The power of photovoltaic power generation is affected by a variety of factors such as weather, radiation and temperature, exhibit a high degree of randomness and uncertainty. To address this problem, this paper propo...
详细信息
ISBN:
(数字)9798331523527
ISBN:
(纸本)9798331523534
The power of photovoltaic power generation is affected by a variety of factors such as weather, radiation and temperature, exhibit a high degree of randomness and uncertainty. To address this problem, this paper proposes a ultra-short-term photovoltaic power prediction model based on Convolutional Neural Networks (CNN) and attention mechanism and bidirectional long short-term memory (Bi-LSTM). Firstly, Pearson's correlation coefficient was used to filter out the meteorological factors which have significant influence on the historical power. Subsequently, in order to capture the spatial features of the input data, a convolutional neural network is utilized for feature extraction and an attention mechanism is introduced to strengthen the model's ability to discriminate key features. Meanwhile, the Bi-LSTM network is utilized to capture the temporal dependencies in the time series data, and finally the PV power prediction value is obtained. Finally, the validation is based on data from actual PV power plants, and the results show that the proposed Convolutional Neural Networks and attention mechanism (CA) and Bi-LSTM Ultra-short-term PV power prediction model outperforms the single model in terms of prediction accuracy, reflecting the effectiveness and superiority of the hybrid model.
Aiming to address the stability challenges in powersystems caused by the volatility and uncertainty of photovoltaic (PV) power generation, an optimization strategy for PV-storage systems incorporating demand response...
详细信息
ISBN:
(数字)9798331523527
ISBN:
(纸本)9798331523534
Aiming to address the stability challenges in powersystems caused by the volatility and uncertainty of photovoltaic (PV) power generation, an optimization strategy for PV-storage systems incorporating demand response (DR) is proposed. Which is based on PV generation characteristics, Time-of-Use Pricing (TUP), and demand side flexibility. A multi-objective optimization model is established to balance the operational and environmental costs of PV-storage configuration. Building on dynamic adjustments at the demand side, a Multi-Objective Particle Swarm Optimization (MOPSO) algorithm with dynamic inertia weighting is introduced to enhance global search capability for optimized energy storage (ES) configuration. In case study, two scenarios are designed to validate the effectiveness of the proposed model in reducing costs and improving PV utilization rates.
High percentage of photovoltaic gain connect to the wire line, so that the electricity grid from power distribution of the receiving end of the network into a set of production, storage, distribution of multi-source c...
详细信息
ISBN:
(数字)9798350309638
ISBN:
(纸本)9798350309645
High percentage of photovoltaic gain connect to the wire line, so that the electricity grid from power distribution of the receiving end of the network into a set of production, storage, distribution of multi-source complex new network, the distribution network security operation and new energy consumption pressure increases. In response to the above, this paper puts forward the distributed ES multi-objective optimization configuration strategy of distribution network adapted to the high penetration rate distributed PV. And through a county power grid practical example to certify that the ES configuration approach proposed can effectively mitigate the impact of a high proportion of PV accessed, and it can reduce the abandonment of light.
With the rapid growth of wind power penetration, wind farms (WFs) are required to implement frequency regulation that active powercontrol to track a given power reference. Due to the wake interaction of the wind turb...
详细信息
Aiming at the problem of heavy overload in the distribution station area during the peak period of energy consumption caused by intermittent loads such as agricultural motor wells, the mobile energy storage technology...
详细信息
ISBN:
(数字)9798331527624
ISBN:
(纸本)9798331527631
Aiming at the problem of heavy overload in the distribution station area during the peak period of energy consumption caused by intermittent loads such as agricultural motor wells, the mobile energy storage technology is considered to meet the agricultural power demand, and a two-stage mobile energy storage vehicle pre configuration and dynamic adjustment strategy of "Rural busy power energization" and "rural idle distributed energy storage" is proposed, taking into account the guarantee of load power demand and the efficiency and economy of energy storage. Firstly, the mathematical model of agricultural motor well load considering the time shift characteristics and the mobile energy storage vehicle model considering the power supply time constraint are established; Secondly, a multi-stage mobile energy storage configuration and scheduling strategy is established. In the Rural busy power generation stage, the mobile energy storage vehicle capacity is configured with the minimum daily power supply cost as the goal, and the power supply path is optimized with the highest charge state consistency at the completion of power supply as the goal; At the stage of distributed energy storage in rural slack, the collaborative optimization of mobile energy storage vehicles participating in multi scenario power services is carried out with the goal of maximizing the annual net income. Finally, the proposed two-stage strategy has certain economic benefits under the premise of meeting the power demand of the load, which is verified by combining the power consumption data of wells in Jilin Province and IEEE 33 bus systemsimulation.
With the deployment of wide-area measurement systems (WAMS) equipment, dynamic security assessment (DSA) based on artificial intelligence (AI) has more and more advantages. For the powersystem, the number of transien...
详细信息
To achieve large-scale renewableenergy, grid friendly coordination and the need to maximize grid-connection and consumption functions, the clustering method has become a forward-looking solution for distribution netw...
To achieve large-scale renewableenergy, grid friendly coordination and the need to maximize grid-connection and consumption functions, the clustering method has become a forward-looking solution for distribution network planning, construction and dispatching control. In this paper, the modularity index and active power balance index based on electrical distance are taken as the comprehensive classification index. Then genetic algorithm is introduced to divide the distributed PV cluster in the distribution network. Finally, a 10kV distribution system is taken as an example, and the distributed photovoltaic cluster planning is simulated and analyzed, which proves that the distributed photovoltaic cluster division method is effective.
Aiming to address the stability challenges in powersystems caused by the volatility and uncertainty of photovoltaic (PV) power generation, an optimization strategy for PV-storage systems incorporating demand response...
详细信息
This paper addresses the shared energy storage siting and sizing problem, considering grid constraints based on scenario generation techniques. In the context of high penetration of renewableenergy, the powersystem ...
详细信息
ISBN:
(数字)9798350349030
ISBN:
(纸本)9798350349047
This paper addresses the shared energy storage siting and sizing problem, considering grid constraints based on scenario generation techniques. In the context of high penetration of renewableenergy, the powersystem faces practical challenges such as increased uncertainty and scarcity of flexible resources. To tackle these issues, a two-layer optimization model is proposed in this study. It utilizes scenario generation techniques to obtain possible scenarios for renewableenergy and load outputs, and incorporates grid constraints for economic dispatch. Through iterative optimization, an optimal shared energy storage siting and sizing solution that meets the requirements of the power grid is obtained. Additionally, the paper discusses the impact on the accommodation capacity of renewableenergy and proposes countermeasures in system economic dispatch. However, there are still limitations in uncertainty estimation, energy storage planning, and investment cost calculations in this paper. Furthermore, further enhancement is needed in terms of quantification theories supporting the economic evaluation of shared energy storage siting and sizing. Overall, this research aims to provide an optimization approach for the shared energy storage siting and sizing problem, incorporating scenario generation techniques and grid constraints, to promote stable operation and economic development of powersystems with high penetration of renewableenergy.
In the context of the rising share of new energy generation, accurately generating new energy output scenarios is crucial for day-ahead powersystem scheduling. Deep learning-based scenario generation methods can addr...
详细信息
暂无评论