Power System Operation Research Articles

Comparison of Artificial Intelligence and Machine Learning Methods Used in Electric Power System Operation

Comparison of Artificial Intelligence and Machine Learning Methods Used in Electric Power System Operation

Green hydrogen exports in New Zealand and Chile can improve electricity supply security if configured as local energy insurance

Extreme weather events, for example, prolonged droughts, are increasingly stressing electricity systems and threatening the achievement of energy transition goals. At the same time, countries such as Chile and New Zealand are developing strategies to export renewable energy through green hydrogen. This paper economically evaluates the use of future green hydrogen exports as strategic storage under the logic of energy insurance, based on the assumption that Chile and New Zealand will adopt a hydrogen economy. Our first contribution is to compare the marginal costs of re-electrified green hydrogen, for different scenarios, to the value of lost load in New Zealand and Chile. We then determine the marginal cost of energy produced from green hydrogen based on projected production, transportation, and re-electrification costs for the year 2030. Finally, we estimate the eventual penalties that exporters would incur in the case of breaking their contracts and the overall resulting system costs of using hydrogen for system security. We found that re-electrifying hydrogen can be competitive with conventional technologies at 3 USD/kg. At 1.5 USD/kg, hydrogen is more competitive than fossil fuel-based technologies, for both New Zealand and Chile. Thus, in 2030, it could make economic sense for New Zealand and Chile to use hydrogen as a strategic reserve. The system cost of the proposed insurance scheme in 2030 ranges from 0.53 to 1.76 USD/MWh, which is small compared to total electricity costs. These values can be used for power system expansion and operation planning.

Risk Assessment and Analysis of New Power System Operation Under Extreme Disasters

Abstract In recent years, new power systems have been developing continuously, and the operational risk assessment of new power systems under extreme disaster conditions has attracted much attention. This paper uses Latin hypercube sampling technology to establish a power system failure model under extreme disasters and proposes a new power system risk assessment method that applies the power system power flow model to establish a comprehensive system risk index. In addition, taking the power grid of a certain province in eastern China as an example, a case analysis is conducted on the IEEE39 node system to verify the effectiveness of the method.

Real-time multi-risk assessment of large scale power system with high-penetration renewable energy

Abstract To accurately assess the impact of real-time uncertainty of high penetration renewable energy sources on the real-time operation of large-scale power systems, this study proposes an innovative method for real-time multi-risk assessment in power systems. Firstly, by utilizing an improved spectral clustering algorithm and mixture density network to analyze historical operational data, effective clustering of different renewable energy generation curves and accurate fitting of prediction errors were achieved. Next, random sampling was performed from the probability density curves of prediction errors to obtain real-time renewable energy outputs. At the same time, a non-sequential Monte Carlo method was used to incorporate interruptions for each component into the scenario simulation. Subsequently, a state assessment was conducted for each sampled scenario by minimizing load shedding and energy curtailment. On this basis, risk indices that comprehensively consider the real-time flexibility of the system and power supply-demand imbalances were established. Finally, validation in a test system verified the accuracy and speed of the proposed multi-risk assessment method.

Current ripple optimization design of DC/DC converter

Abstract Renewable energy has the advantages of renewability and high temperature and has great potential for development, but its instability limits its large-scale promotion. Aiming at the stable operation of the new energy power system and ensuring the safe and reliable operation of the power grid, this project defines the basic topology of the variable multiple DC/DC converter according to the idea of switching circuit parallel factor or reducing ripple under each duty cycle. Secondly, the system structure under the boost mode is modeled, and the system is optimized by the combination of a single closed-loop current balance and duty cycle feedforward control. Finally, the model is simulated, and the results show that the method is correct and reasonable.

Research on the diagnosis method of inter-turn short-circuit faults of dry-type air-core reactor winding based on frequency response analysis

Inter-turn short circuit fault (ISCF) is the main fault type of dry-type air-core reactors (DARs), and the reactor burnout event caused by winding ISCF seriously threatens the safe and stable operation of the electric power system. In order to effectively curb the further worsening of ISCF in DARs, a fault detection method based on frequency response analysis was proposed. First, the effect of ISCF on the frequency response curve of the windings was investigated based on the distributed parameter model of DARs. Then, four sets of eigenvalues were proposed for ISCF diagnosis based on the influence law and curve data analysis theory. Finally, based on the eigenvalues, the support vector machine model optimized by the sparrow search algorithm was used to effectively classify the degree of ISCF of the reactor, and the accuracy reached 96%. Furthermore, a test platform was built based on the theoretical analysis for experimental verification, and the test results are consistent with the simulation results. Hence, the method proposed in this paper could effectively classify the ISCF and its severity in DARs. The research in this paper could provide effective guidance for the diagnosis of ISCF in DARs.

Novel cyber-physical collaborative detection and localization method against dynamic load altering attacks in smart energy grids

Owing to the integration of energy digitization and artificial intelligence technology, smart energy grids can realize the stable, efficient and clean operation of power systems. However, the emergence of cyber-physical attacks, such as dynamic load-altering attacks (DLAAs) has introduced great challenges to the security of smart energy grids. Thus, this study developed a novel cyber-physical collaborative security framework for DLAAs in smart energy grids. The proposed framework integrates attack prediction in the cyber layer with the detection and localization of attacks in the physical layer. First, a data-driven method was proposed to predict the DLAA sequence in the cyber layer. By designing a double radial basis function network, the influence of disturbances on attack prediction can be eliminated. Based on the prediction results, an unknown input observer-based detection and localization method was further developed for the physical layer. In addition, an adaptive threshold was designed to replace the traditional precomputed threshold and improve the detection performance of the DLAAs. Consequently, through the collaborative work of the cyber-physics layer, injected DLAAs were effectively detected and located. Compared with existing methodologies, the simulation results on IEEE 14-bus and 118- bus power systems verified the superiority of the proposed cyber-physical collaborative detection and localization against DLAAs.

Research on system/regional dispatch center-based hierarchical zonal load dispatch model

Abstract The development of new power systems and the expanding scale of demand-side load resources represented by electric vehicles have brought new challenges to the stable and economic operation of power systems, and the current load aggregation regulation model is no longer adapted to the current environment. Based on this, this paper proposes a hierarchical zonal load aggregation regulation model, in which the system layer and the regional layer cooperate to regulate the resources, and finally verifies the feasibility and economy of the model by example analysis.

Residential electricity prediction based on GA-LSTM modeling

With residential electricity demand increasing year after year due to population growth and infrastructure expansion, accurate electricity load forecasting is critical to the operation of power systems. Although certain traditional machine learning models have achieved better results in several fields, their prediction accuracy for energy sources such as electricity is still unsatisfactory. The nonlinear and non-smooth consumption patterns of residential electricity make accurate prediction of electricity loads even more challenging. In this paper, we propose an attention-based competitive stochastic search method for training Long Short-Term Memory (LSTM) networks to predict electricity energy consumption. On the one hand, an attention layer is added to the traditional LSTM to assign feature weights; on the other hand, a genetic algorithm is introduced for stochastic search to prevent convergence to a local optimum during the training process. The experimental results show that the proposed model combines genetic algorithm and LSTM, and the prediction accuracy of the proposed model is higher than other existing prediction models in terms of root mean square error (RMSE), mean absolute error (MAE), r-square(R2), and mean absolute percentage error (MAPE), which are 0.6056, 0.3726, 0.8517, and 0.1856, respectively. In addition, the model also achieves excellent results in short-term prediction, which is better than the traditional LSTM, and the accuracy is significantly improved. It is proved that this method is effective and feasible in the prediction of power energy consumption.

Voltage stability index: a review based on analytical method, formulation and comparison in renewable dominated power system

In an interconnected complex power system network voltage stability evaluation is indispensable to guarantee secure power system operation. To further increase the system performance and to make the system safer assessment, the voltage stability improvement is obligatory. In the various literature different voltage security assessment method using the voltage stability index has been presented. Different lists proposed in literature can be utilized to realize the weak buses and weak transmission lines to enacting the countermeasures against issues of voltage insecurity. Additionally, the arrangement and measuring of inexhaustible assets, on the web and disconnected observing of force framework and the measure of load to be shed at whatever point essential. This paper shows a survey on the different voltage stability index from various perspectives. The audit results on various record gives a far and wide logical to perceive the impending works in this field and to choose the best index for variety of applications such as voltage security assessment, renewable energy integration, distributed generation (DG) placement and sizing, online monitoring of the power system, and shedding of load.

Space Division and WGAN-GP Based Fast Generation Method of Practical Dynamic Security Region Boundary

Fast and accurate transient stability analysis is crucial to power system operation. With high penetration level of wind power resources, practical dynamic security region (PDSR) with hyper plane expression has outstanding advantages in situational awareness and series of optimization problems. The precondition of obtaining accurate PDSR boundary is to locate sufficient points around the boundary (critical points). Therefore, this paper proposes a space division and Wasserstein generative adversarial network with gradient penalty (WGAN-GP) based fast generation method of PDSR boundary. First, the typical differential topological characterizations of dynamic security region (DSR) provide strong theoretical foundation that the interior of DSR is hole-free and the boundaries of DSR are tight and knot-free. Then, the space division method is proposed to calculate critical operation area where the PDSR boundary is located, tremendously compressing the search space to locate critical points and improving the confidence level of boundary fitting result. Furthermore, the WGAN-GP model is utilized to fast obtain large number of critical points based on learning the data distribution of the small training set aforementioned. Finally, the PDSR boundary with hyperplanes is fitted by the least square method. The case study is tested on the Institute of Electrical and Electronics Engineers (IEEE) 39-bus system and the results verify the accuracy and efficiency of the proposed method.

Low‐carbon power system operation with disperse carbon capture‐transportation‐utilization chain

Low‐carbon power system operation with disperse carbon capture‐transportation‐utilization chain

FEM-Circuit co-simulation of superconducting synchronous wind generators connected to a DC network using the homogenized J–A formulation of the Maxwell equations

High-temperature superconductors (HTS) are greatly appealing for the development of high efficient, and high energy density power devices. They are particularly relevant for applications requiring light and compact machines such as wind power generation. In this context, to ensure the proper design of the superconducting machines and their reliable operation in power systems, it is then important to develop models that can accurately include their physics but also can describe properly their interaction with the system. To achieve such a goal, one approach is the co-simulation. This numerical technique can bring fine geometrical and physical details of the machines through a finite element model (FEM) meanwhile dealing with the operation of the whole system that incorporates the machine and a subset of the power grid represented by an external electrical circuit. The goal of the present work is to put to use this numerical technique when superconducting components are involved. Here, a case study is proposed involving a 15 MW hybrid superconducting synchronous generator (HTS rotor and conventional stator) coupled to a direct current network via a rectifier and its associated filter. The case study related to wind power application allows grasping the technical issues when employing co-simulation dealing with HTS machines. The FEM of the generator is done in the commercial software COMSOL Multiphysics, which interacts with the circuit simulator Simulink through the built-in Functional Mock-up Unit. For the present study, a new version of the latest J–A formulation combined with homogenization technique is introduced allowing an even faster computation time compared to the T–A formulation. Distributed variables and global variables such as current density, magnetic flux density, and local losses for the former and voltage, current, electromagnetic torque, and power quality for the latter are estimated and compared for both formulations. The idea is to find the best-suited combination FEM-circuit under criteria of computational speed, accuracy, and numerical stability. Thus, it is shown that all formulations generate an error of less than 5% on the machine parameters and that the J–A formulation with first order elements stands out with a significant 4-fold reduction in computational costs.

A data-driven distributionally robust expansion planning model for ADNs with multi-microgrids considering energy trading strategy based on game theory

With the increasing integration of distributed energy resources, demand response, microgrids, and automation technologies in modern distribution networks, a market framework for local energy trading among microgrids and the distribution utility is a reality. However, the expansion planning problem for active distribution networks (ADNs) with multiple microgrids is complex due to uncertainties associated with distributed generation and competitive scenarios. This paper proposes a novel data-driven distributionally robust model that considers energy trading and uncertainties in generation and load to solve the expansion planning problem for ADNs with multiple microgrids. The uncertainties are represented using data bins and their probabilities, and the energy trading strategy is modeled based on game theory. The proposed model enables the distribution system operator (DSO) to find the best expansion planning from their perspective, while each microgrid seeks its own benefits. We exemplify the proposed model using a modified version of the IEEE 123-bus test system. Results demonstrate the effects of surplus generation levels on the energy price strategy and the influence of competitive environments on the expansion planning decision. The proposed model provides a new approach to address the complexities associated with the expansion planning problem for ADNs with multiple microgrids and could have significant implications for the design and operation of future power systems.

Federated knowledge distillation for enhanced insulator defect detection in resource‐constrained environments

AbstractInsulator defect detection is crucial for the stable operation of power systems. It has become a mainstream research direction to realise insulator defect detection based on the combination of line images captured by UAVs and deep learning techniques. However, the existing high‐quality insulator defect detection models still face problems such as relying on massive‐labelled data and huge model parameters. Especially on resource‐constrained devices, it becomes a challenge to strike a balance between model lightweighting and performance. Although the knowledge distillation technique provides a solution for model lightweighting, the loss of information in the distillation process leads to the performance degradation of small models, which in turn creates a paradox between lightweighting and performance. Hence, an insulator defect detection method based on federated knowledge distillation is proposed. The method not only realises the lightweighting of the model, but also effectively improves the model performance by collaboratively training the model through the federated learning approach. Moreover, the asynchronous aggregation approach and model freshness mechanism designed in the method further enhance the training efficiency and collaborative effect. The experimental results show that the detection accuracy and efficiency of this paper's method on public datasets are significantly better than the benchmark algorithm.

Dual NWP wind speed correction based on trend fusion and fluctuation clustering and its application in short-term wind power prediction

With the continuous growth of grid-connected installed capacity of wind power, the inevitable gap, volatility and randomness of wind power pose challenges to the stability of real-time operation of power system. Accurate wind power prediction (WPP) can effectively ensure the safe and stable operation of power system. At present, the main input of short-term power prediction based on data-driven model is numerical weather prediction (NWP), and its prediction accuracy leads to the failure to effectively improve the accuracy of short-term power prediction. To solve this problem, this paper proposes a dual NWP wind speed (WS) correction method based on trend fusion and fluctuation clustering. First, the WS trend is used to construct a new input feature, and the NWP WS error distribution is determined to establish a more correct and stable mapping relationship with the NWP WS error. Secondly, the error is decomposed by Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), and the trend and fluctuation components are defined by Pearson coefficient. The trend curve features in the short 24h period were extracted from the two dimensions of time and value, and the trend and fluctuation curve databases under different scenarios were formed by K-Medoids clustering. Finally, the trend component is modified by the Attention-GRU model, and the corresponding trend component is searched and matched from the database to correct the fluctuation component. The NWP WS is modified by the superposition of the two components and the short-term WPP is made. Two wind farms in Mengxi, China were used for example analysis, and the prediction accuracy was improved by 10 % and 13.1 % respectively, which demonstrated the effectiveness of the proposed method.

Research on two‐level energy management based on tiered demand response and energy storage systems

AbstractIn response to the escalating demands of the electricity market for load dispatch optimization and the stable operation of power systems, the design of effective incentive mechanisms to guide user electricity consumption behaviour has become an urgent task. This study addresses the complexity of the power load dispatch system by analysing the characteristics and interrelations of large‐scale user load demand responses. A dual‐layer energy management model was constructed, and a demand response incentive mechanism was designed. Adaptive incentive strategies were formulated according to different electric power user demand response scenarios. Furthermore, an optimal incentive decision‐making technology oriented towards user comfort was proposed, achieving an integrated function of strategy formulation, implementation, analysis, and optimization for power demand response. Through typical applications in core business scenarios such as elasticity of power user demand response, tiered incentive mechanisms, and comprehensive user utility, the model and strategies have been confirmed to optimize the economic benefits of virtual power plants and demand‐side electricity users under the premise of ensuring user comfort. This provides a novel solution for the efficient operation of the power market.

A computational efficient approach for distributionally robust unit commitment with enhanced disjointed layered ambiguity set

AbstractTo achieve the sustainable development of the society, renewable energy dominated power systems are gradually formed. However, the uncertainty of renewable power poses challenges for power system operations, such as balancing the load and generation in day‐ahead unit commitment problems. To address this issue, an enhanced disjointed layered ambiguity set is proposed in this paper to effectively capture the uncertainty of renewable generation forecast errors. On this basis, a two‐stage distributionally robust unit commitment optimization problem is formulated, which is computational challenge. To this end, a novel reformation approach and a worst‐case support set identification method are proposed to derive the optimal solution in a computationally efficient way. Simulation results demonstrate that the proposed ambiguity set brings lower operation costs of unit commitment while maintaining similar reliability compared to existing methods. In detail, the proposed ambiguity set achieves a reduction in operating costs of approximately 10.01%. The proposed novel reformation approach and solution method are also shown to have higher computation efficiency than the existing Benders decomposition method, resulting in a reduction in computation time to less than 3.78% of the original duration.

Research and application of power equipment monitoring and fault diagnosis

Power equipment monitoring and fault diagnosis are important parts of power system operation and maintenance. By monitoring the status and performance parameters of power equipment in real time, and timely discovering and diagnosing potential fault problems, the reliability, safety and economy of the power system can be improved. At present, this research has made significant progress, but there are still some research gaps that need to be further explored and resolved. Through the research and application of power equipment monitoring and fault diagnosis, this paper aims to improve the reliability, safety and economy of power grid, reduce the risk of failure, optimize equipment operation and maintenance strategies, and improve power supply quality and user satisfaction. Condition monitoring and fault diagnosis are very important for the normal operation of the power system equipment, which can not only strengthen the fault diagnosis of the power system equipment, but also avoid the problem of large-scale paralysis caused by the failure of the power system equipment.

Short-Term Electrical Load Forecasting Using an Enhanced Extreme Learning Machine Based on the Improved Dwarf Mongoose Optimization Algorithm

Accurate short-term electrical load forecasting is crucial for the stable operation of power systems. Given the nonlinear, periodic, and rapidly changing characteristics of short-term power load forecasts, this paper introduces a novel forecasting method employing an Extreme Learning Machine (ELM) enhanced by an improved Dwarf Mongoose Optimization Algorithm (Local escape Dwarf Mongoose Optimization Algorithm, LDMOA). This method addresses the significant prediction errors of conventional ELM models and enhances prediction accuracy. The enhancements to the Dwarf Mongoose Optimization Algorithm include three key modifications: initially, a dynamic backward learning strategy is integrated at the early stages of the algorithm to augment its global search capabilities. Subsequently, a cosine algorithm is employed to locate new food sources, thereby expanding the search scope and avoiding local optima. Lastly, a “madness factor” is added when identifying new sleeping burrows to further widen the search area and effectively circumvent local optima. Comparative analyses using benchmark functions demonstrate the improved algorithm’s superior convergence and stability. In this study, the LDMOA algorithm optimizes the weights and thresholds of the ELM to establish the LDMOA-ELM prediction model. Experimental forecasts utilizing data from China’s 2016 “The Electrician Mathematical Contest in Modeling” demonstrate that the LDMOA-ELM model significantly outperforms the original ELM model in terms of prediction error and accuracy.