Ahmet Yucekaya

Purpose: The power plants face failures during start-up or operation which may cause long disruptions in electricity generation, a serious problem for both electricity producer and market operater. The capacity of coal plant is submitted to the day-ahead market for the next day. When the plant is scheduled for the operation, a failure prevents power generation and causes capacity loss and downtime cost. Hence, a framework needs to be developed to estimate the failures before the operation and market settlement. Design/methodology/approach: In this work, we use historical data for plant failures and analyze the failure types, modes and components using descriptive statistics. Then Failure Mode Effect Analysis is used to analyze the faults, errors and failures for each plant. To address varying risk levels, risk priority numbers are calculated for each failure type that can cause crucial failures for each plant. Then, the Andersen–Gill’s extended proportional hazards model (PHM) is applied to calculate the probability of failures in power plants at different times. Findings: Using a threshold level for survival probability, which indicates the probability of a failure for each plant, a prognostic alert system is created that can predict the timing of an upcoming failure. The proposed methodology provides both plant and previous failure-based survival curves to help decision makers with the operations. Originality/value: Coal plants are still crucial for the sustainable operation of electricity markets. The proposed methodology is a novel, generic and promising solution for coal plants as the decision makers will be able to schedule a maintenance before failure using this methodology.

Warehouses are vital in linking production to consumption, often using a forward–reserve layout to balance picking efficiency and bulk storage. However, replenishing the forward area from reserve storage is prone to delays and congestion, especially during high-demand periods. This study investigates the strategic use of buffer areas—intermediate zones between forward and reserve locations—to enhance flexibility and reduce bottlenecks. Although buffer zones are common in practice, they often lack a structured decision-making framework. We address this gap by developing an optimization model that integrates demand forecasts to guide daily replenishment decisions. To handle the computational complexity arising from large state and action spaces, we implement an approximate dynamic programming (ADP) approach using certainty-equivalent control within a rolling-horizon framework. A real-world case study from an automotive spare parts warehouse demonstrates the model’s effectiveness. Results show that strategically integrating buffer zones with an ADP model significantly improves replenishment timing, reduces direct picking by up to 90%, minimizes congestion, and enhances overall flow of intra-warehouse inventory management.

Electricity consumption in a country, region, or city comprises demand from residential, industrial, commercial, and other specific consumptions such as street lighting, and agricultural related consumptions, along with losses from leakage and transmission and unauthorized usage. However, tracking the specific consumption components in real time is challenging, as detailed consumption data for each category is typically determined only after billing periods. Understanding the electricity demand of each subcategory and its proportion within total consumption is crucial for effective system planning and operation. This study develops a framework to disaggregate total electricity consumption into subcategories—residential, industrial/ commercial, irrigation, and lighting—at an hourly resolution. The methodology depends crucially on a special day detection approach that identifies consumption patterns on days at which where electricity usage is at its lowest, without any a priori information of the holidays in each country or a region. Based on this, baseline consumption levels for different periods are determined, indices for subcategories are developed, and time series models are generated to analyze consumption trends. For validation, the methodology is applied to Turkish electricity data, where the structure of consumption is analyzed in relation to holidays and special occasions, accounting for the reduction in demand during these periods. The proportions of residential, industrial/commercial, and lighting consumption are derived from total consumption, and the remaining categories are estimated accordingly. Finally, the accuracy and convergence of the results are evaluated, and the findings are presented with their implications for energy planning and grid management.

Vehicle owners often use certified service centers throughout the warranty period, which usually extends for five years after buying. Nonetheless, after this timeframe concludes, a large number of owners turn to unapproved service providers, mainly motivated by financial factors. This change signifies a significant drop in income for automakers and their certified service networks. To tackle this issue, manufacturers utilize customer relationship management (CRM) strategies to enhance customer loyalty, usually depending on segmentation methods to pinpoint potential clients. However, conventional approaches frequently do not successfully forecast which clients are most likely to need or utilize maintenance services. This research introduces a machine learning-driven framework aimed at forecasting the probability of monthly maintenance attendance for customers by utilizing an extensive historical dataset that includes information about both customers and vehicles. Additionally, this predictive approach supports workforce planning and scheduling within after-sales service centers, aligning with AI-driven labor optimization frameworks such as those explored in the AI4LABOUR project. Four algorithms in machine learning—Decision Tree, Random Forest, LightGBM (LGBM), and Extreme Gradient Boosting (XGBoost)—were assessed for their forecasting capabilities. Of these, XGBoost showed greater accuracy and reliability in recognizing high-probability customers. In this study, we propose a machine learning framework to predict vehicle maintenance visits for after-sales services, leading to significant operational improvements. Furthermore, the integration of AI-driven workforce allocation strategies, as studied within the AI4LABOUR (reshaping labor force participation with artificial intelligence) project, has contributed to more efficient service personnel deployment, reducing idle time and improving customer experience. By implementing this approach, we achieved a 20% reduction in information delivery times during service operations. Additionally, survey completion times were reduced from 5 min to 4 min per survey, resulting in total time savings of approximately 5906 h by May 2024. The enhanced service appointment scheduling, combined with timely vehicle maintenance, also contributed to reducing potential accident risks. Moreover, the transition from a rule-based maintenance prediction system to a machine learning approach improved efficiency and accuracy. As a result of this transition, individual customer service visit rates increased by 30%, while corporate customer visits rose by 37%. This study contributes to ongoing research on AI-driven workforce planning and service optimization, particularly within the scope of the AI4LABOUR project.

Although aggregate electricity consumption provides valuable information for market analysis, demand composition, including industrial, residential, illumination, and other uses, and special days, such as national or religious holidays and annual industrial shutdowns, differ for each country. This paper analyzes the hourly electricity consumption of European countries in the European Transmission System Operation for Electricity (ENTSO-E) grid from 2006 to 2018. We propose an outlier detection method to identify special days and a modulated Fourier Series Expansion model to determine the breakdown of industrial versus household consumption and heating versus cooling consumption. The proposed outlier detection method uses the time series for each hour and checks whether a day has more than a threshold number of hours with exceptional electricity consumption levels. The proposed demand prediction model has a 3% average error when electricity usage for heating is not dominant. It also allows country classification based on consumption patterns to efficiently manage regional or country-based electricity markets.

Forecasting electricity consumption is crucial for the operation planning of distribution companies and suppliers and for the success of deregulated electricity markets as a whole. Distribution companies often need consumption forecasting for meters to better plan operations and demand fulfillment. Although it is easier to forecast the aggregated demand for a region, meter based demand forecasting brings challenging issues such as non-uniform usage and uncertain customer consumption patterns. The stochastic nature of the demand for electricity, along with parameters such as temperature, humidity, and work habits, eventually causes deviations from the expected demand. In this paper, real meter data from a regional distribution company is used to cluster the customer using their non-uniform usage and automated ranking mechanism is proposed to select the best method to forecast the consumption. The proposed end-to-end methodology includes data processing, missing value detection and filling, abnormal value detection, and mass reading for meters and is applied to regional data for the period 2017-2018 and provides a powerful tool to forecasts the demand in hourly and daily horizons using only the past demand data. Besides proposing effective methodologies for data preprocessing, 10 different regression methods, 7 regressors, 5 machine learning methods that include LSTM and Ar-net models are used to forecast the meter based consumption. The hourly forecasting errors in the demand, in the Mean Absolute Percentage Error (MAPE) norm, are less than 4% for most customer groups. The meter based forecast is then aggregated to reach a final demand which is then used for operation and demand planning. The proposed framework can be considered reliable and practical in the circumstances needed to make demand and operation decisions.

Loyalty programs provide income to the user as a result of their expenditures. It helps businesses if the customer ensures continuity. A loyalty program is based on the bilateral relationship between the customer and the business. It is important to be sure of the reliability of this bilateral relationship and to be able to follow it. Today, many companies are trying to incorporate Blockchain technology into their systems because they pay attention to reliability and transparency. In this study, a loyalty ecosystem based on Blockchain technology, which will include member businesses, change the shopping and reward experience, and encourage employees is explained. We propose an application named Decentralized Loyalty Token (DLOT) to be used by entities where the community is together and the spending potential is high such as restaurants, cafes, and e-commerce platforms that want to be included in this structure. Users will earn rewards while spending DLOT Tokens and can store and accumulate the rewards indefinitely or use them for any payment. In addition, users will be able to convert the loyalty Tokens into a digital value in other businesses included in Wallet. The details of the proposed Blockchain-based loyalty system are explained along with benefits to customers and entities.

Due to expensive infrastructure and the difficulties in storage, supply conditions of natural gas are different from those of other traditional energy sources like petroleum or coal. To overcome these challenges, supplier countries require take-or-pay agreements for requested natural gas quantities. These contracts have many pre-clauses; if they are not met due to low/high consumption or other external factors, buyers must completely fulfill them. A similar contract is then imposed on distributors and wholesale consumers. It is thus important for all parties to forecast their daily, monthly, and annual natural gas demand to minimize their risk. In this paper, a model consisting of a modulated expansion in Fourier series, supplemented by deviations from comfortable temperatures as a regressor is proposed for the forecast of monthly and weekly consumption over a one-year horizon. This model is supplemented by a day-ahead feedback mechanism for the forecast of daily consumption. The method is applied to the study of natural gas consumption for major residential areas in Turkey, on a yearly, monthly, weekly, and daily basis. It is shown that residential heating dominates winter consumption and masks all other variations. On the other hand, weekend and holiday effects are visible in summer consumption and provide an estimate for residential and industrial use. The advantage of the proposed method is the capability of long term projections and to outperform time series methods.

Since coal resources are located around the world and often far away from where the coal is consumed, transportation is important. The industries that use coal such as power plants, industrial plants, coke plants, and commercial institutions usually prefer different transportation methods. The demand in these industries and the transportation methods they use differ over time. This chapter analyzes the international coal transportation and demand. An analysis for the US coal market and the transportation to industries along with the methods that are used between 2001-2015 are presented. A trend analysis was performed to show the long-term demand for each transportation method in each industry. Such analysis is also useful as it allows observing the coal demand from each industry. Analysis results reveal the change in coal amounts that are transported to each industry using the railroad, truck, and other methods.