Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.Nghiên cứu, đánh giá ảnh hưởng của nguồn điện gió công suất lớn đến hệ thống điện.
THE UNIVERSITY OF DANANG UNIVERSITY OF SCIENCE AND TECHNOLOGY ⎯⎯⎯⎯⎯⎯⎯⎯⎯ VO VAN PHUONG RESEARCH, EVALUATE THE INFLUENCE OF LARGE-SCALE WIND POWER SOURCES ON THE POWER SYSTEM Major: Electrical Engineering Code: 52 02 01 PHD DISSERTATION IN BRIEF Da Nang, 2023 This dissertation has been finished at: University of Science and Technology, The University of Danang Supervisor 1: Assoc Prof PhD Dinh Thanh Viet Supervisor 2: Prof Sc.D Tran Quoc Tuan Examiner 1: ……………………………… Examiner 2: ……………………………… Examiner 3: ……………………………… The PhD dissertation will be defended at the Dissertation Assessment Committee at University of Science and Technology, The University of Danang at date month 2023 The dissertation is available at: - The Information Resources Center, University of Danang - The National Library INTRODUCTION The reason for choosing the dissertation One of the renewable energy sources with huge potential today is wind energy However, the process of expanding and developing large-scale wind power sources will create a great change in the power structure of countries, causing many impacts on the power system and electricity market Therefore, the dissertation focuses on researching the effects of large-scale wind power sources on the power system and electricity market in order to solve the abovementioned problems Purpose of research - Research and build a forecasting model of wind power generation capacity using artificial intelligence networks combined with optimal algorithms Research and build models to serve the problem of planning and integrating wind power sources into the power system Research methodology - Theoretical research combined with experiment, programming, simulation on DIgSILENT PowerFactory, Matlab, Python software - Test the application in accordance with hypothetical power grids Subjects and scope of research Research subjects: This dissertation researches on wind power sources and some related forms of renewable energy; researches on software and programming languages Matlab, Python for simulation and computation Scope of research: This dissertation researches on issues related to the forecasting of wind power generation capacity, planning issues and optimal calculation of wind power sources Scientific and practical significance of the dissertation - Research content published in international scientific journals will be a reference source for authors wishing to research in a similar topic - The wind power generation capacity forecast model proposed by the dissertation can be used for wind power plants, dispatch centers to serve the dispatch, operation and production planning of wind power plants - The planning calculation model allows consultants and authorities to have a calculation tool to serve the problem of power system planning with an increasing penetration of renewable energy sources - The research results will also make a positive contribution to the promotion of the exploitation, application and expansion of renewable energy sources, especially wind energy New contributions of the dissertation - The dissertation has researched, analyzed and calculated and evaluated the effects of large-scale wind power sources on the power system, including the effect on power balance, short circuit, power system stability, power quality according to the model of wind speed changes dramatically and changes over time in 24 hours - The dissertation has researched to build a computational model to develop and integrate renewable energy power sources into the power system, including taking into account energy storage systems With the objective function of calculating the optimization of investment and operating costs while ensuring compliance with scenarios of CO2 emission reduction, the dissertation developed a software program and applied the calculation to the power grid The software program proposed by the dissertation has calculated the power structure suitable for CO2 emission reductions in different scenarios - In this dissertation, it has also researched and analyzed the impact of large-scale wind power sources on the electricity market, and calculated the impact of the forecast error of wind power generation capacity on the revenue of wind power plants participating in the competitive power generation market - The dissertation has researched, proposed, modeled and successfully built wind power generation capacity forecasting software with relatively good accuracy On the basis of the open-source programming language Python, the dissertation combined the application of artificial intelligence networks with swarm algorithms and genetic algorithms to build wind power generation capacity forecasting programs according to two models PSO-PSO-ANN and GA-PSO-ANN The above models have been applied to forecast the generation capacity for Tuy Phong wind power plant in Binh Thuan province, Vietnam The results show that the above forecasting models can be used for wind power plants, dispatch centers to serve the dispatch, operation and production planning of wind power plants - In addition, the dissertation also researched and built a shortterm wind power forecasting model using Python programming language, incorporating the TensorFlow library to train artificial neural networks Layout of the dissertation The dissertation layout includes introduction, content chapters, conclusion, list of published works, list of references and appendices Chapter Overview of wind power sources and studies on the impact of large-scale wind power on the power system and electricity market Chapter Study the impact of large-scale wind power sources on the power system and electricity market Chapter Study on optimizing the integration of renewable energy sources into the power system considering scenarios for reducing CO2 emissions Chapter Research and build a forecasting model of wind power generation capacity using artificial intelligence networks combined with optimal algorithms CHƯƠNG CHAPTER OVERVIEW OF WIND POWER SOURCES AND STUDIES ON THE IMPACT OF LARGE-SCALE WIND POWER ON THE POWER SYSTEM AND ELECTRICITY MARKET 1.1 Overview of wind power sources Wind power is a clean energy source and has huge potential 1.2 Research situation on the impact of large-scale wind power sources on the power system and electricity market 1.2.1 Studies on the effects of wind power on power systems and electricity markets In this dissertation, PhD students will carry out research on calculating, simulating and analyzing the effects of large-scale wind power sources on the power system, the impact of wind power sources on the electricity market 1.2.2 Studies on wind power development planning In this dissertation, PhD students will develop an optimization computational model for integrating renewable energy sources into the power system taking into account scenarios for reducing CO2 emissions, and integrate the energy storage system in the power system 1.2.3 Studies on forecasting wind power generation capacity 1.2.3.1 Classification and purpose of types of wind power forecasting 1.2.3.2 Studies on forecasting wind power generation capacity In general, there have been many research authors on the problem of forecasting wind power generation capacity, each study has its own advantages and strengths of each method as mentioned above However, errors in wind power generation capacity forecasts can be further minimized In this dissertation, PhD students will propose a wind power generation capacity forecasting model using a combination of optimal algorithms and artificial intelligence This proposed model can improve forecast error compared to some other models 1.3 Conclusion of chapter Based on the above-mentioned contents on the overview of wind power sources and studies on the impact of large-scale wind power sources on the power system and electricity market, it can be seen that wind energy sources have been strongly exploited In this dissertation, PhD students carry out research on the effects of large-scale wind power sources on power systems and electricity markets, and perform calculations, simulations and analyses of the effects of wind power sources on IEEE power systems In addition, in order to serve the problem of planning for the development of renewable energy sources, including wind energy sources, the dissertation builds an optimization calculation model for integrating renewable energy sources into the power system taking into account scenarios to reduce CO2 emissions In addition, the PhD student proposed a wind power generation capacity forecasting model using a combination of optimal algorithms and artificial intelligence CHƯƠNG CHAPTER STUDY THE IMPACT OF LARGE-SCALE WIND POWER SOURCES ON THE POWER SYSTEM AND ELECTRICITY MARKET 2.1 Introduction The sudden change in generation capacity of wind power plants increases uncertain factors in the operation of the power system, so the operating costs of the whole system increase 2.2 Turbine, wind generator models 2.2.1 Classification of wind turbines According to the structure, there are 02 types of wind turbines: Vertical axis and horizontal axis 2.2.2 Wind turbine structure 2.2.3 Wind turbines use grid-connected permanent magnet synchronous generators 2.2.4 Wind energy and wind power Wind turbines convert the kinetic energy of the wind into mechanical energy to rotate the wind turbine (2.1) 2.2.5 Generator-side and grid-side converters 2.2.6 Wind turbine pitch controller 2.3 Impact of large-scale wind power on the power system 2.3.1 Power balancing and stabilizing the power system Unpredictable variation in generation capacity of wind power plants may lead to a power imbalance in the system and may affect the stability of the power system Any power imbalance affects the system frequency and can cause unsynchronization and instability in some cases 2.3.2 Power quality Wind power plants can assist in regulating and maintaining voltage in the system in faulty situations 2.3.3 Effects on power transmission lines In case the power system does not have a good link between regions or countries, there may be situations of system congestion and the power generation of wind power plants must be limited 2.3.4 Influence on optimal operation of power plants Depending on the level of penetration and characteristics of the system, wind power plants also affect the efficiency of other power plants in the power system (and vice versa) 2.3.5 Security of power supply and environment Wind power plants play a role in maintaining the stability of the system and contribute to meeting the demand for power supply to the load At the same time, the development of wind power sources plays an active role in contributing to reducing greenhouse gas emissions, protecting the environment and ensuring the security of electricity supply 2.4 Research, calculate and analyze the impact of wind power sources on the power system 2.4.1 Research grid The IEEE grid diagram is built on DIgSILENT software, including 03 power plants, 03 stepup transformers, 09 busbars, 06 transmission lines and 03 loads From this IEEE diagram, in the dissertation add 02 wind power plants The Wind1 wind power plant connects to the Wind1 busbar, through 01 T_Wind1 stepup • In general, electricity prices are expected to be lower during periods of high winds compared to periods of low winds • If the existing capacity to release capacity cannot meet the demand for electricity transmission (from one region to another), then the power supply area will be separated from the rest of the electricity market and form its own pricing area 2.5.2 Increased costs for ancillary services When the penetration of wind power plants into the power system increases, ensuring system security requires increasing the level of capacity redundancy due to the instability of the generation capacity of wind power plants, leading to an increase in operating costs of the whole system as well as an increase in costs for ancillary services on the system 2.5.3 Impact on the financing of wind power plant participation in the electricity market The accuracy of wind power capacity forecasts affects the selling and purchasing prices of power plants: • If the amount of power produced is more than the forecasted capacity, then the excess capacity will be resold at a lower price • If the amount of power generated is less than the forecasted capacity, then the amount of missing capacity will have to be purchased at a higher cost 2.6 Study on the impact of wind power generation capacity forecast errors on the revenue of wind power plants participating in the competitive power generation market The results show that in case the wind power plant offers the market price according to the forecast results according to the GA12 PSO-ANN model (with a MAPE error of 4.52%), the loss of revenue in 24 hours (calculated on 01 turbine) is 60,636 VND/kWh Meanwhile, if the bid is based on the forecast results from the Adam-ANN model (with a MAPE error of 7.79% - higher than the GA-PSO-ANN model), the corresponding loss is 113,312 VND/kWh, 1.87 times greater than the GA-PSO-ANN option 2.7 Conclusion of chapter In this chapter, the dissertation presented an overview of the effects of large-scale wind power on the power system The dissertation has calculated, analyzed and simulated the effects of large-scale wind power sources on the IEEE grid model The results of calculations and simulations are shown in detail through specific tables, charts and analysis In this chapter, the dissertation also presented the influence of large-scale wind power on the electricity market, which specifically explains the influence of wind power on market prices, the effect on the cost of ancillary services, and finally the financial impact of wind power plants participating in the competitive electricity market The dissertation presented specific research and calculation results on the impact of wind power generation capacity forecast errors on the revenue of wind power plants participating in the competitive power generation market The research results show that the greater the forecast error in wind power generation capacity, the more wind power plants will lose when participating in the competitive electricity market 13 CHƯƠNG CHAPTER STUDY ON OPTIMIZING THE INTEGRATION OF RENEWABLE ENERGY SOURCES INTO THE POWER SYSTEM CONSIDERING SCENARIOS FOR REDUCING CO2 EMISSIONS 3.1 Introduction In this chapter, the author builds a computational model for planning the development of renewable energy sources into the power system according to CO2 emission reduction scenarios 3.2 Computational model 3.2.1 Objective function The objective of the program is to optimally calculate investment and operating costs for the entire power system while ensuring constrains: [∑ cl Fl + ∑ cn,s Gn,s + ∑(on,s g n,s (𝑡))] g, G, F l n,s n,s,t 3.2.2 Constraints Constraints at nodes on balancing of generating power, load and transmission power: ∑ 𝑔𝑛,𝑠 (𝑡) − 𝑑𝑛 (𝑡) = ∑ 𝐾𝑛,𝑙 𝑓𝑙 (𝑡) ∀ 𝑛, 𝑡 𝑠 𝑙 Constraints on limits on power plants' capacity generation capacity: − (𝑡) + (𝑡) 𝑔𝑛,𝑠 𝐺𝑛,𝑠 ≤ 𝑔𝑛,𝑠 (𝑡) ≤ 𝑔𝑛,𝑠 𝐺𝑛,𝑠 ∀ 𝑛, 𝑡 14 The Gn,s installed capacity limit for power plants using s technology at node n follows the constraint: 𝑚𝑖𝑛 𝑚𝑎𝑥 𝐺𝑛,𝑠 ≤ 𝐺𝑛,𝑠 ≤ 𝐺𝑛,𝑠 The transmission capacity |f l(t)| on line l at times should also not exceed the maximum power transmission capacity of the line to avoid line overload: |𝑓𝑙 (𝑡)| ≤ 𝐹𝑙 ∀ 𝑙 3.2.3 CO2 emissions CO2 emissions caused by the power system should be limited by the CAPCO2 at the following constraint: ∑ 𝑔𝑛,𝑠 (𝑡) 𝑒𝑠 ≤ 𝐶𝐴𝑃𝐶𝑂2 ƞ𝑠 𝑛,𝑠,𝑡 3.2.4 Optimization algorithm for integrating renewable energy sources into the power system considering CO2 emission reduction scenarios Based on the proposed calculation model, the dissertation develops an optimization calculation program to integrate renewable energy sources into the power system taking into account scenarios for reducing CO2 emissions 3.3 Research on optimizing the integration of renewable energy sources into the power system according to CO emission reduction scenarios 3.3.1 Research grid model In the research dissertation, 06 scenarios are as below: • Scenario 1: No reduction in CO2 emissions • Scenario 2: 8% reduction in CO2 emissions • Scenario 3: 15% reduction in CO2 emissions • Scenario 4: 25% reduction in CO2 emissions 15 • Scenario 5: 35% reduction in CO2 emissions • Scenario 6: assessment of the effect on reducing CO2 emissions when BESS systems are involved in the system 3.3.2 Simulation results It can be seen that the lower the reduction in CO2 emissions, the less penetration of renewable energy sources is required At 0% and 8% reductions, wind and solar energy sources are mainly concentrated in the Southern and Central Highlands regions When the required CO2 reduction is higher, the penetration of renewable energy sources is also required higher, with a slight shift in distribution, adding these sources to the Central and Northern regions In scenario 6, when more energy storage systems are allowed, the simulation results show that wind and solar power plants can penetrate more into the system as shown in Figure 3.7 Figure 3.1 Allocation of power generation output of plants when BESS penetrates It can be seen that when the level of reduction in CO2 emissions increases, renewable energy power plants (wind and solar) 16 participate more in the power structure and power generation structure of the whole power system In scenario (BESS system participates in the system), wind power plants participate more in the system than sources solar energy 3.4 Conclusion of chapter This chapter has developed a calculation model for the development of renewable energy sources into the power system in the future, with the objective function of calculating investment and operating cost optimization while ensuring compliance with CO2 emission reduction scenarios It can be seen that once policies on environmental protection and greenhouse gas emission reduction are applied by countries around the world, the development of renewable energy will be strongly promoted, especially wind power instead of solar Thereby, it can be seen that in the future, there is a need for supportive policies to bring developing countries to access the world's contemporary wind power technology to shorten the investment cost of wind power, because a low-emission power system depends on renewable energy, especially wind power sources At the same time, it is necessary to develop other renewable energy sources and support services to meet the optimization and stability in the operation of the power system 17 CHƯƠNG CHAPTER RESEARCH AND BUILD A FORECASTING MODEL OF WIND POWER GENERATION CAPACITY USING ARTIFICIAL INTELLIGENCE NETWORKS COMBINED WITH OPTIMAL ALGORITHMS 4.1 Introduction This chapter proposes a model of using artificial intelligence networks combined with particle swarm optimization algorithms and genetic algorithms to build wind power generation capacity forecasting programs 4.2 Artificial intelligence network and optimal algorithm 4.2.1 Artificial Intelligence Network (ANN) In this study, the author uses an input layer consisting of 03 neurons representing wind speed, wind direction and temperature, 01 hidden layer and an output layer with 01 neuron is the power of wind power generation 4.2.2 Particle swarm optimization algorithm In this chapter, the PSO algorithm is used in collaboration with genetic algorithms and artificial intelligence networks to build a forecasting model of wind power generation capacity 4.2.3 Genetic algorithm (GA) Genetic Algorithm (GA) is a very effective tool for solving optimal problems 4.2.4 PSO-ANN algorithm for training artificial intelligence networks The PSO-ANN algorithm model is shown as Figure 4.4 18 PSO ANN Figure 4.4 PSO-ANN algorithm model 4.3 Wind power generation capacity forecasting model using artificial intelligence networks combined with optimal algorithms 4.3.1 PSO-PSO-ANN wind power generation capacity forecast model The PSO-PSO-ANN algorithm structure consists of main loops: PSO1 loop, PSO2 loop and neural network loop shown as Figure 4.6 PSO1 PSO2 ANN Figure 4.6 PSO-PSO-ANN algorithm model The PSO1 outermost loop uses the PSO algorithm to determine the optimal c12, c22 and w2 parameters for the PSO2 algorithm The PSO2 loop also uses the PSO algorithm that receives the parameters 19 c 12, c22 and w2 from the result from the PSO1 loop to adjust the parameters of the neural network The ANN loop is used to calculate the error in each loop 4.3.2 Forecast model of wind power generation capacity GAPSO-ANN The GA-PSO-ANN algorithm structure consists of main loops: GA loop, PSO loop, ANN loop shown in Figure 4.8 GA PSO2 ANN Figure 4.8 GA-PSO-ANN algorithm model 4.3.3 Data 4.3.3.1 Introduction about Tuy Phong wind power plant 4.3.3.2 Data Data including active power and wind speed, wind direction, and temperature parameters were collected in 30-minute cycles used to train the model taken from Tuy Phong wind power plant, Binh Thuan 4.4 Test results 4.4.1 Methods for evaluating results To evaluate the effectiveness of forecasting models, the following two types of accuracy measurement standards are used: 20 Mean absolute percentage error (MAPE) and mean squared error (MSE) 4.4.2 Test results In both cases, the proposed GA-PSO-ANN and PSO-PSO-ANN algorithms outperformed PSO-ANN and Adam-ANN Since the forecast graph compared to the actual results for the two proposed algorithms is relatively similar, the graph of the GA-PSO-ANN model is displayed as illustrated in Figure 4.18 and 4.19, the wind power forecast results for one day (Figure 4.18) and for a week (Figure 4.19) using the GA-PSO-ANN model are quite close to the actual wind power forecast results stored in the SCADA system Công suất đầu tuabin (MW) Công suất phát nhà máy điện gió thực tế dự báo 01 ngày (mơ hình GA-PSO-ANN) 0,8 0,6 0,4 0,2 101112131415161718192021222324 Giờ Thực tế Dự báo Figure 4.18 Actual and forecast generation capacity in 24 hours In addition, the dissertation also researched and built a shortterm wind power forecasting model using Python programming language, incorporating the TensorFlow library to train artificial neural networks 21 4.5 Conclusion of chapter This chapter has proposed a model and successfully built wind power generation capacity forecasting software with a relatively good level of accuracy compared to other models The results show that the PSO-PSO-ANN and GA-PSO-ANN forecasting models give significantly better forecasting results than the PSO-ANN or Adam-ANN models Table 4.6 shows the MAPE comparison between different wind power forecasting models The proposed models PSO-PSOANN and GA-PSO-ANN show better accuracy than the aforementioned models Table 4.6 Compare the MAPE value of the proposed model compared to other models Model MAPE GA-PSO-AN 4.52% PSO-PSO-ANN 4.54% PSO-ANN 4.90% Adam-ANN 7.79% Persistence 11.94% BP-FFANN 7.35% GA-FFANN 6.79% ANFIS 14.92% WT + ANFIS 12.58% WT + NNPSO 8.19% WT-ACO-FFANN 5.35% VWPF 6.85% 22 CONCLUSION AND RECOMMENDATION Conclusions The dissertation presented an overview of wind power sources and studies on the impact of large-scale wind power sources on the power system and electricity market The increased penetration of wind power into the power supply structure will lead to more impacts on the power system and the electricity market The dissertation has researched, analyzed and presented the effects of large-scale wind power on the power system To clarify this content, the dissertation has calculated, analyzed and simulated the impact of large-scale wind power sources on the power system on the grid model In addition, the dissertation has researched the development of a calculation model for the development of renewable energy power sources into the power system, focusing on wind power sources, solar power sources and energy storage systems The objective is to calculate and optimize investment and operating costs while ensuring compliance with CO2 emission reduction scenarios The software program proposed by the dissertation calculated the power structure suitable for reductions in CO2 emissions in different scenarios From there, it can be seen that once policies on environmental conservation and greenhouse gas emission reduction are applied by countries around the world, it will promote the development of renewable energy power sources strongly, especially wind power The dissertation also presented the effects of large-scale wind power on the electricity market, including the effect on market prices, the effect on the cost of ancillary services, and the financial 23 impact of wind power plants participating in the competitive power market To better illustrate, the project has studied the calculation of the effect of the forecast error of wind power generation capacity on the revenue of wind power plants participating in the competitive power generation market for specific situations To contribute to solving the above problem, the dissertation has researched and proposed models and successfully built wind power generation capacity forecasting software with a relatively good level of accuracy compared to other models The PSO-PSOANN and GA-PSO-ANN forecasting models proposed by the dissertation have been applied to forecast the generation capacity for Tuy Phong wind power plant in Binh Thuan province, Vietnam The results show that the above forecasting models give much better forecasting results than the PSO-ANN or Adam-ANN models and can be used for wind power plants, dispatch centers to serve the dispatch, operation and production planning of wind power plants Recommendations On the basis of the research results of this dissertation, some further research directions are proposed as follows: - Study the optimal distribution of wind turbines in wind power plants - Research, monitor and automatically control optimal wind power sources through SCADA/EMS system - Research on integrating large-scale renewable energy sources into the power system - Research on optimal operation of wind energy sources in the electricity market 24 PUBLICATIONS OF THE AUTHOR Dinh Thanh Viet, Vo Van Phuong, Minh Quan Duong, Alexander Kies, Bruno U Schyska, Yuan Kang Wu, A Short-Term Wind Power Forecasting Tool for Vietnamese Wind Farms and Electricity Market, 2018 4th International Conference on Green Technology and Sustainable Development (GTSD 2018), 23-24 Nov 2018, Ho Chi Minh City, Vietnam (SCOPUS indexed) Dinh Thanh Viet, Vo Van Phuong, Minh Quan Duong, Ma Phuoc Khanh, Alexander Kies, Bruno Schyska, A Cost-Optimal Pathway to Integrate Renewable Energy into the Future Vietnamese Power System, 2018 4th International Conference on Green Technology and Sustainable Development (GTSD 2018), 23-24 Nov 2018, Ho Chi Minh City, Vietnam (SCOPUS indexed) Dinh Thanh Viet, Tran Quoc Tuan, Vo Van Phuong, Optimal Placement and Sizing of Wind Farm in Vietnamese Power System Based on Particle Swarm Optimization, 2019 International Conference on System Science and Engineering (ICSSE 2019), Dong Hoi city, Quang Binh province, Vietnam, July 20-21, 2019 (SCOPUS indexed) Dinh Thanh Viet, Vo Van Phuong, Minh Quan Duong, Tran Quoc Tuan, Models for Short‐Term Wind Power Forecasting Based on Improved Artificial Neural Network Using Particle Swarm Optimization and Genetic Algorithms, Energies 2020, 13, 2873; doi:10.3390/en13112873 (SCIE journal) Markus Schlott, Bruno Schyska, Dinh Thanh Viet, Vo Van Phuong, Duong Minh Quan, Ma Phuoc Khanh, Fabian Hofmann, Lueder von Bremen, Detlev Heinemann, Alexander Kies, PyPSA-VN: An open model of the Vietnamese Electricity System, 5th International Conference on Green Technology and Sustainable Development (GTSD 2020), Ho Chi Minh city, Vietnam, November 27-28, 2020 (SCOPUS indexed) Dương Minh Quân, Đinh Thành Việt, Lê Tuân, Hoàng Dũng, Võ Văn Phương, Mã Phước Khánh, Vai trò hệ thống lưu trữ với mức độ xâm nhập cao nguồn lượng tái tạo vào lưới điện việt nam đến năm 2030, The University of Danang - Journal of Science and Technology, Vol 18, No 5.2, 2020, page 45-50 Đinh Thành Việt, Võ Văn Phương, Dương Minh Quân, Nguyễn Đình Ngọc Hải, Chu Văn Long, Nghiên cứu ứng dụng học sâu dự báo cơng suất phát nguồn điện gió, The University of Danang - Journal of Science and Technology, Vol 19, 2021, page 6–11 The research cooperation project between Germany and Vietnam is under the Vietnam-Germany Joint Research Initiative on Wind Power program (funded by GIZ and the Ministry of Industry and Trade of Vietnam): Analysis of the Large Scale Integration of Renewable Power into the Future Vietnamese Power System Project Co-Manager: Detlev Heinemann, Dinh Thanh Viet Co-authors: Bruno U Schyska, Stefan Schramm, Alexander Kies, Duong Minh Quan, Vo Van Phuong, Ma Phuoc Khanh, Chau Minh Thang, 2016-2018 The University of Danang scientific research project in 2019 (code B2019-DN01-27): Nghiên cứu ứng dụng trí tuệ nhân tạo kết hợp với thuật toán tối ưu để dự báo cơng suất phát nguồn điện gió Project Manager: Đinh Thành Việt Co-authors: Võ Văn Phương, Dương Minh Quân The project has been accepted and completed