Short-term load forecasting method based on secondary decomposition and improved hierarchical clustering

Results in Engineering, Journal Year: 2024, Volume and Issue: 22, P. 101993 - 101993

Published: March 15, 2024

In the context of large-scale grid connection new energy, short-term load forecasting is a vital and challenging task for power system to balance supply demand. To effectively improve accuracy, method proposed aiming mine characteristics data study application artificial intelligence algorithms. this paper, seasonal trend decomposition using loess (STL) firstly applied decompose into trend, residual components component with highest complexity further decomposed by complete ensemble empirical mode adaptive noise (CEEMDAN) approach. Secondly, in order reduce number components, improved hierarchical clustering technique cluster all intrinsic functions (IMFs) obtained CEEMDAN high-frequency low-frequency components. Then, different network models are trained get prediction results total value achieved stacking them. Finally, national demand dataset Great Britain 2021–2022 used conduct ablation comparative experiments. The mean absolute percentage error (MAPE) root square (RMSE) 2.064% 724.01 MW, respectively, which verified effectiveness advancement method.

Language: Английский

---

A Comprehensive Survey on Load Forecasting Hybrid Models: Navigating the Futuristic Demand Response Patterns through Experts and Intelligent Systems

Results in Engineering, Journal Year: 2024, Volume and Issue: 23, P. 102773 - 102773

Published: Aug. 24, 2024

Language: Английский

---

Optimal Placement and Sizing of D-STATCOMs in Electrical Distribution Networks Using a Stochastic Mixed-Integer Convex Model

Electronics, Journal Year: 2023, Volume and Issue: 12(7), P. 1565 - 1565

Published: March 26, 2023

This paper addresses the problem regarding optimal placement and sizing of distribution static synchronous compensators (D-STATCOMs) in electrical networks via a stochastic mixed-integer convex (SMIC) model complex domain. The proposed employs convexification technique based on relaxation hyperbolic constraints, transforming nonlinear programming into one. nature renewable energy demand is taken account multiple scenarios with three different levels generation demand. SMIC adds power transfer losses D-STATOMs order to size them adequately. Two objectives are contemplated aim minimizing annual installation operating costs, which makes it multi-objective. Three simulation cases demonstrate effectiveness compared solvers General Algebraic Modeling System. results show that achieves global optimum, reducing costs by 29.25, 60.89, 52.54% for modified IEEE 33-, 69-, 85-bus test systems, respectively.

Language: Английский

---

Techno-economic optimization of photovoltaic (PV)-inverter power sizing ratio for grid-connected PV systems

Results in Engineering, Journal Year: 2024, Volume and Issue: 23, P. 102580 - 102580

Published: July 17, 2024

- The accurate sizing of the inverter, specifically power ratio (PSR) plays a vital role in maximizing energy production and economic benefits. Existing studies often overlook complex interplay between capture minimizing inverter-related costs when selecting optimal PSR. This research presents techno-economic approach to optimizing PSR for grid-connected photovoltaic (PV) systems. A simulation model is developed, incorporating real weather data inverter efficiency curves. calibrated using Pattern Search Algorithm (PSA) ensure an representation real-world behavior by achieving minimum relative difference 13.78 % (Norm-RMS) AC output. analysis explores trade-off PSR, annual yield, clipping. An 1.19 identified, balancing (up 2000W capacity) efficiency. promotes cost-effective selection wider PV adoption.

Language: Английский

---

Review of bio-inspired optimization applications in renewable-powered smart grids: Emerging population-based metaheuristics

Energy Reports, Journal Year: 2022, Volume and Issue: 8, P. 11769 - 11798

Published: Sept. 22, 2022

The management of renewable-powered smart grids deals with nonlinear optimization problems featuring a variety linear or constraints, discrete continuous variables, involving high dimensionality the solution space, and strict time requirements to identify optimal near-optimal solution. One promising approach for addressing such is apply bio-inspired population-based algorithms, many metaheuristics emerging lately. In this paper, we have identified highest impact published recently reviewed their applications in energy using Preferred Reporting Items Systematic reviews Meta-Analyses (PRISMA) methodology Web Science Core Collection as reference database. Four main grid application domains been analyzed: (i) prediction models' reduce uncertainty (ii) resources coordination handle stochastic nature renewables, (iii) demand response controllable loads flexibility while considering consumers' needs constraints (iv) efficiency costs. results showed advantages decentralized low computational resource overhead. At same time, several issues need be addressed increase adoption scenarios: lack standard testing methodologies benchmarks, efficient exploration exploitation search guidelines clear links type problems, etc.

Language: Английский

---

Analyzing Optimal Battery Sizing in Microgrids Based on the Feature Selection and Machine Learning Approaches

Published: May 27, 2022

Microgrids are becoming popular nowadays because they provide clean, efficient, and low-cost energy. To use the stored energy in times of emergency or peak loads, microgrids require bulk storage capacity. Since future renewable energy, technology employed should be optimized to generate electricity. Batteries play a variety essential roles daily life used at hours during time emergency. There different types batteries i.e., lion batteries, lead-acid etc. Optimal battery sizing is challenging problem, that limits modern technologies such as electric vehicles, It important know features life, throughput, autonomy get optimal for microgrids. Mixed-integer linear programming (MILP) an established technique integration optimization sources parameters sizing. A new MILP based dataset introduced this work. Support vector machine (SVM) learning application estimate optimum size. The impact feature selection algorithms on proposed learning-based model evaluated. performance six best-performing analyzed. experimental results show improve methodology. Ranker search shows best with Spearman’s rank-ordered correlation constant 0.9756, 0.9452, Kendall 0.8488 root mean squared error 0.0525.

Language: Английский

---

Scenario prediction and decoupling analysis of carbon emission in Jiangsu Province, China

Technological Forecasting and Social Change, Journal Year: 2022, Volume and Issue: 185, P. 122074 - 122074

Published: Oct. 11, 2022

Language: Английский

---

Development of technical economic analysis for optimal sizing of a hybrid power system: A case study of an industrial site in Tlemcen Algeria

Results in Engineering, Journal Year: 2022, Volume and Issue: 16, P. 100675 - 100675

Published: Oct. 1, 2022

The current study aimed to develop an optimal sizing simulation model for off-grid photovoltaic-wind hybrid power system of industrial site in Algeria. loss supply probability algorithm was used our system. technical and economic evaluation the case showed that storage occupied most critical part total investment cost analysis indicated a unique configuration each size batteries bank. For one day's autonomy, best corresponded 61 PV panels 9 wind turbines. Based on levelized energy analysis, represented this combination is 52% cost. turbines accounted 42% only 3%. This resulted very competitive with European countries. However, public grid region still six times lower due government subsidies. findings are encouraging can help decision-makers adopt alternative more sustainable solutions policy. These results will aid determining future research directions Algeria's renewable systems.

Language: Английский

---

A hybrid chaotic-based discrete wavelet transform and Aquila optimisation tuned-artificial neural network approach for wind speed prediction

Results in Engineering, Journal Year: 2022, Volume and Issue: 14, P. 100399 - 100399

Published: March 25, 2022

Wind speed prediction has received reasonable attention recently because of its clean and promising source renewable energy. Recent studies have shown that developing efficient model to predict wind is a challenging task nonlinear stochastic characteristics. This paper aims propose new hybrid speed. For this purpose, Discrete Wavelet Transform (DWT), Phase Space Reconstruction (PSR) chaos theory, Aquila Optimization Algorithm (AOA) Backpropagation Neural Network (BPNN) are hybridised novel DWT-PSR-AOA-BPNN proposed. To ascertain the proposed performance, different variants (DWT-PSR-GA-BPNN, DWT-PSR-PSO-BPNN, PSR-PSO-BPNN PSR-AOA-BPNN) were developed for comparison. The comparison was done using statistical evaluators Mean Average Error (MAE), Root Square (RMSE), Absolute Percentage (MAPE), efficiency Loague Green (ELG). results showed performed better therefore considered tool when compared with DWT-PSR-GA-BPNN, PSR-AOA-BPNN models. That is, had lowest MAE, RMSE MAPE values testing (MAE = 1.1490, 1.4190 0.2743) validation 0.8122, 0.9771 0.1953). also achieved highest ELG 0.9904 (testing) 0.99738 (validation) respectively. It concluded considering results, indication corroborates fact can be utilized grid operations.

Language: Английский

---

Assessment and determination of 2030 onshore wind and solar PV energy targets of Türkiye considering several investment and cost scenarios

Results in Engineering, Journal Year: 2022, Volume and Issue: 16, P. 100733 - 100733

Published: Oct. 27, 2022

The importance of renewable energy (RE) shift increases as the instabilities around world enhanced by pandemic raise issues about security while demand countries continue to increase. This is especially case for Türkiye, which a member OECD and among developing countries. In next decade, onshore wind, solar photovoltaics (PV) will be focus Türkiye's RE sector due rapid decrease in their costs. Hence, reasonable estimation investments cost projections wind PV crucial plan, decide set effective policies. this study, three different investment scenarios are generated Türkiye. addition, global local conducted PV, again scenarios. These then utilized estimate annual installed capacity changes Then, amounts Türkiye projected until 2030 five novel scenarios: Economic, Average, Ambitious, Best-Case, Worst-Case. According results, achievable most suitable targets determined 25,000 MW 60,000 respectively. results assist policymakers elucidating future methodology may useful determination other

Language: Английский

---