Hybrid Machine Learning and Modified Teaching Learning-Based English Optimization Algorithm for Smart City Communication

Vibration control devices have recently been used in structures subjected to wind and earthquake excitations. The optimal design problems of the passive control device and the feedback gain matrix of the controller for the seismic-excited structures are some attractive problems for researches to develop optimization algorithms with the advancement in terms of simplicity, accuracy, speed, and efficacy. In this paper, a new modified teaching–learning-based optimization (TLBO) algorithm, known as MTLBO, is proposed for the problems. For some benchmark optimization functions and constrained engineering problems, the validity, efficacy, and reliability of the MTLBO are firstly assessed and compared to other optimization algorithms in the literature. The undertaken statistical indicate that the MTLBO performs better and reliable than some other algorithms studied here. The performance of the MTLBO will then be explored for two passive and active structural control problems. It is concluded that the MTLBO algorithm is capable of giving better results than conventional TLBO. Hence, its utilization as a simple, fast, and powerful optimization tool to solve particular engineering optimization problems is recommended.

This paper investigates energy consumption patterns using panel data of final energy consumption and economic variables from 1970 to 2010 for more than 100 countries and regions. Although previous economic studies address the role of economic development and income as determinant factors of energy consumption, we examine how physical factors such as climate affects energy consumption level and patterns. By integrating economic and engineering approaches, we demonstrate statistical analyses showing that climate determines not only energy consumption levels, but also the relationship between energy consumption and income levels over time. While climate affects energy consumption patterns, our results suggest that energy technology and price policy are significant in determining whether a country can decouple energy consumption from economic growth.

Internet of Things (IoT) does not stop integrating an important number of components and objects that are characterised by their complexity and heterogeneity. Such constraints make the existing routing protocols unsuitable for IoT communications in a smart cities environment. To accomplish all the expected tasks and satisfy the user services, it is important to guarantee a quality of communication that answers to the requirements of smart cities applications in terms of data and processing. This study addresses the problem of the performance degradation of IoT communications in smart cities and proposes a new routing algorithm to improve them. The proposed algorithm is called SSRA (smart and self‐organised routing algorithm), which can select the best route for the packets. SSRA allows a self‐organising routing process according to a new situation of the network and devices parameters recently detected. When using SSRA, the communication records an improvement in performance in terms of packet delivery rate, throughput, end‐to‐end delay and overhead packets. SSRA extends also the devices lifetime by allowing fair and efficient energy consumption.

In this paper, a novel two-stage structural damage detection method using modal flexibility and strain energy-based index (MFSEBI) and modified teaching–learning-based optimization (MTLBO) algorithm is proposed. In the first stage, a novel damage index (MFSEBI) is proposed based on the combination of two structural modal properties including modal strain energy of elements and diagonal members of the structural flexibility matrix to identify the suspected damaged elements. The performance of this indicator is compared with the performance of an indicator derived from the modal strain energy. As the change in the structural modal properties is also affected by environmental variations, in this study, the effect of varying environmental conditions on the performance of the MFSEBI is also examined. In the second stage, the modal response of the structure is used and subsequently updated by MLTBO to estimate the damage extents of the suspected elements. At this stage, the MTLBO algorithm is proposed by enhancing the teaching and learning quality of the TLBO algorithm using new updating mechanisms of each learner position. The performance of the MTLBO and TLBO algorithms is compared in terms of the accuracy of the results and convergence rate. The results of three numerical examples indicate a better performance of the MFSEBI index in damage localization using a smaller number of mode shapes. These results also demonstrate the higher accuracy of the estimated damage extents and the faster convergence rate of the objective function using MTLBO, even with the consideration of measurement noise effects.

This study analyzes the impact of energy security and geopolitical risks on energy consumption in countries with geopolitical risk from 1985 to 2021, with the aid of financial development, economic growth, and human capital as moderating variables. Employing robust panel data econometric techniques, the analysis reveals that heightened geopolitical risks and compromised energy security significantly affect energy consumption patterns. The increase in energy security risk by 1% has a dual impact on energy consumption patterns in countries with high geopolitical risk, as renewable energy consumption increases by 0.1227%, while non-renewable energy consumption also increases by 0.113%. As geopolitical risk increases by 1%, energy consumption patterns change, decreasing renewable and non-renewable energy consumption. Specifically, renewable energy consumption decreases by 0.00010% with a 1% rise in geopolitical risk. A 1% increase in financial development significantly impacts energy consumption in these countries. The adoption of sustainable energy solutions is positively correlated with the development of financial markets in high-risk countries, with non-renewable energy consumption decreasing by 0.0187% as financial development progresses. Additionally, an increase in economic growth of 1% leads to a 0.6750% increase in renewable energy consumption, indicating a preference for renewable sources as economies expand, aligning with global sustainability efforts. The findings underscore the importance of resilient energy policies considering geopolitical uncertainties while promoting sustainable economic development. This study offers critical insights for policymakers aiming to balance energy security with financial stability in geopolitically sensitive regions, providing a comprehensive framework to guide strategic decisions in the face of evolving global risks.

An experimental investigation and optimization of energy consumption and surface defects in wire cut electric discharge machining

The COVID-19 pandemic has generated multiple impacts. In particular, in the educational sector, the virtual class modality generated changes in the patterns of energy consumption at the institutional level; the identification of this consumption will allow us to reflect on new energy saving and efficient use strategies. In this research, we present a case study of the effects of the COVID-19 pandemic on electricity consumption in 13 state universities in Michoacán, Mexico. Electric energy consumption has been evaluated before and during the presence of the COVID-19 between 2019 and 2020. The comparative analysis estimated the reduction in energy consumption and its economic and environmental impact. The results show a considerable decrease in electricity consumption, generating an average saving of 76.24 MWh/month, which translates into an annual emission reduction from 2019 to 2020 of approximately 497 TnCO2e, and in economic terms of $8,882.25 USD each month. In general, it was identified that consumption patterns in the use of machinery and computer equipment for administrative activities were drastically reduced. If education continues in virtual or hybrid modes, energy consumption schemes will continue to decline and institutions could move towards resilient, affordable, and sustainable models of energy production and consumption.

The rise of electric and autonomous vehicles in smart cities poses challenges in vehicular energy management due to un-optimized consumption, inefficient grid use, and unpredictable traffic patterns. Traditional centralized machine learning models and cloud-based Energy Management Systems (EMSs) struggle with real-time adaptability, high-dimensional data processing, and data privacy risks. These issues lead to high costs, excessive energy waste, and regulatory concerns. Federated Learning (FL) offers a decentralized approach where multiple edge devices collaboratively train models without sharing raw data. This enhances privacy, reduces communication overhead, and is well-suited for smart city applications. However, FL’s black-box nature limits interpretability, reducing trust in AI-driven decisions. Explainable AI (XAI) addresses this by enhancing transparency, interpretability, and regulatory compliance. This research introduces Explainable FL (XFL) for optimizing vehicular energy management in smart cities. The proposed XFL framework integrates distributed learning with explainability techniques for interpretable and accountable decision-making. Using a real-world AEV telemetry dataset of approximately 1,219,567 records with features like speed, energy consumption, and traffic density, it employs a hierarchical FL architecture to ensure secure and decentralized learning. It efficiently analyzes real-time traffic, vehicle energy states, and grid load balancing while preserving privacy. Experimental results show that the proposed Multi-Layer Perceptron (MLP)-based global model achieves superior predictive accuracy, with R² values of 94.73% for energy consumption and 99.83% for traffic density, significantly outperforming previous methods.

Although a large body of research has advanced our understanding of the definition, characteristics, and domains of smart cities at a high level of abstraction, relatively little attention has been given to varying smart city practices. This study analyses the contents and progress of 2,080 smart city pilot projects across 136 sampled smart cities in China since 2013. While the central government has set a unified framework for guiding smart city practices, both the experiences and progress vary substantially at the local level. Among the smart city domains, pilot projects related to smart government have been the most common but those on smart living and smart people have not received as much attention. The findings confirm that smart city development is a process. A period of 1.5–2 years is typically required for pilot projects to demonstrate actual progress. Smart cities at the county/township level have progressed better in infrastructure but have lagged in the institutional and people dimensions. Those implemented in Eastern China have also advanced more noticeably than those in Central and Western China.

The study provides a unique method for creating an efficient substitution box (S-box) for advanced encryption standards using a Chaotic Logistic Map (CLM) and a Linear Congruential Generator (LCG) (AES) for secure communications in a smart city. The Pseudo-Random Number Generator (PRNG), which is further examined, is constructed using an extensive search of reasonable possibilities for the initial seed and set parameters. Using statistical testing, the performance analysis of the new S-box is assessed. Additionally, the resilience of differential, as well as linear cryptanalysis, is shown. It is derived using other features, including nonlinearity, the Bit Independence Criterion (BIC), and the Strict Avalanche Criterion (SAC). The suggested S-box has good potential and is usable for symmetric key cryptography, according to the features of the new S-cryptographic box.

Connecting the indispensable roles of IoT and artificial intelligence in smart cities: A survey

The revolution of the Internet of Things (IoT) is transforming many concepts, making them “Smart”. It has revolutionized many areas of real life. Smart City is one of the key concepts of this revolution. Although cities are being digitally transformed, it still has obstacles along the way. In this paper, we have analyzed different publications for our Systematic Literature Review (SLR). This study highlights the areas where the blockchain is used and determines the benefits of using blockchain. The main contribution is to explore and identify the barriers and hurdles in Smart City Domain and how these hurdles are mitigated by the blockchain technology. This Systematic Study also addresses different challenges and issues such as security, immutability, interoperability, decentralization, privacy, and trust in the development of Smart Cities. An overview of the systematic research is also presented that would help identify the most and least studied concerns addressed in this study. This paper aims at analyzing how blockchain technology is used in different smart city business models, what are the features of blockchain that could consider it to be used beyond crypto currencies. We hope that this study can inspire interest in theory and exercise to stand-in discussions in this area adhere to these limits.

Teaching learning-based optimization is one of the widely accepted metaheuristic algorithms inspired by teaching and learning within classrooms. It has successfully addressed several real-world optimization problems, but it may still be trapped in local optima and may suffer from the problem of premature convergence in the case of solving some challenging optimization problems. To overcome these drawbacks and to achieve an appropriate percentage of exploitation and exploration, this study presents a new modified teaching learning-based optimization algorithm called the fuzzy adaptive teaching learning-based optimization algorithm. The proposed fuzzy adaptive teaching learning-based optimization algorithm uses three measures from the search space, namely, quality measure, diversification measure, and intensification measure. As the 50-50 probabilities for exploitation and exploration in the basic teaching learning-based optimization algorithm may be counterproductive, the Mamdani-type fuzzy inference system of the new algorithm takes these measures as a crisp inputs and generates selection as crisp output to choose either exploitation or exploration based on the current search requirement. This fuzzy-based adaptive selection helps to adequately balance global search or exploration and local search or exploitation operations during the search process as these operations are intrinsically dynamic. The performance of the fuzzy adaptive teaching learning-based optimization is evaluated against other metaheuristic algorithms including basic teaching learning-based optimization on 23 unconstrained global test functions. Moreover, adaptive teaching learning-based optimization is used to search for near-optimal values for the four parameters of the COCOMO II model, which are then tested for validity on a software project of NASA. Analysis and comparison of the obtained results indicate the efficiency and competitiveness of the proposed algorithm in addressing unconstrained continuous optimization tasks.

The importance of energy consumption and environmental protection is one of the key issues of the past decade. Most of the energy consumption during the summer season in residential buildings, offices, hospitals, and hotels is related to their chiller plant. The highly variable cooling demand of the buildings connected to a hybrid chiller plant has to be distributed among absorption and vapor compression chillers to achieve higher energy efficiencies. Cooling load sharing strategies in chiller plants have a significant impact on energy consumption and consequently with more productivity and environmentally protected. This paper examines the behavior and pattern of energy consumption in a hybrid chiller plant that includes a combination of vapor compression and absorption chillers. In order to properly understanding the pattern of energy consumption, an existing mechanical room for a hospital in Tehran has been studied for six months and its energy consumption has been compared with the software modeling. This comparison includes the capacity of each chiller, the amount of energy consumed by vapor compression chillers and absorption chillers, and the percentage of their cooling energy allocation. The results indicate that the sequence of the chiller function and how they are placed in the circuit during a partial load is in the highest importance in viewpoint of energy saving.

Wire-cut electrical discharge machining (WEDM) is a widely used non-contact machining process used to cut difficult-to-machine materials such as titanium, nickel and inconel alloys. WEDM is famous for producing components in diverse engineering applications, including automotive, marine, space, medical sectors with the highest accuracy and consistency. In this paper, experimental investigation on surface roughness (SR) of Ti6Al4V alloy employing WEDM process is presented using Taguchi L16 experimental plan by varying four process variables, viz., pulse on time (Ton), pulse off time (Toff), current (I) and wire speed (WS) at four different levels. The novelty of the present work is minimization of surface roughness (SR) in WEDM of Ti6Al4V alloy employing reusable wire technology during experimental work and optimizes the problem with modified teaching–learning-based optimization (M-TLBO) algorithm. A novel technique for fitness curve fitting is also illustrated to obtain global optima for minimization of SR. Results showed that SR decreased by 2.65% at optimal parameter setting Ton = 13 µs, Toff = 10 µs, I = 1 A and WS = 850 rpm and global optima is obtained as 3.749 µm. Pulse on time (44.06%) and current (28.69%) are recognized as the most dominant process variables affecting SR followed by pulse off time (15.80%) and wire speed (7.47%). Surface morphology study of machined Ti alloy using SEM images showed that smoother surface is obtained at lower settings of pulse on time and current. The proposed M-TLBO algorithm is found to be highly accurate and consistent during several runs conducted with mean fitness value and standard deviation recorded as 3.751 µm and 0.006417, respectively.