Search

Abstract The integration of renewable energy sources (RESs) into power systems has increased significantly due to technical, economic, and environmental factors, necessitating greater flexibility to manage variable consumption loads and renewable energy generation. Accurate forecasting of solar energy production and consumption load is critical for enhancing power system flexibility. This study introduces a novel deep learning model, a spatial‐temporal hybrid convolutional‐transformer (CT‐Transformer) network with unique features and extended memory capacity. Additionally, a flexibility index (FI) is introduced to evaluate power system flexibility (PSF) based on the forecasting results. The CT‐Transformer forecasts PSF for the next 24 and 168 hours, using the FI to evaluate PSF based on forecasting results. The input data includes meteorological, solar energy production, load demand, and pricing data from France, comprising hourly data from 2015 and 2016 (about 17,520 entries). Data preprocessing involves correcting incomplete and irrelevant segments. The CT‐Transformer's performance is compared to other deep learning techniques, showing superior results with the lowest prediction error (2.5%) and a maximum error of 10.1% (MAE). It also achieved a prediction error of 0.08% for system flexibility, compared to the highest error of 0.96%. This research highlights the CT‐Transformer's potential for accurate RES and load forecasting and PSF evaluation.

Abstract Demand‐side flexibility or demand response (DR) has long been recognized as a potential source of balancing capacity. The charging of electric vehicles (EVs) is a known source of flexible capacity, and the vast amount of charging capacity available can be utilized for valuable applications, including ancillary power markets, by controlling the charging sessions according to the needs of the power system. One identified and unexplored potential market for EV DR capacity is the Fast Frequency Reserve (FFR) market for the Nordic system area. This article proposes and demonstrates that a home charger can participate in this extremely fast reacting ancillary service market with only software modifications made to the charger. The biggest challenge in the FFR market is the response time requirement for capacity activation. When a certain frequency limit is exceeded, the activation must happen within 0.7 s in the worst case. In this study, a laboratory test setup was constructed to test the capabilities of the FFR‐enabled EV charger. The tests were conducted by building a laboratory microgrid capable of changing the grid frequency. Additionally, an economic feasibility study was carried out to evaluate the business potential of the concept in Finland. The economic study included an analysis of the concept's potential with different levels of DR service availability. The laboratory tests demonstrated the FFR capabilities of the charger and as a final outcome of the research, the Norwegian transmission system operator (TSO) approved the tested charger as a type‐prequalified FFR‐providing entity. The economic study revealed that the approach has good business potential, primarily because of the almost non‐existent cost side even if the availability rate decreases significantly.

Abstract The study aims to predict solar energy generation to ensure the successful operation of solar power plants. This objective is crucial in light of the increasing energy demand, global warming concerns, and greenhouse gas emissions. To achieve this, the study employs multiple linear regression and feature selection techniques to calculate energy generation. Additionally, long short‐term memory (LSTM) is used to predict energy generation levels based on climate conditions. Furthermore, the spatial distribution of energy generation is analyzed using inverse distance weighting. The results of the study reveal that temperature, solar radiation, relative humidity, wind speed, wind direction, and vapor pressure deficit are the most significant parameters for predicting energy generation. The LSTM method proves to be highly accurate in predicting fluctuating energy generation patterns. Notably, the southern regions of the study area exhibit a greater potential for energy generation compared to the northern regions. Approximately 30% of the region generates over 1400 kWh, with the southern areas, characterized by hot and dry climates, producing around 1500 kWh, while the northern regions, with cold and humid climates, generate approximately 1100 kWh.

Abstract Natural disasters, man‐made attacks, and cyber‐attacks are some of the main hazards of power system which can interrupt the process of continuous power delivery to the end users. In this way, man‐made attacks characteristics’ are fundamentally different from other hazards due to its adaptive strategy that allows attackers to target the most vulnerable parts of the power system. By choosing appropriate time and place; attackers always have advantages over the defender to penetrate the system and launch malicious actions. Therefore, it is quite necessary to take into account the optimal policy for allocating resources in the defender's strategy. This research proposes a four‐level Defence–Defence–Attack–Defence (DDAD) approach to improve the power system resilience against the intentional human attacks. A new defence level, a planning level, is added to the common three‐level Defence–Attack–Defence (DAD) model in power system planning state in order to prevent cut off loads and voltage drop beyond standard with lower cost. In the proposed method, load priority is used to classify the vulnerable sections. The proposed model is performed on IEEE‐30 bus test system and the results indicate the feasibility of the proposed method. As the results indicate, in proposed method less than 10% budget is needed compared with the previous method while all critical loads will be remained. Furthermore, the new method needs no security guard to protect transmission lines for 30 years.