| 1. |
- Altintas, Atilla, 1979, et al.
(författare)
-
Forecasting of Day-Ahead Wind Speed/electric Power by Using a Hybrid Machine Learning Algorithm
- 2023
-
Ingår i: Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering. - 1867-8211 .- 1867-822X. ; 502 LNICST, s. 3-11
-
Konferensbidrag (refereegranskat)abstract
- The amount of energy that has to be delivered for the following day is currently predicted by power system operators using day-ahead load forecasts. With the use of this forecast, generation resources can be committed a day in advance, some of them may require several hours’ notice to be ready to produce power the following day. In order to determine how much wind power will be available for each hour of the following day, power systems with large penetrations of wind generation rely on day-ahead predictions. The main objective of this study is to improve the day-ahead forecasting of wind power by improving the forecasting method using machine learning. A hybrid approach, which combines a mode decomposition method, Empirical Mode Decomposition (EMD), with Support Vector Regression (SVR), is used. The results suggest that using Support Vector Regression together with the hybrid method, which includes the Empirical Mode Decomposition to predictions can improve the accuracy of predictions. Higher accuracy forecasting of wind power is expected to improve the planning of dispatchable energy generation and pricing for the day-ahead power market.
|
|
| 2. |
- Antoniadou-Plytaria, Kyriaki, 1989, et al.
(författare)
-
Effect of Short-term and High-resolution Load Forecasting Errors on Microgrid Operation Costs
- 2022
-
Ingår i: IEEE PES Innovative Smart Grid Technologies Conference Europe. - 9781665480321 ; 2022-October
-
Konferensbidrag (refereegranskat)abstract
- The aim of this paper is to evaluate the effect of the load forecasting errors to the operation costs of a grid-connected microgrid. To this end, a microgrid energy scheduling optimization model was tested with deterministic and stochastic formulations under two solution approaches i.e., day-ahead and rolling horizon optimization. In total, twelve simulation test cases were designed receiving as input the forecasts provided by one of the three implemented machine learning models: linear regression, artificial neural network with backpropagation, and long short-term memory. Simulation results of the weekly operation of a real residential building (HSB Living Lab) showed no significant differences among the costs of the test cases for a daily mean absolute percentage forecast error of about 12%. These results suggest that operators of similar microgrid systems could use simplifying approaches, such as day-ahead deterministic optimization, and forecasts of similar, non-negligible accuracy without substantially affecting the microgrid's total cost as compared to the ideal case of perfect forecast. Improving the accuracy would mainly reduce the microgrid's peak power cost as shown by its 20.2% increase in comparison to the ideal case.
|
|
| 3. |
- Antoniadou-Plytaria, Kyriaki, 1989, et al.
(författare)
-
Market-based Energy Management Model of a Building Microgrid Considering Battery Degradation
- 2021
-
Ingår i: IEEE Transactions on Smart Grid. - 1949-3053 .- 1949-3061. ; 12:2, s. 1794-1804
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents a model for energy management system of a building microgrid coupled with a battery energy storage. The model can be used to dispatch the battery as a flexible energy resource using a market-based setting. The battery is modeled considering battery degradation and real-life operation characteristics derived from measurements at a residential building. The performance of the model was evaluated first with simulations and integrated afterwards to an energy management system, which was demonstrated at a real residential building (HSB Living Lab) equipped with photovoltaic and battery storage systems. The simulation results showed that the building owner, and subsequently the residents, could benefit from the proposed model in reduced annual cost up to 3.1% under the considered pricing scheme. The demonstration results showed that dispatch under the measurement-based model could decrease the undelivered energy over the daily requested amount from the battery from 13.3% to 3.7%. Thus, the proposed model, which couples the measurement-based dispatch with battery degradation, can lead to a more accurate estimation of the building operation cost and an improved overall performance of battery as a flexible resource in building microgrids.
|
|
| 4. |
- Antoniadou-Plytaria, Kyriaki, 1989, et al.
(författare)
-
Scenario-based Stochastic Optimization for Energy and Flexibility Dispatch of a Microgrid
- 2022
-
Ingår i: IEEE Transactions on Smart Grid. - 1949-3053 .- 1949-3061. ; 13:5, s. 3328-3341
-
Tidskriftsartikel (refereegranskat)abstract
- Energy storage is one of the most important components of microgrids with non-dispatchable generators and can offer both energy and flexibility services when the microgrid operates in grid-connected mode. This paper proposes a scenario-based stochastic optimization model that can be used to determine the energy and flexibility dispatch of a residential microgrid with solar and stationary battery systems. The objective of the model is to minimize the expected energy and peak power cost as well as the battery aging cost, while maximizing the expected revenue from flexibility. The formulated stochastic optimization problem is solved in rolling horizon with the uncertainty model being dynamically updated to consider the most recent forecast profiles for solar power and electricity demand. The benefits of the proposed approach were demonstrated by simulating the daily operation of a real building. The results showed that the estimated flexibility was successfully dispatched yielding an economic value of at least 7% of the operation cost of the building microgrid. The model can be used by flexibility providers to assess their flexibility and design a bidding strategy as well as by system operators to design incentives for flexibility providers.
|
|
| 5. |
- Hodel, Henrik, 1995, et al.
(författare)
-
Which wind turbine types are needed in a cost-optimal renewable energy system?
- 2024
-
Ingår i: Wind Energy. - 1099-1824 .- 1095-4244. ; 27:6, s. 549-568
-
Tidskriftsartikel (refereegranskat)abstract
- Previous research has indicated that wind power plants can be designed to have less-variable power generation, thereby mitigating the drop in economic value that typically occurs at high wind power penetration rates. This study investigates the competitiveness of adapted turbine design and the interplay with other flexibility measures, such as batteries and hydrogen storage, for managing variations. The analysis covers seven turbine designs for onshore and offshore wind generation, with different specific power ratings and hub heights. Various flexibility measures (batteries, hydrogen storage and transmission expansion) are included in the optimization of investment and dispatch of the electricity system of northern Europe. Three driving forces for turbine design selection are identified: (1) lowest cost of electricity generation; (2) annual wind production per land area and (3) improved generation profile of wind power. The results show that in regions with good wind resources and limited availability of variation management, it is cost-efficient to reduce the variability of wind power production by adapting the turbine design. This remains the case when variation management is available in the form of batteries, hydrogen storage and transmission system expansion. Moreover, it is more cost-effective to improve variability by changing the specific power rating rather than the turbine hub height.
|
|
| 6. |
- Mirzaei Alavijeh, Nima, 1993, et al.
(författare)
-
Key Drivers and Future Scenarios of Local Energy and Flexibility Markets
- 2021
-
Ingår i: 2021 IEEE Madrid PowerTech, PowerTech 2021 - Conference Proceedings.
-
Konferensbidrag (refereegranskat)abstract
- This paper explores the key drivers of local energy and flexibility markets, develops a set of plausible future scenarios for these markets, and analyzes the scenarios' impact. The results can provide insight to policymakers, researchers, system operators, and aggregators in a better design and more successful implementation of local markets. This study is based on the well-established scenario planning technique of "intuitive logics"and it is conducted by means of qualitative methods, surveys, and cross-impact analysis. Results explore and rank the impact and uncertainty of 20 key factors and trends which can affect the future of local energy and flexibility markets. The results show that factors related to the availability of active and smart end-users, and regulatory incentives are the most impactful and uncertain ones in the future of local markets. Four future scenarios are introduced based on these factors and their impacts are discussed.
|
|
| 7. |
- Roghani Araghi, Ali, et al.
(författare)
-
Enhancing the net energy of wind turbine using wind prediction and economic NMPC with high-accuracy nonlinear WT models
- 2020
-
Ingår i: Renewable Energy. - : Elsevier BV. - 0960-1481 .- 1879-0682. ; 151:May, s. 750-763
-
Tidskriftsartikel (refereegranskat)abstract
- Economic nonlinear model predictive control (ENMPC) is a strong candidate for controlling wind turbines (WTs). In the model predictive control (MPC) group, the model is the crucial component for the true controller performance. It is common to use simplified models to reduce the problem complexity. These models neglect some of the underlying dynamic responses of real wind turbines. This paper simulates the case in which high accuracy nonlinear models describe both the plant and the controller. The results will be compared to reduced-order models in order to extract conclusions and decide the most appropriate model for WT control. On the other hand, one of the main features of MPC and ENMPC is the concept of receding prediction horizon, which considers the future evolution of the plant to compute the control action. The error of prediction will drastically reduce MPC performance. Also, rapid variation in wind speed can cause problems since wind turbines cannot easily follow these sudden variations due to their high inertia and aerodynamic characteristics. This paper provides an advanced control approach to improve the energy extraction from turbulent wind and enhance wind turbine durability. By implementing this method, the wind speed forecasting is done with a combination of artificial neural networks (ANN) and dynamic equations applied in ENMPC. The results show a significant enhancement of the control performance.
|
|
| 8. |
- Srivastava, Ankur, 1989, et al.
(författare)
-
A Review on Challenges and Solutions in Microgrid Protection
- 2021
-
Ingår i: 2021 IEEE Madrid PowerTech, PowerTech 2021 - Conference Proceedings.
-
Konferensbidrag (refereegranskat)abstract
- Protection of microgrid has become challenging due to the hosting of various actors such as distributed generation, energy storage systems, information and communication technologies, etc. The main protection challenges in the microgrid are the bi-directional power flow, protection blinding, sympathetic tripping, change in short-circuit level due to different modes of operation, and limited fault current contribution by converter-interfaced sources. This paper presents a comprehensive review of the available microgrid protection schemes which are based on traditional protection principles and emerging techniques such as machine learning, data-mining, wavelet transform, etc. A categorical assessment of the reviewed protection schemes is also presented. The key findings of the paper suggest that the time-domain and communication-assisted protection schemes could be suitable solutions to address the identified protection challenges in the microgrid.
|
|
| 9. |
- Srivastava, Ankur, 1989, et al.
(författare)
-
Development of a DSO Support Tool for Congestion Forecast
- 2021
-
Ingår i: IET Generation, Transmission and Distribution. - : Institution of Engineering and Technology (IET). - 1751-8687 .- 1751-8695. ; 15:23, s. 3345-3359
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents a novel DSO support tool with visualisation capability for forecasting network congestion in distribution systems with a high level of renewables. To incorporate the uncertainties in the distribution systems, the probabilistic power flow framework has been utilised. An advanced photovoltaic production forecast based on sky images and a load forecast using an artificial neural network is used as the input to the tool. In addition, advanced load models and operating modes of photovoltaic inverters have been incorporated into the tool. The tool has been applied in case studies to perform congestion forecasts for two real distribution systems to validate its usability and scalability. The results from case studies demonstrated that the tool performs satisfactorily for both small and large networks and is able to visualise the cumulative probabilities of nodes voltage deviation and network components (branches and transformers) congestion for a variety of forecast horizons as desired by the DSO. The results have also shown that explicit inclusion of load-voltage dependency models would improve the accuracy of the congestion forecast. For demonstrating the applicability of the tool, it has been integrated into an existing distribution management system via the IoT platform of a DMS vendor, Atos Worldgrid.
|
|
| 10. |
- Srivastava, Ankur, 1989, et al.
(författare)
-
Dynamic State Estimation based Transmission Line Protection Scheme: Performance Evaluation with Different Fault Types and Conditions
- 2023
-
Ingår i: International Journal of Electrical Power and Energy Systems. - : Elsevier BV. - 0142-0615. ; 148
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents the experimental validation of a transmission line protection scheme based on dynamic state estimation for different fault types and conditions. The protection scheme utilizes real-time high-frequency sampled measurements from advanced sensors and evaluates the operating condition of the transmission line based on which a tripping signal is generated in case a fault occurs. The validation is performed using a physical scaled-down model of a power system, consisting of a transmission line, transformer, synchronous generator, and loads. The following faults are examined during the validation: unbalanced faults under different load conditions, high impedance fault, fault current fed from both ends, hidden failure, external fault, and load change conditions. The results show that the scheme performs as intended and thus proves its efficacy to detect various types of faults. The maximum fault detection time is calculated to be 42.5 milliseconds, while the maximum fault clearing time comes out to be 82.5 milliseconds, on par with currently employed protection methods. The obtained results demonstrate the ability of the scheme to detect different fault types under varying conditions and avoid potential issues with relay coordination
|
|
