Turkish Day-ahead Market Research Articles

A New Artificial Intelligence-Based System for Optimal Electricity Arbitrage of a Second-Life Battery Station in Day-Ahead Markets

Electric vehicles (EVs) are widely regarded as a crucial tool for carbon reduction due to the gradual increase in their numbers. However, these vehicles are equipped with batteries that have a limited lifespan. It is commonly stated that when the battery capacity falls below 70%, it needs to be replaced, and these discarded batteries are typically sent for recycling. Nevertheless, there is an opportunity to repurpose these worn-out batteries for a second life in electric power systems. This study focuses on the arbitrage situation of a second-life battery (SLB) facility in day-ahead electricity markets. This approach not only contributes to balancing supply and demand in the electric power system but also allows the battery facility to achieve significant gains. We propose an artificial intelligence system that integrates optimized deep learning algorithms for market price predictions with a mixed-integer linear programming (MILP) model for market participation and arbitrage decisions. Our system predicts prices for the next 24 h using Neural Hierarchical Interpolation for Time Series (N-HiTS) and decides when to enter the market using the MILP model and incorporating the predicted data and the statuses of the batteries. We compare the accuracy of our trained deep learning model with other deep learning models such as recurrent neural networks (RNNs), Long Short-Term Memory (LSTM), and Neural Basis Expansion Analysis for Interpretable Time-Series Forecasting (N-BEATS). We test the efficiency of the proposed system using real-world Turkish day-ahead market data. According to the results obtained, this study concludes that substantial gains can be achieved with the predicted prices and the optimal operating model. A facility with a total battery energy capacity of 5.133 MWh can generate a profit of USD 539 in one day, showcasing the potential of our study. Our new system’s approach provides proof of concept of new research opportunities for the participation of SLB facilities in day-ahead markets.

Merit-order of dispatchable and variable renewable energy sources in Turkey's day-ahead electricity market

This study employs linear and non-linear quantile regression models to assess the merit-order effect (MOE) of integrating renewable energy sources (RESs) into the Turkish day-ahead electricity market. The analysis spans nine different quantiles from January 2019 to December 2022. Our results show that both dispatchable and variable renewable energy sources (VREs) are essential for reducing market clearing prices (MCPs) in the Turkish day-ahead market. However, they have different impacts on quantiles of MCPs and price variability. VREs enhances the price variability across all hours in linear and non-linear models, while dispatchable renewable energy reduces price variability except at night.

Generation failures, strategic withholding, and capacity payments in the Turkish electricity market

Since the deregulation of significant parts of electricity markets in many countries worldwide, a generally pronounced matter is that firms strategically lower their generating capacity to raise electricity prices. This paper investigates whether strategic capacity withholding exists in the form of generation failures in the Turkish day-ahead market and whether the capacity remuneration mechanism contributes to the failure durations. The empirical results show strong support for strategic capacity withholding in the Turkish market, and the capacity mechanism adds to the duration of these failures. To the best of our knowledge, this is the first study to investigate capacity withholding considering centrally determined capacity prices and to focus on failure durations and the potential amount of power generation losses they cause. Our analysis conveys core messages for policymakers. A random verification mechanism may be implemented to verify that the failures are purely technical and apply penalties for nonperformance. Second, the Turkish capacity mechanism needs to be restructured to make it more compatible with performance incentives. Our analysis, while focused on the Turkish market, provides insights into the prevalent challenges and potential solutions tied to strategic capacity withholding in deregulated electricity markets globally, notably those employing capacity remuneration mechanisms.

A dynamic multi-level iterative algorithm for clearing European electricity day-ahead markets: An application to the Turkish market

Designing and clearing day-ahead electricity market auctions have recently received significant attention from academia and practice alike. Given the size and the complexity of day-ahead market auctions, clearing them within the time limits imposed by the market is a major practical concern. In this paper, we model all the practical details of the Turkish day-ahead electricity market and provide a new multi-level iterative heuristic to clear the market. We compare our results with a commercial solver using data provided by Energy Exchange Istanbul. Our heuristic achieves an average optimality gap less than 0.09%, with an average solution time of just 14 s; whereas the commercial solver takes, on average, 18 min (and in some cases up to three hours) to find the optimal solution. We also demonstrate that using our heuristic solution to warm-start the commercial solver further reduces the solution time by 25%, on average. Overall, our heuristic proves to be very efficient in clearing the Turkish day-ahead market. We also test the performance of our algorithm as the problem size grows.

How do variable renewable energy technologies affect firm-level day-ahead output decisions: Evidence from the Turkish wholesale electricity market

This paper presents firm-level estimates of how an increase in variable renewable energy (VRE) generation affects individual firms’ day-ahead available capacity and generation plans in a developing country, Turkey. In addition to having a fast growing energy demand, Turkey represents an understudied market case where the market leader, unlike the rest of the generators, is a public enterprise that potentially prioritizes political motives over economic efficiency. We first cluster firms in the Turkish day-ahead market based on their generation profiles using unsupervised machine learning and hourly data from years 2017 to 2019. Then, we estimate the short run marginal effects of the projected VRE generation on firms’ day-ahead available capacity and generation plans via panel data methods. Our results support the existing concerns that the public enterprise, especially during the times of financial turmoil, acts with the motivation to stabilize market prices. Additionally, we find that there is a substantial degree of heterogeneity in firms’ responses to VREs and individual responses significantly differ from the aggregate market response.

Portfolio management and performance improvement with Sharpe and Treynor ratios in electricity markets

After 1980s, liberalization in energy industry accelerated. At that times, private sector started to show more tendency to electricity thanks to regulations and policies made by governments so electricity markets emerged and spread very rapidly, which created market risk that needs to be managed carefully along. Decision makers in electricity generation industry had to be faced this market risks besides other operational risks. They had to review policies regarding to risk management and they noticed that determining the right bidding strategy for electricity market and bilateral contract market was crucial. In this paper, Mean–variance, Semi-variance, and Down-side risk methods, which are common in portfolio optimization of financial literature are used to manage risk and to optimize electricity market bidding strategies and decision policy for an electricity generation company. Apart from the other limited studies, performances of optimal portfolio solutions are measured and further more improved with the help of Sharpe and Treynor ratios for electricity market. It is seen that direct use of portfolio management tools in electricity markets can cause sub-optimal solutions, so risk aversion constant of utility functions should be adapted. This study shows that optimal bidding strategies for electricity generators can be improved with the help of Sharpe and Treynor ratios. In order to demonstrate the results, two consecutive years of Turkish Day-ahead Market data are used in an empirical case study.

Optimizing Day-Ahead Electricity Market Prices: Increasing the Total Surplus for Energy Exchange Istanbul

Problem definition: We design a combinatorial auction to clear the Turkish day-ahead electricity market, and we develop effective tabu search and genetic algorithms to solve the problem of matching bidders and maximizing social welfare within a reasonable amount of time for practical purposes. Academic/practical relevance: A double-sided blind combinatorial auction is used to determine electricity prices for day-ahead markets in Europe. Considering the integer requirements associated with market participants’ bids and the nonlinear social welfare objective, a complicated problem arises. In Turkey, the total number of bids reaches 15,000, and this large problem needs to be solved within minutes every day. Given the practical time limit, solving this problem with standard optimization packages is not guaranteed, and therefore, heuristic algorithms are needed to quickly obtain a high-quality solution. Methodology: We use nonlinear mixed-integer programming and tabu search and genetic algorithms. We analyze the performance of our algorithms by comparing them with solutions commercially available to the market operator. Results: We provide structural results to reduce the problem size and then develop customized heuristics by exploiting the problem structure in the day-ahead market. Our algorithms are guaranteed to generate a feasible solution, and Energy Exchange Istanbul has been using them since June 2016, increasing its surplus by 448,418 Turkish liras (US$128,119) per day and 163,672,570 Turkish liras (US$46,763,591) per year, on average. We also establish that genetic algorithms work better than tabu search for the Turkish day-ahead market. Managerial implications: We deliver a practical tool using innovative optimization techniques to clear the Turkish day-ahead electricity market. We also modify our model to handle similar European day-ahead markets and show that performances of our heuristics are robust under different auction designs.

Electricity Price Forecasting Using Recurrent Neural Networks

Accurate electricity price forecasting has become a substantial requirement since the liberalization of the electricity markets. Due to the challenging nature of electricity prices, which includes high volatility, sharp price spikes and seasonality, various types of electricity price forecasting models still compete and cannot outperform each other consistently. Neural Networks have been successfully used in machine learning problems and Recurrent Neural Networks (RNNs) have been proposed to address time-dependent learning problems. In particular, Long Short Term Memory (LSTM) and Gated Recurrent Units (GRU) are tailor-made for time series price estimation. In this paper, we propose to use multi-layer Gated Recurrent Units as a new technique for electricity price forecasting. We have trained a variety of algorithms with three-year rolling window and compared the results with the RNNs. In our experiments, three-layered GRUs outperformed all other neural network structures and state-of-the-art statistical techniques in a statistically significant manner in the Turkish day-ahead market.

On the determination of European day ahead electricity prices: The Turkish case

Day ahead electricity prices in European markets are determined by double-blind auctions. That is, both buyers and sellers may place anonymous orders with different prices and quantities. The market operator has to solve an optimization problem within an hour to clear the auction and determine the prices for the Day Ahead Market (DAM) which are used as a reference point for the other electricity contracts. All electricity traded at the same time period is traded at the same price, called market clearing price. The market operator has to end the algorithm with a feasible solution if the algorithm could not find the optimal solution within the time limit. In this paper, we develop an optimization model to solve the problem with day ahead electricity prices including all the practical considerations in the Turkish DAM. We present a mixed integer formulation and provide methods based on aggregation techniques and variable elimination to solve the problem within the limits of the practical requirements. Using real market data, we show that, aggregation reduces the problem size approximately 60 percent whereas variable elimination provides another 30 percent reduction. We also propose an IP-based large neighborhood search to obtain an initial solution. Empirical evidences coming from the Turkish DAM data indicate the heuristic has a substantial solution quality and the overall suggestions deliver remarkable solution time improvements. This is the first paper in terms of formulating DAM problem in Turkey, developing new approaches to solve it within the time limits of the market, and using real data.