Energy Informatics Research Articles

Optimization of grid-connected voltage support technology and intelligent control strategies for new energy stations based on deep learning

To explore the optimization method of grid-connected voltage support technology in new energy stations, this study first analyzes and discusses this technology. Second, this study describes the deep learning model architecture and feature selection in detail and determines the framework used for the optimization model proposed here. Lastly, the development of optimization and control strategies is investigated, and the optimized model’s effectiveness is verified through experiments. The results reveal that the optimized model's accuracy, precision, recall, and F1 score are higher than those of the comparison model in the performance comparison experiment, reaching the highest values of 0.890, 0.888, 0.878, and 0.883, respectively. This reflects that the optimized model shows high performance on small datasets, and its performance benefits become more pronounced as the data volume increases. This feature is particularly significant because, in practical applications, power systems often need to process large amounts of data to achieve efficient voltage support. In simulation experiments, the optimized model demonstrates excellent performance in terms of response time, stability, robustness, and energy consumption. Moreover, this model effectively addresses various data challenges and uncertainties encountered in grid-connected voltage support technology for power systems, thereby providing robust support for stable and efficient voltage regulation. In light of the findings, this study offers substantial insights for advancing research in the realms of power systems and new energy technologies. The exploration into the application of deep learning and intelligent control strategies within power systems reveals significant potential for transforming grid optimization practices. This study accentuates how data-driven methodologies can revolutionize energy management, paving the way for smarter and more efficient energy systems. By enhancing both the responsiveness and operational efficiency of power grids, the study contributes to the acceleration of digital transformation within the energy sector, fostering innovation and laying a robust foundation for future advancements in energy informatics.

From bricks to bytes: Verifiable data for decarbonizing the building sector

Amidst the pressing need to combat climate change and curb greenhouse gas (GHG) emissions, the building sector emerges as a pivotal sector, substantially impacting worldwide emissions. Despite efforts to improve energy efficiency and incorporate non-fossil energy sources, the sector still lags in achieving the necessary decarbonization goals. Existing Building Energy Management Systems primarily prioritize economic criteria, overlooking the vital aspect of emissions reduction. Energy Informatics and Information Systems hold the potential to bridge this gap by enabling precise and verifiable GHG emissions accounting, end-to-end real-time tracking, and automated verification within Energy Management Systems (EMS). This paper presents research on designing the advancement of EMSs in the form of a Building Energy Emission Management System (BEEMS) leveraging verifiable emission data for emission-based actions. The central research question revolves around designing BEEMS to facilitate emission-based actions based on verifiable data. Following a multi-step approach, the research methodology encompasses a comprehensive literature review and iterative evaluation of our design principles through a workshop and semi-structured interviews with experts from industry and research. The contributions include a conceptual architecture of a BEEMS and six design principles for future BEEMS development. Ultimately, this research strives to facilitate end-to-end verifiable GHG emissions management in the building sector to enable emission-based energy consumption decisions, contributing to the existing body of knowledge of the Energy Informatics field on BEEMS.

From use cases to business cases: I-GReta use cases portfolio analysis from innovation management and digital entrepreneurship models perspectives

This study provides a detailed exploration of how innovation management and digital entrepreneurship models can help transform technical use cases in smart grid contexts into viable business cases, thereby bridging the gap between technical potential and market application in the field of energy informatics. It focuses on the I-GReta project Use Cases (UCs). The study employs methodologies like Use Case Analysis, Portfolio Mapping of Innovation Level, Innovation Readiness Level, and the Tech Solution Business Model Canvas (TSBMC) to analyse and transition from technical use cases to viable business cases. This approach aligns technological solutions with market demands and regulatory frameworks, leveraging digital entrepreneurship models to navigate market challenges and foster energy management, sustainability, and digitalization.

Abstracts of the 12th DACH+ Conference on Energy Informatics 2023

Abstracts of the 12th DACH+ Conference on Energy Informatics 2023

Electricity consumption simulation using random coefficient periodic autoregressive model

The concept of a continuous-time conditional linear random process involves a random kernel being integrated stochastically by a process with independent increments, which is often called a “generative process”. In cases where the “generative process” is Poisson, the resulting model represents an investigated signal as a sum of numerous stochastically dependent random impulses each of which occurs according to some inhomogeneous Poisson arrival process. This model can be applied to represent various processes related to energy consumption, such as electricity loads of electrical power systems, gas and water consumption, and other energy resources, while also considering the signals’ cyclostationarity, which is usually caused by the rhythmic nature of consumer behaviour. A member of the discretetime conditional linear cyclostationary random processes class is the random coefficient periodic autoregressive (RCPAR) model, which is appropriate for use in energy informatics, including estimation, forecasting, and computer simulation purposes. The primary objective of the paper is to establish a procedure for simulating the hourly electricity consumption of small and medium-sized enterprises using the RCPAR model, which has periodic parameters and creates cyclostationary properties while also accounting for the investigated process conditional heteroscedasticity. The statistical estimation step of the proposed procedure uses the general methodology for estimating the parameters of the RCPAR model and the methods of statistical analysis of cyclostationary signals. This step is used to identify the simulation characteristics. The simulation step is based on the methods of cyclostationary white noise generation and its transformation by a digital linear filter with random parameters. The last ones are obtained using the Gaussian random vectors computer simulation methods, taking into account the cyclostaionarity property.

Deep learning-based meta-learner strategy for electricity theft detection

Electricity theft damages power grid infrastructure and is also responsible for huge revenue losses for electric utilities. Integrating smart meters in traditional power grids enables real-time monitoring and collection of consumers’ electricity consumption (EC) data. Based on the collected data, it is possible to identify the normal and malicious behavior of consumers by analyzing the data using machine learning (ML) and deep learning methods. This paper proposes a deep learning-based meta-learner model to distinguish between normal and malicious patterns in EC data. The proposed model consists of two stages. In Fold-0, the ML classifiers extract diverse knowledge and learns based on EC data. In Fold-1, a multilayer perceptron is used as a meta-learner, which takes the prediction results of Fold-0 classifiers as input, automatically learns non-linear relationships among them, and extracts hidden complicated features to classify normal and malicious behaviors. Therefore, the proposed model controls the overfitting problem and achieves high accuracy. Moreover, extensive experiments are conducted to compare its performance with boosting, bagging, standalone conventional ML classifiers, and baseline models published in top-tier outlets. The proposed model is evaluated using a real EC dataset, which is provided by the Energy Informatics Group in Pakistan. The model achieves 0.910 ROC-AUC and 0.988 PR-AUC values on the test dataset, which are higher than those of the compared models.

Exploring the energy informatics and energy citizenship domains: a systematic literature review

To effectively address the challenges posed by the increasing share of the energy sector in global greenhouse effects, the domains of energy informatics and energy citizenship play a critical role. Energy informatics aims at using information systems and channels to reduce energy consumption. However, there is a realization that the challenges posed by global greenhouse effects cannot be catered to alone by the energy information systems. Therefore, there is a need for engaging human inhabitants to actively engage toward more sustainable means (i.e., energy citizenship) thus reducing the energy sector’s share in the global greenhouse effect. This paper presents a systematic literature review (SLR) after analysis of (n = 115) articles on the topic to identify (i) the themes considered in energy informatics and energy citizenship domains, and (ii) the interconnection between energy informatics and energy citizenship domains, (iii) energy information needs among stakeholders which establish a clear interconnect with energy citizenship. These identified themes and their interconnections are critical for energy researchers, policymakers, and energy businesses to identify relevant research topics, identify energy consumers’ needs, and create just energy transition policies. The paper additionally summarizes the gaps in the state of the art by mentioning the open research questions that arise due to the identified interconnection between energy informatics and energy citizenship.

Pedagogical Perspectives of Interdisciplinary Teaching and Research: An Energy System Modelling Outlook in Relation to Energy Informatics

The purpose of this paper is to present and discuss pedagogical frameworks and approaches to developing, delivering, and evaluating a new interdisciplinary course within the domain of energy informatics at both Master’s and PhD levels. This study is needed because many papers on sustainable energy engineering education concentrate on course content but provide very little information on the pedagogical methods employed to deliver that content. The proposed new course is called “smart energy and power systems modelling” and is aimed at discussing how mathematical optimization, in the context of computer science, can contribute to more effectively managing smart energy and power systems. Different pedagogical frameworks are discussed and adapted for the specific domain of energy informatics. An ASSURE model coupled with Bloom’s taxonomy is presented for the design of the course and identification of learning objectives; self-regulated learning strategies are discussed to enhance the learning process; a novel model called GPD (Gaussian Progression of Difficulty) for lecture planning was proposed; a teaching-research nexus is discussed for the course planning and enhancement. Adopting qualitative analyses and an inductive approach, this paper offers a thorough reflection on the strengths and weaknesses of the new course, together with improvement possibilities based on fieldwork and direct experience with the students and colleagues. Opportunities and challenges of interdisciplinary teaching are presented in light of real-world experience, with a particular focus on the interaction between mathematics and computer science to study the specific application of energy and power systems.

PROPERTIES OF DISCRETE-TIME CONDITIONAL LINEAR CYCLOSTATIONARY RANDOM PROCESSES IN THE PROBLEMS OF ENERGY INFORMATICS

Modern challenges in the energy industry require comprehensive research in the field of energy informatics, which combines computer science, control systems, and energy management systems within a single methodology. An important area of energy informatics is the study of problems of systems and processes modeling in energy, including energy loads and consumption. Linear and conditional linear random processes (CLRP) are mathematical models of signals represented as the sum of a large number of random impulses occurring at random times. The energy consumption, vibration signals of energy objects, etc. can be modeled using this approach. A variant of the CLRP model with discrete time, taking into account the cyclic properties of energy consumption, has been investigated in the paper. The goal is to justify the conditions for the discrete-time CLRP to be a periodically correlated random process, as well as a cyclostationary process. It has been shown that the corresponding conditions depend on the periodicity of the probability distributions of the kernel and the generating white noise of the CLRP representation. To achieve the goal, the properties of mathematical expectation and covariance function of CLRP, as well as the method of characteristic functions, have been used. The paper proves that the discrete-time CLRP is a periodically correlated random sequence if the generating white noise has periodic mathematical expectation and variance, and the kernel is a periodically correlated random field. Based on the analysis of the multivariate characteristic function, it has been proven that the discrete-time CLRP is cyclostationary if the generating white noise is a cyclostationary process and the kernel is a cyclostationary random field. The properties of discrete-time conditional linear cyclostationary random processes are important for mathematical modeling, simulation, statistical analysis, and forecasting of energy consumption. Keywords: mathematical model, energy informatics, conditional linear random process, cyclostationary process, white noise, characteristic function.

Editorial Special Issue: Design Science Research in Information Systems and Technology

The papers in this special section focus on design science research in information systems and technology. The rapid digital transformation of businesses and society creates new challenges and opportunities for information systems (IS) research, with the designing of system becoming a strong focus. Technologies, such as blockchain, cloud computing, and wearable devices, have spawned a paradigmatic shift in the design of IS. Thus, design science research in IS has evolved to become a mature yet thriving area of research. Design science seeks to extend the boundaries of human and organizational capabilities by designing new and innovative constructs, models, methods, processes, and systems. Scholars having diverse backgrounds in fields, such as IS, computer science, software engineering, energy informatics, and medical informatics, are actively engaged in generating novel solutions to interesting design problems in IS.

Understanding the role of digitalization and social media on energy citizenship.

The digitalisation of the energy domain can bring forth numerous aspects of the energy transition that can boost the emergence of energy citizenship, information sharing, and improved decision-making processes. However, this is premised on citizens being able to make sense of (digital) information. Hence, this paper proposes a link between energy informatics and energy citizenship via energy literacy, considering the cognitive and affective aspects of energy literacy and their relation to behaviour and action. By doing so, this paper aims to understand how the use of energy-related information and social media within five different case studies from the GRETA project can impel energy citizenship. This paper approaches this rationale through different means: (a) structured interviews to understand how citizens understand and make use of energy information within the case studies; (b) topic modelling on the content of those interviews to identify common factors that might spur on hinder behaviour change towards energy citizenship; and (c) social media content analysis to identify key energy-related topics of discussions among citizens around the globe and assess the role of social media as a tool for energy citizenship. As a result, this paper identified some key takeaways to improve the delivery of energy-related information to energy citizens for enhanced energy citizenship. These takeaways allow to conclude that it is fundamental to surpass the formal boundaries of techno-economic constructs and start addressing qualitative/subjective constructs (e.g., emotions, affections, and feelings) to foster energy citizenship. Also, these takeaways could be translated into social mechanism principles in the design of frontend energy-related digital platforms for improved end-user interactions and energy citizenship. Finally, this paper recognised the need to incentivise energy citizens to use social media for consuming energy-related information, and the need to formulate coordinated and coherent response strategies for disseminating energy-related information.

Dynamic Capabilities in Electrical Energy Digitalization: A Case from the Norwegian Ecosystem

This paper aims to identify the dynamic capabilities required for electrical energy service providers to transform toward a digital and platform-based business models in the context of the current energy transition. The paper contributes to two fields: Information systems in the domain of platforms ecosystems and digital services innovation through the usage of dynamic capabilities theoretical lens and the field of energy informatics in the domain of digital business models and service innovation. Through the case study approach we investigate the case of Norwegian electrical energy provider TrønderEnergi and how the company is moving toward a fully digital business model and how the company build the dynamic capabilities required for the digitalization era. Through semi-structured interviews, the study managed to identify several activities related to each capability and then classified these activities under three main activities, which are: sensing, seizing, and transforming, and then classified them into sub-capabilities and identified activities related to each sup capability. The paper concludes with managerial implications for practitioners and initiates an empirical extension for the dynamic capabilities theoretical lens.

Make or buy: IT-based decision support for grid imbalance settlement in smarter electricity networks

Decision (support) systems are a particularly important type of information system to energy informatics. A key challenge in energy informatics is that electricity supply must be in balance with demand at all times. More volatile renewable energy sources increase the relevance of electricity network balancing, i.e., imbalance settlement. Typically, electricity distribution network operators bought balancing power from external service providers (Buy option). Interestingly, however, more local energy resources help smarter electricity networks develop a Make option, as in our real-world evaluation. Choosing the better decision alternative within the relevant timeframes challenges human decision-making capabilities. Therefore, this research proposes a model-based decision system to improve the operators’ decisions concerning Make or Buy under various levels of data quality represented by availability, granularity, and timeliness. The study reports savings up to 40% of costs for imbalance settlement supporting ambitious development efforts by the municipality we study in our real-world evaluation.

Abstracts of the 11th DACH+ Conference on Energy Informatics

Abstracts of the 11th DACH+ Conference on Energy Informatics

An Intelligent Data-Driven Approach for Electrical Energy Load Management Using Machine Learning Algorithms

Data-driven electrical energy efficiency management is the emerging trend in electrical energy forecasting and management. This fusion of data science, artificial intelligence, and electrical energy management has turned out to be the most precise and robust energy management solution. The Smart Energy Informatics Lab (SEIL) of the Indian Institute of Technology (IIT) conducted an experimental study in 2019 to collect massive data on university campus energy consumption. The comprehensive comparative study preparatory to the recommendation of the best candidate out of 24 machine learning algorithms on the SEIL dataset is presented in this work. In this research work, an exhaustive parametric and empirical comparative study is conducted on the SEIL dataset for the recommendation of the optimal machine learning algorithm. The simulation results established the findings that Bagged Trees, Fine Trees, and Medium Trees are, respectively, the best-, second-best-, and third-best-performing algorithms in terms of efficacy. On the contrary, a reverse ranking is observed in terms of efficiency. This is grounded in the fact that Bagged Trees is most effective algorithm for the said application and Medium Trees is the most efficient one. Likewise, Fine Trees has the optimum tradeoff between efficacy and efficiency.

Some features of Hilbert transform and their use in energy informatics

Information-measuring technologies (IMT) are an important instrument for solving problems of energy informatics. They allow to form primary information based on the interaction of energy facilities with IMT sensors that form information signals. In many practical applications, the constructive model of information signals is the model of narrowband signals. The article summarizes the features of the discrete Hilbert transform and its application to obtain the primary characteristics of information signals – bypass and phase as functions of time. The main advantages of using the discrete Hilbert transform in signal processing for energy informatics are considered, including the consistency of obtaining frequency and time characteristics, high information content, the ability to analyze the dynamics of changes in signal characteristics, the possibility of obtaining samples of characteristics of information signals of significant volumes, etc. It is proposed to use a phase characteristic to select the time interval that limits the signal sample and sets it to a multiple of the signal period, and the sampling rate of information signals to reduce the errors in estimating their spectrum. The possibility of obtaining on their basis secondary deterministic (voltage level, voltage deviations from the nominal level, attenuation coefficient, signal period, signal phase shift, oscillation frequency, etc.) and statistical (sample characteristic, sample variance, sample median, sample circular variance, sample circular median, sample circular kurtosis, etc.) of signal information characteristics, which allows more complete to use their information resource. These characteristics can be used both for assessing power quality characteristics and for monitoring and diagnosing of energy facilities. Keywords: energy informatics, information signals, signal processing, discrete Hilbert transform, amplitude signal characteristics, phase signal characteristics

Torch-NILM: An Effective Deep Learning Toolkit for Non-Intrusive Load Monitoring in Pytorch

Non-intrusive load monitoring is a blind source separation task that has been attracting significant interest from researchers working in the field of energy informatics. However, despite the considerable progress, there are a very limited number of tools and libraries dedicated to the problem of energy disaggregation. Herein, we report the development of a novel open-source framework named Torch-NILM in order to help researchers and engineers take advantage of the benefits of Pytorch. The aim of this research is to tackle the comparability and reproducibility issues often reported in NILM research by standardising the experimental setup, while providing solid baseline models by writing only a few lines of code. Torch-NILM offers a suite of tools particularly useful for training deep neural networks in the task of energy disaggregation. The basic features include: (i) easy-to-use APIs for running new experiments, (ii) a benchmark framework for evaluation, (iii) the implementation of popular architectures, (iv) custom data loaders for efficient training and (v) automated generation of reports.

Preface

The 2022 International Conference on Energy Utilization and Automation (ICEUA 2022) was held on February 25th to 27th, 2022 as a virtual conference due to the growing concerns over the coronavirus outbreak (COVID-19), and in order to protect the well-being of our attendees, partners, and staff as our number one priority. The meeting arounds the network communication and recent research achievements in the field of information security, from institutions of higher learning, scientific research institutes, enterprises and institutions at home and abroad experts, professors, scholars, engineers and so on to provide a share professional experience, expand the professional network, face to face to new ideas and show the research results of the international platform, Exploring key challenges and research directions in this field, with a view to promoting the development and application of theories and technologies in this field in universities and enterprises, as well as establishing business or research connections for attendees and seeking global partners for future ventures.This scientific event brings together more than 100 national and international researchers in Energy Utilization and Automation. On top of the local participants coming from different national universities, international participants are also registered from different countries, namely Malaysia, India, Ethiopia, Australia. During the conference, the conference model was divided into three sessions, including oral presentations, keynote speeches, and online Q&A discussion. In the first part, some scholars, whose submissions were selected as the excellent papers, were given about 5-10 minutes to perform their oral presentations one by one. Then in the second part, keynote speakers were each allocated 30-45 minutes to hold their speeches.In the second part, we invited four professors as our keynote speakers. Assoc.Prof. Guohua Xie, Wuhan University, performed a speech: Solution-Processed Organic Light-Emitting Devices. And then we had Assoc.Prof. Muhyiddine Jradi, Center for Energy Informatics, University of Southern Denmark. He presented an insightful speech: Auditing and Smartness Evaluation of Building Automation and Control Systems. Prof. Rajan Jose, Faculty of Industrial Sciences & Technology, Universiti Malaysia Pahang, delivered a speech: Energy for 21st Century and Beyond. Prof. Thanikaivelan Palanisamy, our finale keynote speaker, from CSIR-Central Leather Research Institute. He presented an insightful speech: Advanced Sustainable Materials from Leather Wastes for Energy and Environmental Applications. Their insightful speeches had triggered heated discussion in the third session of the conference. Every participant praised this conference for disseminating useful and insightful knowledge.List of Committee member are available in this pdf.

Identifiers for structural warnings of malfunction in power grid networks

Although its uninterrupted supply is essential for everyday life, the electricity occasionally experiences disruptions and outages. The work presented in the current paper aims to initiate the research to design a strategy based on advanced approaches of algebraic topology to prevent such malfunctions in a power grid network. Simplicial complexes are constructed to identify higher-order structures embedded in a network and, alongside a new algorithm for identifying delegates of the simplicial complex, are intended to pinpoint each element of the power grid network to its natural layer. Results of this methodology for analysis of a power grid network can single out its elements that are at risk to cause cascade problems which can result in unintentional islanding and blackouts. Further development of the outcomes of research can find implementation in the algorithms of the energy informatics research applications.

Abstracts of the 10th DACH+ Conference on Energy Informatics

Abstracts of the 10th DACH+ Conference on Energy Informatics