Electric Service Research Articles

Using a Machine Learning Approach to Model a Chatbot for Ceylon Electricity Board Website


 Customer support is one of the main aspects of the user experience for online services. However, the rise of natural language processing techniques, the industry is looking at automated chatbot solutions to provide quality services to an ever-growing user base. In Sri Lanka, Ceylon Electricity Board website is one of the largest websites that customers use always to get information about electricity services. Hence, a chatbot system is very essential in CEB website. This paper presents a study about implementing and evaluating of a chatbot model for CEB website. This study implements virtual conversation agent based on deep learning algorithm which is multilayer perceptron neural network and a special text dataset for conversations about CEB services. The conversation agent model is made by utilizing the natural language processing techniques to facilitate the processing of user messages. The output of this research is the response from the chatbot and identify the best testing method to get highest accuracy for chatbot model. The chatbot model achieves the highest accuracy with the number of epochs set to 2000 and the learning rate value of 0.01 on response context data training so that it gets 78.8% accuracy.
 Keywords: Natural language processing, chatbot, deep learning, multilayer perceptron neural network, Monte Carlo cross validation, k-fold cross validation

Online Service Booking Platform with Payment Integration

This research work provides the design and development of an online service booking platform with payment integration. The platform is designed to enable users to book and pay for services such as plumbing and electrical services online from the comfort of their own homes. The system uses HTML, CSS, and PHP to create an intuitive user interface, as well as a secure payment gateway for online transactions. The platform is designed to provide better user experience and the system is designed for both mobile and desktop devices. The study concludes by providing a set of recommendations for future development of the platform, and discusses the potential benefits and challenges of online service booking platforms.

Analysis of spatial distribution characteristics of electric vehicle sales and service shops and the corresponding influencing factors

AbstractThe electric vehicle industry is essential for China's economic transformation and industrial upgrading. Identifying the distribution of electric vehicle sales and service shops is of great significance to boost the development of retail geography theory and promote the optimization of industrial space. Regression and spatial econometric methods analyze the influencing factors of electric vehicle sales and service shop distribution. According to the point of interest data of electric vehicle sales and service shops, taking 10 typical cities in China as an example, the spatial distribution of electric vehicle sales and service shops and its influencing factors are empirically explored by spatial econometric methods. The results indicate the following: (1) From high to low, the influence degree of spatial dependence factors are car license restriction policy, the average age of residents, number of schools, built‐up area, the amount of investment in real estate, electric vehicle sales, and GDP; (2) On the whole, the spatial distribution of electric vehicle sales and service shops shows the characteristics of a multi‐center circle‐layered spatial structure that spreads from the inside to the outside; and (3) The spatial influencing factors such as electric vehicle sales, charging stations, permanent resident population, schools, and subway stations in the four first‐tier cities is evident.

Energy and Economic Analysis of Renewable Energy-Based Isolated Microgrids with AGM and Lithium Battery Energy Storage: Case Study Bigene, Guinea-Bissau

By the year 2020, 90% of the population with access to electricity worldwide was surpassed. However, the reality is very different for many countries, especially for those on the African continent that had more than 572 million people without electricity service at the end of 2019. This work studies the implementation of an isolated microgrid activated with photovoltaic energy and energy storage in batteries under the case study of the community of Bigene, located in the African country of Guinea-Bissau. This type of project is a potential solution to the problem of access to energy, but as the cost of the energy storage system is typically very high, this work technically and economically addresses the effect of using absorbed glass material (AGM) and lithium batteries. A simulator was developed using TRNSYS software to analyze the operation of the microgrid under a defined annual demand profile for different types of users, and economic analysis was conducted considering a project lifetime of 25 years. The results showed no significant differences in the solar fraction of both types of batteries when the photovoltaic power was less than 600 kW, regardless of the capacity of the storage bank. The analysis of auxiliary power requirements showed that lithium technology leads to a lower consumption from 800 kW of PV capacity, and utilizing less than this capacity did not have a significant difference with AGM batteries. In this microgrid with a photovoltaic capacity of less than 700 kW and an energy storage of less than 2580 kWh, the type of storage technology, AGM or lithium, did not represent a considerable difference in the levelized cost of energy, indicating that AGM technology could be selected considering its low initial investment cost compared to lithium batteries.

Comfort violation minimization oriented energy management strategy for a renewable-assisted stand-alone multi-energy electric vehicle service station

In this study, a comfort violation minimization oriented energy management strategy is proposed for a stand-alone electric vehicle (EV) service station serving multiple EV types in a multi-energy manner. The main purpose of this strategy is to minimize the discomfort of EV owners due to insufficient energy supply while considering the fairness among users and optimizing the utilization of renewable energy sources. The criteria for selecting this strategy include: (1) mitigating customer dissatisfaction arising from inadequate energy supply, (2) ensuring fairness in energy distribution among different EV types, and (3) maximizing the use of renewable power sources, such as photovoltaic (PV) units. The developed mixed-integer linear programming (MILP) model comprises a PV unit as the main power source, with an energy storage system (ESS) and an electrolyzer-supported main hydrogen storage unit fulfilling the energy and hydrogen demands of battery electric vehicles (BEVs) and fuel cell electric vehicles (FCEVs), respectively. A comfort violation fairness constraint is also introduced to guarantee a fair service for all EV owners, thereby enhancing the social acceptability of the provided EV service.Simulation results, obtained under various case studies considering component size changes and comfort fairness constraint relaxation, demonstrate the importance of striking a balance between investing in larger components and allowing for a certain level of customer dissatisfaction. The analysis revealed that relaxation of the fairness constraint led to a reduction in overall comfort violation by up to 15 % for both BEVs and FCEVs combined; however, this relaxation resulted in significant differences in comfort violation among different EV owner types, with variations ranging from a minimum of 0 % to a maximum of >90 %. These findings emphasize the significance of considering fairness in energy distribution to prevent potential dissatisfaction among end-users. Future studies will explore the development of a grid-connected system and compare the stand-alone structure in a techno-economic context, considering the possible impact of different EV types on grid operation during normal and resiliency-oriented conditions.

Impacts of electricity quality improvements: Experimental evidence on infrastructure investments

Hundreds of millions of households depend on electricity grid connections providing low quality and unreliable services. Understanding the impacts of and consumer response to electricity quality improvements is important for development and the environment. We investigate this in the Kyrgyz Republic through randomized improvements in the grid, which can improve electricity service quality. Treated households experience significantly fewer voltage fluctuations per day, an indicator of improved electricity quality post-intervention. Treated households’ billed consumption of electricity services increased during peak months post-intervention, with increases in consumption of 4% and 18% for homeowners and renters, respectively. Consistent with this, treated households, particularly renters, significantly increased ownership of electric heaters. Treated households invested more in energy efficiency, potentially mitigating their electricity bill increases post-intervention.

GIS-Based Electric Service Resource Management System

<p>With the increasing investment in railway construction, China’s railway transport network is now very sound, the number of operating miles is growing, and the operating speed has also made a qualitative leap. At the same time, the safety and reliability of the operation of railway signal cables and other electrical equipment has also put forward higher requirements. At the present stage, the management of railway electrical services equipment mainly relies on manual management, which is cumbersome, inefficient and unsuitable for multi-user sharing. At the same time, the structure of railway electrical equipment is complex, and the components of the equipment are prone to aging, which can easily cause equipment failure. How to professionally manage electrical service equipment and improve the safety and reliability of electrical service equipment has become an urgent problem for railway electrical service departments. Geographic Information System (GIS) architecture uses spatial data layering technology to achieve multi-level and proportional display of equipment and facilities, which can provide visual display of professional facilities such as railway engineering, electricity and power supply, and carry out multi-source and multi-temporal intelligent analysis of data, provide geographical information service interface for various professions of engineering and electricity to meet their own functional requirements. Knowledge mapping is a key technology for acquiring knowledge and building a knowledge database in the era of big data. In order to explore the hidden information between railway electrical resources, integrate seemingly independent data into the knowledge base and apply them. In this paper, we design a GIS-based electric service resource management system in combination with knowledge mapping that can make data complete and well-structured after processing scattered and redundant information, and analyze and discuss the system’s architecture, functional requirements, key technologies and development prospects.</p> <p> </p>

A New Electrification Model to End Energy Poverty: An example from a novel rural electrification approach in Madagascar

Highlighted by the United Nations sustainable Development Goals to ensure universal access to clean, reliable, and modern energy services by 2030, the world is increasingly becoming concerned by energy poverty and its consequences on human development and the environment. Yet, even if numerous initiatives and a significant amount of money are directly addressed to tackle the energy-access challenges, a billion people are still denied access to basic and modern electricity services, especially in rural areas of sub-Saharan Africa and Southeast Asia. In the past two decades, the African continent has seen an encouraging improvement as the number of people gaining access to electricity rose from 9 million per year between 2000 and 2013 to 20 million per year between 2014 and 2019, outpacing population growth for the first time. However, most of those recent improvements are restricted mainly to urban and peri-urban areas of a small number of countries located in eastern or western Africa. Also, the population without access to electricity in Africa is expected to increase in the coming years following the health crisis and economic downturn caused by COVID-19. This definitely proves the fragility and poor resilience of the electrification solutions favored today. While grid extension and conventional microgrids suffer from low inclusivity and replicability, solar home systems are only a stopgap measure and fail to boost socioeconomic development. A third way must be proposed to combine quick and affordable access to basic electricity services and community uplift through socioeconomic development, answering the two greatest challenges that developing countries are struggling to cope with today. With this objective in mind, Nanoé, a French–Malagasy social company, is developing the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">lateral electrification model</i> , based on the collaborative and progressing building of electric infrastructures, which is presented in this article, first from a general point of view and then through a focus on Nanoé’s experience in Madagascar.

Environmental improvement to reduce urban vulnerability in irregular settlements

The peripherals illegal settlements in Puebla, have common denominator to born in a situation of urban vulnerability, it means with a lack of infrastructure and basic services and on some occasions on land not suitable for urbanization. This is the case of the Cuitláhuac neighborhood where approximately 400 inhabitants live. The neighborhood only has electricity service, his high urban vulnerability becomes worst in the rainy season with the formation of gullies, flooding sites and soil erosion, affecting the mobility of the inhabitants. Authorities ignore these problems and not always included them in urban development plans. The objective of research is to look for environmental alternatives to reduce urban vulnerability in illegal settlements. The methodology is based on action research and the main techniques were: documentary review, physical and virtual field trips, virtual meetings and semi-directed interviews. A relevant conclusion is that green infrastructure is feasible and can be implemented in the short term and that it arouses much collaborative interest from the inhabitants both for its implementation and for its maintenance.

Modified Efficiency Estimation Tool for Three-Phase Induction Motors

This article presents a modified version of novel algorithms the authors previously proposed to help North America electric motor service centers to evaluate their repaired, rewound, or any existing motors for efficiency. Due to the dependency of the algorithms on a large 60 Hz induction motor database to produce reliable and accurate results, a software was needed and developed to incorporate both the algorithms and the data to create a useful single affordable tool for the North America electric motor repair industry. To eliminate the need for the software, and allow an open-source implementation, the direct dependency of the efficiency algorithms on the motor test data are eliminated in this paper. This allows the two techniques presented here to be used directly by engineers in the motor repair industry in North America. To achieve this goal, modifications to the two original algorithms are required and proposed in this paper. The modifications include the implementation of a new stray-load loss formula and the IEEE Std 112 hot temperature formula. The modified algorithms are validated by testing 28 new and aged, small- and medium-sized induction motors in the range of 1-500 hp. The modified techniques demonstrate a high level of accuracy.

Modularization Design for Smart Industrial Service Ecosystem: A Framework Based on the Smart Industrial Service Identification Blueprint and Hypergraph Clustering

Compared with the conventional industrial product–service system, the smart industrial service ecosystem (SISE) mentioned in this study contains more service activity according to the characteristics of the industrial context, participation of various stakeholders and smart interconnected technologies. This study proposes a detailed modularization design framework for SISE, which can be referenced in various industrial contexts. Firstly, the context-based smart industrial service identification blueprint (SISIB) is proposed to describe the operation model of SISE and identify the service components. The SISIB can ensure that the designers understand the service and work process of the system and improve or carry out the smart industrial service (SIS) component identification. In the case of this article, SIS components from different industrial levels can be systematically identified. Secondly, smart collaboration and sustainable development principles are proposed for measuring the correlation degree among the service components. Considering the complexity and multi-level distribution nature of service components, the hyperedge concept is presented to realize the correlation comparison among the service components, and the evaluation linguistics is applied to handle the decision uncertainties. With this method, the effective correlation comparison between service components can be formed with few hyperedges. Thirdly, the hypergraph clustering theory is applied to define the SISE service module partition. The triangular fuzzy number is first used in hyperedge strength evaluation to comply with the vague linguistics from service design experts. The normalized hypergraph cut principle is realized using the K nearest neighbors (kNN) algorithm, and with this method, the new unified hypergraph and related Laplace matrix can be obtained. Then, the relevant eigenvalue of that Laplace matrix is gained, and the component clustering visualization is realized using the k-means algorithm. After the clustering is performed, several modular design schemes can be gained. In order to select the best modularization scheme, we referenced the modularity concept and realized the quality measurement for the modular design using hypergraph modularity criteria. Regarding these three steps, a detailed modularization case study for a renewable electricity service ecosystem design is presented to verify the viability and feasibility of the study in service modular design. The result showed that the framework in this study can realize the visible and clearance service component identification in a smart connected multi-level industrial context. The modular design scheme based on hypergraph can also achieve high modularity with a more convenient correlation evaluation.

Voltage stability assessment for solar photovoltaic penetration using Reactive Power–Voltage and Active Power–Voltage modal analysis

The assessment of voltage stability in a power system is crucial to ensure all buses in the network can maintain the desired voltage or avoid maximum loadability when subjected to load disturbance. Current research has tended to concentrate on developing new voltage stability assessment tools rather than identifying the best location for the penetration of solar photovoltaic (SP) generation in the network. This paper examines and evaluate the power systems voltage stability with increasing SP penetration levels by employing both the Active Power–Voltage (PV) and Reactive Power–Voltage (QV) modal analysis. The effect of load flow study by penetrating SP at the weakest and the strongest load bus has been investigated in this work. Furthermore, the analysis in this work was carried out in the modified Brunei Darussalam Department of Electrical Services (DES) power system. The main contribution of this paper is to assess and identify the best and worst locations for SP penetration in the simplified DES power system network in Brunei Darussalam using both the QV and PV modal analysis. The load flow results show that the penetration of SP generation is much better at the strongest bus due to it does not influence other load buses as compared to the least reliable bus in the network.

MILP model for fleet and charging infrastructure decisions for fast-charging city electric bus services

The reduction of greenhouse gas emissions is one of required conditions for the transition to the sustainable cities. The creation of sustainable public transportation system is seen as an efcient long-term solution to achieve it. This paper develops a framework for designing a sustainable infrastructure for fast-charging electric buses. This framework helps the decision makers and in particular public authorities to determine a heterogeneous fleet of electric buses, to design the network of required charging facilities and to maximize the flow of passengers utilizing sustainable public transportation to minimize the amount of greenhouse gas emissions. An efcient Mixed Integer Linear Programming model is developed for the particular case where all chargers are interchangeable among the electrical buses. The decision-making process is illustrated through a case study for the public bus transportation in the city of Minsk. Extensive computer experiments show that the developed model provides efcient solutions in acceptable computational time and outperforms state-of-the-art methods on every tested problem instance.

Channel choices and interaction patterns in continuously provided services: a customer journey perspective

ABSTRACT This research investigates channel choice antecedents in service industries, specifically referring to the online/offline dichotomy. We focus on continuously provided services in which prolonged interaction occurs between the provider and the customer in the post-purchase phase. Using a survey sample of 311 cross-service cases relating to bank accounts, mobile telecom, and electricity services, we identified five distinct journey patterns and tested our hypotheses on channel synergy effects and a set of customer-centered antecedents. This research advances the knowledge of customer – provider interactions and provides useful insights for service providers into how to improve customer value and retail strategies.

Unveiling underconsumption of water and electricity services at the bottom of the income distribution

Access to water and energy services crucially depends on these services' affordability, which is commonly assessed by computing the burden of actual utilities' expenditures in relation to households’ income and then comparing it to a reference threshold. However, this monetary indicator overlooks quantities consumed. We estimate quantities underlying expenditures on water and electricity, combining this information with the burden approach, with special emphasis on low-income households. Results reveal situations of households whose affordability ratios are low but with underconsumption signs (hidden unaffordability) and families that despite having high ratios, still suffer from underconsumption. Problems are more acute for the poorest families.

Mobility and transport infrastructure in Mumbai Metropolitan Region: growth, exclusion and modal choices

ABSTRACT Social and physical infrastructure development needs to catch up to population growth in cities of the Global South. The infrastructures are emerging in piecemeal ways following demand, be it housing, water supply, electricity, financial, educational, health or transport services. Indian cities are typical examples of this and can be called archetypes of the problem. This paper finds that transport infrastructure development in Mumbai Metropolitan Region has not kept pace with the demand. Notwithstanding recent developments, urban mobility in the region is characterised by traffic jams, delays and a lack of integrated and inclusionary transport systems, adversely affecting the economic efficiency of the region through loss of labour time, delays in deliveries of goods and services, environmental pollution and health costs.

Collecting and communicating perishable data in a post-disaster context: rapid research and rapid dissemination.

Puerto Rico experienced four natural disasters in 4 years (2017-2021): Hurricanes Irma and Maria, thousands of earthquakes reaching 6.4 magnitude, and the COVID-19 pandemic. In this context, our team sought to understand the impact of disaster aid distribution on poverty and economic inequality, and their relationship to the spread of COVID-19 across Puerto Rico. Rapid research was required to ensure we could collect perishable data within this ever-changing context. Our mixed methods design relied on both secondary and primary data. Because analyses of the former were to inform where and how to collect the latter, timing was of the essence. The data sources identified were not readily available to the public, and thus required gaining access through direct requests to government agencies. The requests coincided with a transition between administrations after an election. This resulted in unexpected delays. Once in the field, the team had to balance the rapid nature of the research with the mindful work to avoid compounding traumas experienced by participants, heightened risk for re-traumatization and fatigue, the risk of COVID-19, the digital divide, and intermittent electrical and telecommunication services. In response to the delayed access to secondary data, we adjusted our research question. We continued to collect data as they became available, incorporating some immediately into analyses, and cleaning and storing others for future research opportunities. To overcome ongoing trauma challenges and prevent fatigue, we recruited and hired a large temporary team, including members of communities where we collected data. By recruiting participants and co-researchers at the same time and place, we both collapsed time between these activities and increased our team's contextual competency. To adapt to challenges presented by the pandemic, we created hybrid data collection procedures where some data were collected online, and some in person, while maintaining COVID-19 protections. We used similar adaptations for dissemination. Rapid research needs to be agile. Working within a convergence framework to investigate wicked problems had the unexpected added benefit of providing our team with a variety of disciplinary approaches which proved helpful in adapting to the changing conditions in the field. In addition to the resourcefulness of a transdisciplinary team, it is important to be willing to pivot in response to changes and to collect data where and when you can. To increase participation, opportunities need to be designed with flexibility, mindful of competing demands faced by individuals willing to collaborate. Collecting and analyzing data iteratively and utilizing local resources can enable rapid research that is rigorous and yields rich data. Our team applied the lessons learned to structure a rapid and iterative dissemination plan. We combined member-checking with community-level dissemination, enabling us to hone findings further before presenting to policy makers and media. Rapid research creates opportunities to make data-informed program and policy adjustments when they can be most impactful. Both the media and policy makers pay closer attention to research on current events. Hence, our recommendation is to do more rapid research! The more we do, the better we will get at it, and the more accustomed community leaders, policy makers, and program designers will become to using data to inform decisions.

A Review of Digital Twin Technology for Electric and Autonomous Vehicles

In the era of technological transformation, mobility and transportation systems are becoming more intelligent and greener. Thanks to powerful technologies and tools, electric and autonomous vehicles are spreading worldwide, substituting internal combustion engine vehicles and revolutionizing the way to drive. In this context, this paper is an extended version of the paper “Digital Twin in Intelligent Transportation Systems: a Review published in 2020 7th International Conference on Control, Decision and Information Technologies (CoDIT)”. The aim of this paper is to provide a comprehensive review of the literature from the last five years on the use of digital twin (DT) technology for Intelligent Transportation Systems (ITSs), focusing on electric and autonomous vehicles. In particular, with respect to the previous work, the focus has been expanded to include DT integration with other cutting-edge technologies, such as the Internet of Things (IoT), Big Data, artificial intelligence (AI), machine learning (ML), and 5G for ITS. Moreover, this paper presents a broad perspective on challenges in EV applications, including tracking, monitoring, battery and charge management, connectivity, security, and privacy. In addition, this paper discusses how DT can be used to effectively address the current issues in electric vehicle services, such as tracking, monitoring, battery and charge management, connectivity, security, and privacy.

Joint Intent Detection Model for Task-oriented Human-Computer Dialogue System using Asynchronous Training

How to accurately understand low-resource languages is the core of the task-oriented human-computer dialogue system. Language understanding consists of two sub-tasks, i.e., intent detection and slot filling. Intent detection still faces challenges due to semantic ambiguity and implicit intentions with users’ input. Moreover, separately modeling intent detection and slot filling significantly decrease the correctness and relevance between questions and answers. To address these issues, we propose a joint intent detection method using asynchronous training strategy. The proposed method firstly encodes local text information extracted by CNN and relationship information among words emphasized by attention structure. Later, a joint intent detection model with asynchronous training strategy is proposed by either fusing hidden states of intent detection and slot filling layers, or adopting the key information to fine-tune the whole network, greatly increasing the relevance of intent detection and slot filling subtasks. The accuracy achieved by the proposed method tested on an open-source airline travel dataset and a self-collected electricity service dataset, i.e., ATIS and ECSF, are 97.49% and 89.68%, respectively, which proves the effectiveness of joint learning and asynchronous training.

Ecuadorian electrical system: Current status, renewable energy and projections

In this research, an analysis of the electricity market in Ecuador is carried out, a portfolio of projects by source is presented, which are structured in maps with a view to an energy transition according to the official data provided. State policies are analyzed, as well as the opportunities for development in renewable energies offered by the reform of the Organic Law of the Electric Power Public Service. Additionally, the roadmap is presented, which includes an increase in the levels of renewable energies and a decrease in fossil fuels in consideration of the growing demand for electrical energy with a view to 2050 in accordance with the state approaches defined in recent years. It is considered that the total 100% renewable installed capacity by 2050 is 26,551.18 MW compared to 11,306.26 MW in 2020 between renewable and non-renewable. It is expected that the current legal framework will continue to articulate strategies for a greater penetration of renewable energies, that national purposes be achieved and international agreements celebrated both regionally and globally be fulfilled, so it is important that sufficient resources are allocated to achieve this long-awaited energy transition in Ecuador.