Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

hysteresis in magnetism (electromagnetism)

For the smart grid energy theft identification, this letter introduces a gradient boosting theft detector (GBTD) based on the three latest gradient boosting classifiers (GBCs): 1) extreme gradient boosting; 2) categorical boosting; and 3) light gradient boosting method. While most of existing machine learning (ML) algorithms just focus on fine tuning the hyperparameters of the classifiers, our ML algorithm, GBTD, focuses on the feature engineering-based preprocessing to improve detection performance as well as time-complexity. GBTD improves both detection rate and false positive rate (FPR) of those GBCs by generating stochastic features like standard deviation, mean, minimum, and maximum value of daily electricity usage. GBTD also reduces the classifier complexity with weighted feature-importance-based extraction techniques. Emphasis has been laid upon the practical application of the proposed ML for theft detection by minimizing FPR and reducing data storage space and improving time-complexity of the GBTD classifiers. Additionally, this letter proposes an updated version of the existing six theft cases to mimic real-world theft patterns and applies them to the dataset for numerical evaluation of the proposed algorithm.

Energy Theft Detection Using Gradient Boosting Theft Detector With Feature Engineering-Based Preprocessing

Gradient Boosted Decision Trees (GBDT’s) are a powerful tool for classification and regression tasks in Big Data. Researchers should be familiar with the strengths and weaknesses of current implementations of GBDT’s in order to use them effectively and make successful contributions. CatBoost is a member of the family of GBDT machine learning ensemble techniques. Since its debut in late 2018, researchers have successfully used CatBoost for machine learning studies involving Big Data. We take this opportunity to review recent research on CatBoost as it relates to Big Data, and learn best practices from studies that cast CatBoost in a positive light, as well as studies where CatBoost does not outshine other techniques, since we can learn lessons from both types of scenarios. Furthermore, as a Decision Tree based algorithm, CatBoost is well-suited to machine learning tasks involving categorical, heterogeneous data. Recent work across multiple disciplines illustrates CatBoost’s effectiveness and shortcomings in classification and regression tasks. Another important issue we expose in literature on CatBoost is its sensitivity to hyper-parameters and the importance of hyper-parameter tuning. One contribution we make is to take an interdisciplinary approach to cover studies related to CatBoost in a single work. This provides researchers an in-depth understanding to help clarify proper application of CatBoost in solving problems. To the best of our knowledge, this is the first survey that studies all works related to CatBoost in a single publication.

/pdf/catboost-for-big-data-an-interdisciplinary-review-utp91h5i0y.pdf

CatBoost for big data: an interdisciplinary review

HVDC systems are playing an increasingly significant role in energy transmission due to their technical and economic superiority over HVAC systems for long distance transmission. HVDC is preferable beyond 300–800 km for overhead point-to-point transmission projects and for the cable based interconnection or the grid integration of remote offshore wind farms beyond 50–100 km. Several HVDC review papers exist in literature but often focus on specific geographic locations or system components. In contrast, this paper presents a detailed, up-to-date, analysis and assessment of HVDC transmission systems on a global scale, targeting expert and general audience alike. The paper covers the following aspects: technical and economic comparison of HVAC and HVDC systems; investigation of international HVDC market size, conditions, geographic sparsity of the technology adoption, as well as the main suppliers landscape; and high-level comparisons and analysis of HVDC system components such as Voltage Source Converters (VSCs) and Line Commutated Converters (LCCs), etc. The presented analysis are supported by practical case studies from existing projects in an effort to reveal the complex technical and economic considerations, factors and rationale involved in the evaluation and selection of transmission system technology for a given project. The contemporary operational challenges such as the ownership of Multi-Terminal DC (MTDC) networks are also discussed. Subsequently, the required development factors, both technically and regulatory, for proper MTDC networks operation are highlighted, including a future outlook of different HVDC system components. Collectively, the role of HVDC transmission in achieving national renewable energy targets in light of the Paris agreement commitments is highlighted with relevant examples of potential HVDC corridors.

/pdf/hvdc-transmission-technology-review-market-trends-and-future-1zjfr7832z.pdf

HVDC Transmission: Technology Review, Market Trends and Future Outlook

Non-technical electricity losses due to anomalies or frauds are accountable for important revenue losses in power utilities. Recent advances have been made in this area, fostered by the roll-out of smart meters. In this paper, we propose a methodology for non-technical loss detection using supervised learning. The methodology has been developed and tested on real smart meter data of all the industrial and commercial customers of Endesa. This methodology uses all the information the smart meters record (energy consumption, alarms and electrical magnitudes) to obtain an in-depth analysis of the customer’s consumption behavior. It also uses auxiliary databases to provide additional information regarding the geographical location and technological characteristics of each smart meter. The model has been trained, validated and tested on the results of approximately 57 000 on-field inspections. It is currently in use in a non-technical loss detection campaign for big customers. Several state-of-the-art classifiers have been tested. The results show that extreme gradient boosted trees outperform the rest of the classifiers.

Detection of Non-Technical Losses Using Smart Meter Data and Supervised Learning

Non-technical losses (NTL) in electricity utilities are responsible for major revenue losses. In this paper, we propose a novel end-to-end solution to self-learn the features for detecting anomalies and frauds in smart meters using a hybrid deep neural network. The network is fed with simple raw data, removing the need of handcrafted feature engineering. The proposed architecture consists of a long short-term memory network and a multi-layer perceptrons network. The first network analyses the raw daily energy consumption history whilst the second one integrates non-sequential data such as its contracted power or geographical information. The results show that the hybrid neural network significantly outperforms state-of-the-art classifiers as well as previous deep learning models used in NTL detection. The model has been trained and tested with real smart meter data of Endesa, the largest electricity utility in Spain.

Hybrid Deep Neural Networks for Detection of Non-Technical Losses in Electricity Smart Meters

Power transmission systems are called upon to play a crucial role in the future decarbonized, electrified and digital energy sectors, as they constitute the most effective way of distributing vast amounts of electricity from renewable energy sources to faraway locations. This paper aims at critically reviewing worldwide the regional visions, as well as existing and newer technologies involved in the development and upgrading of bulk transmission systems. The main emphasis is put on the major challenges and boundary conditions arising during the paradigm change that electric energy systems will undergo over the next half century. Recent research and pilot projects on this subject are revised, embracing effective combinations of AC and DC technologies, such as high-voltage AC transmission systems, phase-shifting transformers, flexible AC transmission systems and point-to-point and multi-terminal high-voltage DC systems. The challenges faced by this transition involve technical, economical, environmental, regulatory and social factors that will finally determine the preference for one or another technology in particular regions of the world. General recommendations and guidelines are proposed to increase the probability of success of future transmission projects, regardless of the type of technology, geographic location or particular external conditions. Several somewhat competing architectures are envisioned in this more volatile context, all together offering great possibilities to increase transmission capability while loop flows are prevented and system stability is preserved or enhanced.

Future power transmission: Visions, technologies and challenges

Magnetic field shielding optimization in underground power cable duct banks

With the continuous increase in the number and relevance of electric transmission lines and distribution networks, there is a higher exposure to the magnetic fields generated by them, leading to more cases of human electrosensitivity, which greatly necessitates the design and development of magnetic field mitigation procedures and, at the same time, the need to minimize both performance degradation and deterioration in the efficiency as well. During the last four decades, fruitful results have been reported about extremely low frequency magnetic field mitigation, giving a wide variety of solutions. This survey paper aims to give a comprehensive overview of cost-effective optimization techniques destined to magnetic field mitigation in power systems, with particular attention to the results reported in the last decade.

Pedro Cruz-Romero

Papers

Detection of Non-Technical Losses Using Smart Meter Data and Supervised Learning

Hybrid Deep Neural Networks for Detection of Non-Technical Losses in Electricity Smart Meters

Future power transmission: Visions, technologies and challenges

Magnetic field shielding optimization in underground power cable duct banks

A Survey on Optimization Techniques Applied to Magnetic Field Mitigation in Power Systems