Turkish Electricity Distribution Research Articles

Loss Per Consumer approach for efficiency analysis of Turkish Electricity Distribution Companies by Using DEA

Loss Per Consumer approach for efficiency analysis of Turkish Electricity Distribution Companies by Using DEA

GENERATIVE AI IN ELECTRICITY DISTRIBUTION: A QUALITATIVE EXPLORATION

Purpose- The purpose of this study is to explore the application and potential of generative artificial intelligence (AI) within the context of electricity distribution companies. The study aims to investigate how these advanced AI technologies, particularly Generative Adversarial Networks (GANs), can address the sector's pressing challenges, such as load forecasting, power outage prediction, and preventive maintenance. Methodology- The study employs a qualitative case study methodology, providing an in-depth analysis of real-world applications of generative AI within electricity distribution companies. The selection of cases represents a wide variety of experiences and contexts, facilitated by both primary data collected through semi-structured interviews with key personnel within the organizations and secondary data derived from an extensive review of company reports, public documentation, and industry publications. The gathered data was systematically analyzed using thematic analysis to identify and report recurring patterns and themes. Findings- The analysis reveals that generative AI has been successfully implemented in various operational aspects of electricity distribution. The first case study presents how GANs have significantly improved load forecasting accuracy in an Eastern Turkish electricity distribution company. The second case study from Southern Turkey showcases how GANs have been used for predicting power outages, thereby aiding efficient resource allocation, reducing downtime, and enhancing customer satisfaction. Lastly, the third case from Northern Turkey demonstrates how generative AI has contributed to effective preventive maintenance of distribution equipment, improving overall system reliability. Conclusion- Based on the analysis findings, it may be concluded that generative AI holds transformative potential for the electricity distribution sector. While the implementation of these technologies is associated with challenges such as data privacy, security, and the requirement of technical expertise, the benefits in terms of improved accuracy, system reliability, and resource efficiency provide a strong justification for their adoption. The paper underlines the importance of an interdisciplinary collaboration between AI researchers, electrical engineers, industry professionals, and policymakers for furthering the adoption of these technologies. As the field of generative AI continues to evolve, it is expected to have an even greater impact on the electricity distribution sector, thereby opening up exciting opportunities for future research and application. Keywords: Generative artificial intelligence (ai), electricity distribution companies, generative adversarial networks (gans), load forecasting, outage prediction, preventive maintenance JEL Codes: M40, M41

Supply continuity in Turkish electricity distribution grid: electricity interruption cost forecasting with time series analysis and machine learning

Supply continuity in Turkish electricity distribution grid: electricity interruption cost forecasting with time series analysis and machine learning

Performance Measurement with Stochastic Data Envelopment Analysis: Comparative Analysis of Turkish Electricity Distribution Companies

Bu çalışmada, Türkiye’de bulunan 21 elektrik dağıtım şirketinin performans ölçümü ve etkinlik çerçevesinde kıyaslanması amaçlamıştır. Dağıtım şirketlerinin rasgele girdi ve çıktı değişkenleri, stokastik girdiye ve çıktıya yönelimli şans kısıtlı Banker, Charnes ve Cooper (BCC) Veri Zarflama Analizi (VZA) modellerine simetrik hata yapısı ile dâhil edilmiştir. Deterministik girdiye ve çıktıya yönelimli BCC VZA modelleriyle stokastik modeller karşılaştırılmış, stokastik ölçüm değerleri, deterministik ölçüm değerleriyle doğrulanmıştır. Çalışmada, belirsiz verilerle çalışan stokastik VZA için şans kısıtlı problemler oluşturulmuş, stokastik modeller deterministik eşdeğerlerine dönüştürülmüş ve doğrusallaştırılmıştır. VZA modellerinde Türkiye’nin 21 elektrik dağıtım şirketi karar verme birimleri (KVB) olarak kabul edilmiştir. Elde edilen sonuçlarla, deterministik ve stokastik modellerin etkinlik sonuçlarına göre, etkin ve etkin olmayan elektrik dağıtım şirketleri belirlenmiştir. Amaç, analiz edilen verilerde istatistiksel gürültüyü VZA modellerine ekleyip, performans ölçümünü bu doğrultuda gerçekleştirmektir. Modellere gürültü unsuru tek faktörlü simetrik hata yapısı kapsamında dâhil edilmiş, modeller arasındaki farklı sonuçları incelemek amacıyla her hata seviyesi için modeller ayrı ayrı ele alınmıştır. Çalışma, Türkiye'de elektrik dağıtım şirketlerinin değerlendirilmesinde, simetrik hata yapısı ile stokastik verileri VZA’ya dâhil eden ilk yaklaşımdır.

Air Products awarded contract to build, own and operate coal-to-syngas plant to supply syngas for Jiutai New Material Co in Hohhot, China

The Turkish electricity distribution and electricity supply businesses have been substantial affected by the transition from a vertically integrated public monopoly model to a model of regulated competition with privatized and unbundled firms. We analyze how select elements of sustainability have been and will be affected by this transition. Specifically, we consider transparency of the electricity market as a whole and implications for electricity supply and distribution, the financial soundness of the electricity distribution industry, the quality of electricity delivered by the distributors, and the competitiveness of the electricity supply business. The key finding is that little if any progress toward sustainability has been achieved. We conclude that there remains much for policymakers to do to establish a sustainable market structure.

Long-term load forecasting: models based on MARS, ANN and LR methods

Electric energy plays an irreplaceable role in nearly every person’s life on earth; it has become an important subject in operational research. Day by day, electrical load demand grows rapidly with increasing population and developing technology such as smart grids, electric cars, and renewable energy production. Governments in deregulated economies make investments and operating plans of electric utilities according to mid- and long-term load forecasting results. For governments, load forecasting is a vitally important process including sales, marketing, planning, and manufacturing divisions of every industry. In this paper, we suggest three models based on multivariate adaptive regression splines (MARS), artificial neural network (ANN) and linear regression (LR) methods to model electrical load overall in the Turkish electricity distribution network, and this not only by long-term but also mid- and short-term load forecasting. These models predict the relationship between load demand and several environmental variables: wind, humidity, load-of-day type of the year (holiday, summer, week day, etc.) and temperature data. By comparison of these models, we show that MARS model gives more accurate and stable results than ANN and LR models.

A panel data analysis on the costs of Turkish electricity distribution companies

Turkey initiated electricity market reforms in 2001, and privatization of distribution companies was one of the main pillars of the electricity market reform. However, many problems have been encountered during the reform process, and both the regulator and the regulated parties are still struggling with major issues such as high loss ratio, financial soundness of the companies, and service quality problems. Moreover, there are concerns about the financial sustainability of these companies due to the recent depreciation of the Turkish Lira. In this respect, this article aims to contribute to the discussions by using panel data analysis to understand the factors affecting the costs of the distribution companies between 2011 and 2014.

The sustainability of Turkish electricity distributors and last-resort electricity suppliers: What did transition from vertically integrated public monopoly to regulated competition with privatized and unbundled firms bring about?

The Turkish electricity distribution and electricity supply businesses have been substantial affected by the transition from a vertically integrated public monopoly model to a model of regulated competition with privatized and unbundled firms. We analyze how select elements of sustainability have been and will be affected by this transition. Specifically, we consider transparency of the electricity market as a whole and implications for electricity supply and distribution, the financial soundness of the electricity distribution industry, the quality of electricity delivered by the distributors, and the competitiveness of the electricity supply business. The key finding is that little if any progress toward sustainability has been achieved. We conclude that there remains much for policymakers to do to establish a sustainable market structure.

Technical Efficiency in Turkish Electricity Distribution Market: An Application of Stochastic Frontier Analysis (SFA)

This study analyzes the technical efficiencies of Turkish electricity distribution companies (21 in total) throughout 2002 and 2009. For this aim, we used three different model specifications, all of which are generated from a Stochastic Frontier Analysis (SFA) model. It has been shown that the signs and significance levels of the coefficient estimations are very consistent and satisfactory in all models. For example, all model specifications confirm the presence of increasing returns to scale and of a mild technological progress over time in the market. In addition, among the inputs, all inputs except the quality of the electricity delivered are important in enhancing technical efficiency of the electricity distribution companies, according to the alternative specifications.

Smart grid opportunities and applications in Turkey

Abstract A smart grid is a system that uses information and communication technologies to integrate, in an intelligent way, all users connected to the electrical power system considering their behaviour and actions. For this purpose, information about the electrical network, such as the current, the voltage or the power, is gathered together over time so that the behaviour of suppliers and consumers can be observed and automatically coordinated. Smart grids are becoming a significant part in the configuration of future electrical power systems. A lot of research has been done on using smart grids to achieve highly efficient and user-friendly electrical power systems. Many new methods have been introduced to solve the difficulties energy providers face when transforming conventional electrical networks into smart grids. These difficulties include the integration of renewable energy and different grid systems at national and international levels due to changes in frequency, voltage and in the synchronisation mechanism. This paper provides an outline of the European smart grid projects and gives an overview of the current infrastructure and smart grid applications of the Turkish Electricity Production System Operator (EUAS), Turkish Electricity Transmission System Operator (TEIAS), and Turkish Electricity Distribution System Operator (TEDAS). In this paper the feasibility of the further steps required is described and some assessments are made and suggestions given on smart grid developments in general.

Efficiency and productivity (TFP) of the Turkish electricity distribution companies: An application of two-stage (DEA&Tobit) analysis

In this study, we analyze the efficiency performances of 21 Turkish electricity distribution companies during the period of 2002–2009. For this aim, we employ a two-stage analysis in order to take into account the business environment variables which are beyond the control of distribution companies. We determine the efficiency performances of the electricity distribution companies by help of DEA in the first stage. Then, in the second stage, using these calculated efficiency scores as dependent variable, we utilize Tobit model to determine the business environment variables which may explain the efficiency scores. According to the results, customer density of the region and the private ownership affect the efficiencies positively. Thus, the best strategy to improve efficiency in the market is privatizing the public distribution companies.

The effect of power distribution privatization on electricity prices in Turkey: Has liberalization served the purpose?

Various electricity reforms have been adopted by a number of countries within the last 2 decades. Turkey, as one of those countries, has restructured its electricity market and intensively privatized the distribution companies. As one of the main targets of the liberalization efforts in the sector was announced to be reduced consumer prices, it is a matter of interest to look at the related developments after privatizations. Hence, this study attempts to explore the impact of power distribution privatization in Turkey on the national end-user electricity prices. Results of the analysis suggest that privatization of electricity distribution companies has not yielded the expected retail price declines within the first 4 years of the program. Whereas wholesale tariffs exhibit a reduction in the rate of 10%, retail tariffs show an increase of 5.9% within the period in question. Besides, the unstable patterns of the two tariffs imply that the market is not yet ready for the automatic pricing mechanism planned to be implemented based on a cost-reflective methodology. Therefore, results indicate that the factors behind the unsatisfactory outcomes of the program should be explored in order for the privatization efforts in the Turkish electricity distribution market to serve the purpose.

The effect of merger and consolidation activities on the efficiency of electricity distribution regions in Turkey

In this study, we analyze the efficiency performances of Turkish electricity distribution companies throughout 2002 and 2009 in the stochastic frontier analysis (SFA) framework. Our more specific goal is to measure how the efficiency performances of the electricity distribution regions were affected by the mergers between distribution regions occurred in 2005. The results demonstrate that efficiencies of the companies serving to mostly the residential customers are higher than those of other companies. However, the positive impact of residential customers on the efficiencies decreased significantly following the mergers between electricity distribution companies. In contrast, the positive impact of higher customer density on efficiency also decreased, but insignificantly following the restructuring activities in the market in 2005. Our study also witnesses that the positive impact of the mergers on the efficiencies decreases as the proportion of sales to residential customers in regions increases. In contrast, the restructuring activities of 2005 increased equally the efficiencies of the companies serving in the regions with higher and lower customer densities. • We analyze efficiency performances of Turkish electricity distribution companies. • The efficiencies of companies serving to mostly residential customers are higher. • Positive impact of residential customers on the efficiencies dropped after mergers. • Positive impact of customer density also decreased, but insignificantly. • Positive impact of mergers on efficiency decreases as sales to residents increase.

Performance assessment of Turkish electricity distribution utilities: An application of combined FAHP/TOPSIS/DEA methodology to incorporate quality of service

The recent years have witnessed the increase in the importance of service quality in the performance measurement of the regulated utilities. In this study, to incorporate quality of service in performance measurement, we propose a combined methodology of FAHP/TOPSIS/DEA methods, and apply it to the Turkish electricity distribution market. With FAHP method, the relative importance levels of different quality indicators are determined. Then TOPSIS method is used to generate quality of service variable. And finally this variable is used as an output in the DEA stage, and efficiency performances of the electricity distribution utilities are determined. The most important advantage of the combined methodology is that it allows taking into account several quality measures simultaneously instead of relying on only one dimension of the quality.

Stochastic frontier panel data modelling for regulatory benchmarking: An application to the Turkish electricity distribution sector

This paper considers stochastic frontier panel data methods for regulatory benchmarking that allow for both latent heterogeneity and inefficiency, encapsulating the regulatory dilemma in comparative efficiency analysis for incentive regulation. It applies a distance function model with appropriate concavity properties for econometric estimation to a panel of electricity distribution utilities in Turkey since, in preparation for accession to the European Union, Turkey is required to align the sector with incentive benchmarking regulation that characterizes the European Union. The results confirm the importance of allowing simultaneously for heterogeneity and inefficiency and emphasize the need for specific time-invariant heterogeneity information, such as geographical data, on regulated companies in different regions.

The privatization of electricity distribution in Turkey: A legal and economic analysis

This paper analyzes the recent regulatory reform in the Turkish Electricity Distribution Market from a legal and economic perspective. We highlight tensions between the judiciary, politicians and bureaucracy and discuss their economic consequences. The paper engages in a discussion of economic consequences of legal procedures. We stress interactions between legal decisions and economic institutions. The historical positions of the Constitutional Court and Danıştay (Council of State), on privatizations have been ambivalent and it is hard to qualify them as an incentive for privatization and reform, despite some recent liberal decisions. We address reasons behind their decisions and offer some suggestions toward improving the privatization process.

Short term and medium term power distribution load forecasting by neural networks

Load forecasting is an important subject for power distribution systems and has been studied from different points of view. In general, load forecasts should be performed over a broad spectrum of time intervals, which could be classified into short term, medium term and long term forecasts. Several research groups have proposed various techniques for either short term load forecasting or medium term load forecasting or long term load forecasting. This paper presents a neural network (NN) model for short term peak load forecasting, short term total load forecasting and medium term monthly load forecasting in power distribution systems. The NN is used to learn the relationships among past, current and future temperatures and loads. The neural network was trained to recognize the peak load of the day, total load of the day and monthly electricity consumption. The suitability of the proposed approach is illustrated through an application to real load shapes from the Turkish Electricity Distribution Corporation (TEDAS) in Nigde. The data represents the daily and monthly electricity consumption in Nigde, Turkey.