small and complicated consumption behaviors, using machine learning to become an important research topic among various energy saving and carbon reduction measures. The main subtopic of this subject is the identification of abnormal electricity consumption behaviors. At present, anomaly detection is typically realized using models based on low-level features directly collected by sensors and electricity meters. However, due to the significant number of dimensions and a large amount of redundant information in these low-level features, the training efficiency of the model is often low. To overcome this, this study adopts an autoencoder, which is a deep learning technology, to extract the high-level electricity consumption information of residential users to improve the anomaly detection performance of the model. Subsequently, this study trains one-class SVM models for anomaly detection by using the high-level features of five actual residential users to verify the benefits of high-level features.

Hybrid Machine Learning Model for Electricity Consumption Prediction Using Random Forest and Artificial Neural Networks

Predicting electricity consumption is notably essential to provide a better management decision and company strategy. This study presents a hybrid machine learning model by integrating dimensionality reduction and feature selection algorithms with a backpropagation neural network (BPNN) to predict electricity consumption in Thailand. The predictive models are developed and tested using an actual dataset with related predictor variables from public sources. An open geospatial data gathered from a real service as well as geographical, climatic, industrial, household information are used to train, evaluate, and validate these models. Machine learning methods such as principal component analysis (PCA), stepwise regression (SWR), and random forest (RF) are used to determine the significant predictor variables. The predictive models are constructed using the BPNN with all available variables as baseline for comparison and selected variables from dimensionality reduction and feature selection methods. Along with creating a predictive model, the most related predictors of energy consumption are also selected. From the comparison, the hybrid model of RF with BPNN consistently outperforms the other models. Thus, the proposed hybrid machine learning model presented from this study can predict electricity consumption for planning and managing the energy demand.

Understanding Sustainable Energy in the Context of Smart Cities: A PRISMA Review

In the context of smart cities, sustainability is an essential dimension. One of the ways to achieve sustainability and reduce the emission of greenhouse gases in smart cities is through the promotion of sustainable energy. The demand for affordable and reliable electrical energy requires different energy sources, where the cost of production often outweighs the environmental factor. This paper aims to investigate the ways smart cities promote sustainability in the electricity sector. For this, a systematic literature review using the PRISMA protocol was employed as the methodological approach. In this review, 154 journal articles were thoroughly analyzed. The results were grouped according to the themes and categorized into energy efficiency, renewable energies, and energy and urban planning. The study findings revealed the following: (a) global academic publication landscape for smart city and energy sustainability research; (b) unbalanced publications when critically evaluating geographical continents’ energy use intensity vs. smart cities’ energy sustainability research outcomes; (c) there is a heavy concentration on the technology dimension of energy sustainability and efficiency, and renewables topics in the literature, but much less attention is paid to the energy and urban planning issues. The insights generated inform urban and energy authorities and provide scholars with directions for prospective research.

New Opportunities, Challenges, and Applications of Edge-AI for Connected Healthcare in Internet of Medical Things for Smart Cities

Revolution in healthcare can be experienced with the advancement of smart sensorial things, Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL), Internet of Medical Things (IoMT), and edge analytics with the integration of cloud computing. Connected healthcare is receiving extraordinary contemplation from the industry, government, and the healthcare communities. In this study, several studies published in the last 6 years, from 2016 to 2021, have been selected. The selection process is represented through the Prisma flow chart. It has been identified that these increasing challenges of healthcare can be overcome by the implication of AI, ML, DL, Edge AI, IoMT, 6G, and cloud computing. Still, limited areas have implemented these latest advancements and also experienced improvements in the outcomes. These implications have shown successful results not only in resolving the issues from the perspective of the patient but also from the perspective of healthcare professionals. It has been recommended that the different models that have been proposed in several studies must be validated further and implemented in different domains, to validate the effectiveness of these models and to ensure that these models can be implemented in several regions effectively.

Stakeholders’ Perceptions of New Digital Energy Management Platform in Municipality of Loulé, Southern Portugal: A SWOT-AHP Analysis

This study aimed to develop a multi-stakeholder analysis to identify the best strategies for the integration of a new Digital Energy Management Platform (DEMP). The municipality of Loulé (South of Portugal) was used as a case study. A Strengths, Weaknesses, Opportunities, and Threats (SWOT) framework combined with an Analytical Hierarchy Process (AHP) framework and a TOWS Matrix was employed to analyse the stakeholder’s perceptions to propose strategies for integrating the DEMP. Five focus stakeholder groups were involved. Results showed that stakeholders considered that the positive aspects of DEMP outweigh the negative aspects by approximately 36%. Strengths were ranked with 34.4%, Opportunities with 33.8%, Weaknesses with 20.2%, and Threats with 11.6%. The sequence of factors with the highest overall score by stakeholders was O1(12.7%) > S2(11.1%) > W2(7.4%) > T3(4.1%). Based on stakeholder perceptions, the most suitable strategies were those that use Strengths and Opportunities of the system (SO strategies), and strategies that take advantage of Opportunities while dealing with Weaknesses (WO strategies), achieving a prevalence compared with the other strategies of 34% and 27%, respectively. Therefore, the participation process involving stakeholders’ groups in the implementation and monitoring of the DEMP provided an action plan and consensus capable of meeting the environmental and municipal energy management challenges.

Machine Learning Techniques in the Energy Consumption of Buildings: A Systematic Literature Review Using Text Mining and Bibliometric Analysis

The high level of energy consumption of buildings is significantly influencing occupant behavior changes towards improved energy efficiency. This paper introduces a systematic literature review with two objectives: to understand the more relevant factors affecting energy consumption of buildings and to find the best intelligent computing (IC) methods capable of classifying and predicting energy consumption of different types of buildings. Adopting the PRISMA method, the paper analyzed 822 manuscripts from 2013 to 2020 and focused on 106, based on title and abstract screening and on manuscripts with experiments. A text mining process and a bibliometric map tool (VOS viewer) were adopted to find the most used terms and their relationships, in the energy and IC domains. Our approach shows that the terms “consumption,” “residential,” and “electricity” are the more relevant terms in the energy domain, in terms of the ratio of important terms (TITs), whereas “cluster” is the more commonly used term in the IC domain. The paper also shows that there are strong relations between “Residential Energy Consumption” and “Electricity Consumption,” “Heating” and “Climate. Finally, we checked and analyzed 41 manuscripts in detail, summarized their major contributions, and identified several research gaps that provide hints for further research.

Role of Internet of Things (IoT) and Crowdsourcing in Smart City Projects

This paper presents and discusses the role of the Internet of Things (IoT) and crowdsourcing in constructing smart cities. The literature review shows an important and increasing concern of the scientific community for these three issues and their association as support for urban development. Based on an extensive literature review, the paper first presents the smart city concept, emphasizing smart city architecture and the role of data in smart city solutions. The second part presents the Internet of Things, focusing on IoT technology, the use of IoT in smart city applications, and security. Finally, the paper presents crowdsourcing with particular attention to mobile crowdsourcing and its role in smart cities. The paper shows that IoT and crowdsourcing have a crucial role in two fundamental layers of smart city applications, namely, the data collection and services layers. Since these two layers ensure the connection between the physical and digital worlds, they constitute the central pillars of smart city projects. The literature review also shows that the smart city development still requires stronger cooperation between the smart city technology-centered research, mainly based on the IoT, and the smart city citizens-centered research, mainly based on crowdsourcing. This cooperation could beneficiate in recent developments in the field of crowdsensing that combines IoT and crowdsourcing.

Exploring and Predicting the Knowledge Development in the Field of Energy Storage: Evidence from the Emerging Startup Landscape

The distribution and deployment of energy storage systems on a larger scale will be a key element of successfully managing the sustainable energy transition by balancing the power generation capability and load demand. In this context, it is crucial for researchers and policy makers to understand the underlying knowledge structure and key interaction dynamics that could shape the future innovation trajectory. A data-driven approach is used to analyze the evolving characteristics of knowledge dynamics from static, dynamic and future-oriented perspective. To this end, a network analysis was performed to determine the influence of individual knowledge areas. Subsequently, an interaction trend analysis based on emergence indicators was conducted to highlight the promising relations. Finally, the formation of new knowledge interactions is predicted using a link prediction technique. The findings show that ensuring the energy efficiency is a key issue that has persisted over time. In future, knowledge areas related to digital technologies are expected to gain relevance and lead the transformative change. The derived insights can assist R&D managers and policy makers to design more targeted and informed strategic initiatives to foster the adoption of energy storage solutions.

A Systematic Review of Energy Management Strategies for Resource Allocation in the Cloud: Clustering, Optimization and Machine Learning

Nowadays, many organizations and individual users are employing cloud services extensively due to their efficiency, reliability and low cost. A key aspect for cloud data centers is to achieve management methods to reduce energy consumption, increasing the profit and reducing the environmental impact, which is critical in the deployment of leading-edge technologies today such as blockchain and digital finances, IoT, online gaming and video streaming. In this review, various clustering, optimization, and machine learning methods used in cloud resource allocation to increase the energy efficiency and performance are analyzed, compared and classified. Specifically, on the one hand, we discuss how clustering methods and optimization techniques are widely applied in energy management due to their capacity to provide solutions for energy consumption reduction. On the other hand, we study how multi-objective optimization methods focus on reducing energy consumption as well as service level agreement (SLA) violation, and improving quality of services (QoS) simultaneously. Also, we discuss how optimization methods such as the firefly algorithm, whale optimization algorithm (WOA), particle swarm optimization (PSO) and genetic algorithm (GA) provide the highest performance in the field. Moreover, we analyze how machine learning methods such as deep neural network (DNN), random forest, and support vector machine (SVM) are applied to the prediction of energy consumption in the cloud, showing an accurate performance in this prediction. Nevertheless, we study how the existing methods still have limitations of low convergence, trap into local optima and overfitting.

Discovery of Resident Behavior Patterns Using Machine Learning Techniques and IoT Paradigm

In recent years, technological paradigms such as Internet of Things (IoT) and machine learning have become very important due to the benefit that their application represents in various areas of knowledge. It is interesting to note that implementing these two technologies promotes more and better automatic control systems that adjust to each user’s particular preferences in the home automation area. This work presents Smart Home Control, an intelligent platform that offers fully customized automatic control schemes for a home’s domotic devices by obtaining residents’ behavior patterns and applying machine learning to the records of state changes of each device connected to the platform. The platform uses machine learning algorithm C4.5 and the Weka API to identify the behavior patterns necessary to build home devices’ configuration rules. Besides, an experimental case study that validates the platform’s effectiveness is presented, where behavior patterns of smart homes residents were identified according to the IoT devices usage history. The discovery of behavior patterns is essential to improve the automatic configuration schemes of personalization according to the residents’ history of device use.

Hybridizing Deep Learning and Neuroevolution: Application to the Spanish Short-Term Electric Energy Consumption Forecasting

The electric energy production would be much more efficient if accurate estimations of the future demand were available, since these would allow allocating only the resources needed for the production of the right amount of energy required. With this motivation in mind, we propose a strategy, based on neuroevolution, that can be used to this aim. Our proposal uses a genetic algorithm in order to find a sub-optimal set of hyper-parameters for configuring a deep neural network, which can then be used for obtaining the forecasting. Such a strategy is justified by the observation that the performances achieved by deep neural networks are strongly dependent on the right setting of the hyper-parameters, and genetic algorithms have shown excellent search capabilities in huge search spaces. Moreover, we base our proposal on a distributed computing platform, which allows its use on a large time-series. In order to assess the performances of our approach, we have applied it to a large dataset, related to the electric energy consumption registered in Spain over almost 10 years. Experimental results confirm the validity of our proposal since it outperforms all other forecasting techniques to which it has been compared.