Turkey's energy landscape is characterised by a dynamic fusion of nonrenewable and renewable sources, which are crucial for meeting the nation's electricity demands. Sources, such as natural gas and coal derivatives, ensure grid stability, while renewables, such as hydroelectric, solar, and wind power, underscore Turkey's commitment to sustainability. Although there are currently no grid-connected wave energy plants, initiatives such as the OREN Ordu Energy project demonstrate the country's growing interest in wave energy. Turkey aims to integrate wave energy into its renewable energy mix, with the help of supportive regulations and incentives. This will bolster resilience and reduce environmental impact. However, successful integration requires overcoming regulatory hurdles, technological advancements, and environmental concerns. This study discusses the potential of wave energy and the importance of increasing the rate of renewable energy, with a PESTLE analysis.
Sustained growth in global electricity demand has significantly accelerated the adoption of renewable energy sources (RES). Within this sector, solar energy systems (SES) have emerged as a leading solution due to their abundance and cost-effectiveness. In particular, photovoltaic (PV) installations have become the dominant technology owing to their exceptional deployment flexibility. The electrical output of PV systems is critically governed by solar irradiance and ambient temperature, whose variations directly affect generation performance. Accurate PV power forecasting is therefore essential for maintaining supply-demand balance in modern grids, and machine learning (ML) techniques have become the prevailing approach for this purpose. This paper proposes a novel residual bidirectional long short-term memory (LSTM) architecture with Swish activation (RSBiLSTM) for PV power generation forecasting via historical generation and meteorological data. The model extends the standard bidirectional LSTM (BiLSTM) framework with residual connections across stacked BiLSTM blocks and Swish activation in the dense prediction head, with hyperparameters tuned via Bayesian optimisation (BHO). RSBiLSTM is benchmarked against a standard LSTM, BiLSTM, and hybrid CNN-LSTM using mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE), and the coefficient of determination (\(R^{2}\)), which are evaluated under both a temporal hold-out split and a ten-fold expanding-window walk-forward cross-validation scheme. Statistical significance was established via the Wilcoxon signed-rank test and the paired t-test. The results confirm that RSBiLSTM delivers accurate and reliable solar power forecasting with statistically significant improvements over the LSTM and CNN-LSTM baselines and consistently large effect sizes against all the baselines.
30 April 2022 in Düzce Üniversitesi Bilim ve Teknoloji Dergisi
Bu çalışmada, dağıtık üretim (DÜ) sistemlerinin optimum şebeke entegrasyonu probleminin çözümü için zıtlık tabanlı parçacık sürü optimizasyonu (OBPSO) kullanımı önerilmektedir. Önerilen OBPSO yöntemi, DÜ’nün optimum yer ve büyüklük değerlerini bulurken çok amaçlı optimizasyon yaklaşımı kullanmaktadır. Ayrıca yük değişimlerine karşı duyarlılık analizi yöntemi ortaya konmuş ve yeni bir amaç fonksiyonu olarak da kullanılmıştır. Amaç fonksiyonları, aktif güç kaybı, gerilim değişimi ve duyarlılık analizi minimizasyonundan oluşmaktadır. DÜ kaynağı olarak fotovoltaik tabanlı güneş enerji sistemleri (DGES) esas alınmıştır. Birim güç faktörü ile işletilen 3 adet DGES eklendiği durumlar değerlendirilmiş ve amaç fonksiyonlarının değişimleri analiz edilmiştir. Önerilen metodun etkinliği standart test sistemlerinden IEEE 33 baralı dağıtım sistemi kullanılarak araştırılmıştır. Yük akışı analizi içi MATPOWER paket programı kullanılmıştır. Elde edilen sonuçlar literatürde bulunan diğer çalışmalarla karşılaştırılmıştır. Neticede, OBPSO yönteminin iyi sonuç verdiği ve karşılaştırılan diğer optimizasyon tekniklerine karşı üstünlükleri olduğu gözlenmiştir. Ayrıca, DGES’nin optimum değerler dikkate alınarak yapılan entegrasyonlarda amaç fonksiyonlarında belirgin iyileşmeye sağladığı gözlenmiştir.
2 October 2024 in International Journal of Computational and Experimental Science and Engineering
It is frequently preferred to perform development processes to improve the results of optimization algorithms and increase their performance. Swarm-based metaheuristic optimization algorithms are frequently preferred due to their ease of application and fast results. In this study, the alpha wolf class, also called the wolf leader class in grey wolf optimization (GWO), was improved with chaotic Chebyshev map and named as chGWO. 7 of the standard test functions were used to evaluate the performance of chGWO and the findings were compared with the literature. Based on the comparisons of the algorithms in the literature, the chGWO algorithm gave good results in single-mode benchmark functions. Then, the improved algorithm was applied to the problem of optimum placement of electric vehicle charging stations (EVCSs) in the grid using the IEEE 33-bus test system. It gave better results than the classical GWO algorithm. It was seen that the improved chGWO was advanced and could be used in solving various engineering problems.