Power System Risk Specified Operational Scenario Generation Based on Conditional Generative Adversarial Networks

The large-scale integration of renewable energy has reduced power system flexibility and exacerbated supply–demand imbalances. In industrial parks, the combined variability of high energy-consuming industrial loads and photovoltaic (PV) generation further complicates the energy management challenge. Aiming to enhance the operational flexibility of industrial parks and mitigate supply–demand imbalances, this paper proposes a multi-time-scale stochastic energy management strategy that accounts for the uncertainty associated with PV generation. First, a conditional generative adversarial network (CGAN) is employed to generate the representative PV generation scenarios, thereby enabling the modeling of PV generation uncertainty within the optimal dispatch model. Considering the coupling mechanisms and control characteristics of various regulation resources within the industrial park, a multi-time-scale dispatch model is developed. In the day-ahead dispatch phase, the operational costs are minimized by optimizing the production plans of industrial loads. In contrast, in the intraday phase, the more flexible measures, such as adjusting the tap positions of arc furnaces and controlling the charge/discharge of energy storage systems, are employed to smooth power fluctuations within the park. A case study validated the effectiveness of the proposed approach, demonstrating a 7.56% reduction in power fluctuations and a 4.34% decrease in daily operating costs. These results highlight the significance of leveraging industrial loads in park-level systems to enhance cost efficiency and renewable energy integration.

A novel capacity demand analysis method of energy storage system for peak shaving based on data-driven

Insurance companies have faced significant losses due to increasingly severe natural disasters, prompting a shift in their approach to extreme risks. To turn these risks into opportunities, it is essential to assess regional insurance risks. This study developed an Insurance Risk Index (IRI) Model using data from 20 regions based on six indicators, incorporating Analysis of Hierarchy Process (AHP), Entropy Weighting Method (EWM), and K-Means clustering. The model categorizes regions into three risk levels: Class I (low), Class II (medium), and Class III (high). Tokyo and California were selected for validation, with IRIs of 0.38 and 0.75, respectively, classifying Tokyo as low risk (Class I) and California as high risk (Class III). Additionally, the study combined the IRI with local economic and population data to assist communities and realtors in making informed decisions on building and development.

To optimize the dispatch and operation control of high proportion renewable energy power system, it is necessary to accurately quantify and evaluate the operational risk of system. For the high proportion renewable energy power system with uncertain wind and light sources, this paper presents a operational risk assessment method of wind and water systems based on probability assessment. By analyzing the distribution of uncertainty probability of system, the state probability is expressed as wind power output probability, solar output probability, transmission line probability and real-time state probability of system components. Use the analytic hierarchy process to assign weight to each type of risk indicators to solve the importance matching problem of different types of risk. On this basis, a operational risk assessment model is built by using Monte Carlo method which is used to select the real-time system states. Finally, an example is analyzed based on the actual power grid in a certain area, and calculation results show that the proposed quantitative calculation method for operational risk assessment of wind, solar and water multi-energy power systems can effectively evaluate the actual operation risk of system and meet the risk assessment requirements of high proportion renewable energy power system.

The robust appraisal of exploration drilling concepts is essential for establishing the economic viability of a prospective recovery field. This study evaluates the different concept selection methods that were considered for drilling operations at the Trym field in Norway. The construction of drilling rigs is a capital-intensive process, and it involves high levels of economic risk. These risks can be broadly categorised as aleatoric (i.e. those related to chance) and epistemic (i.e. those related to knowledge). Evaluating risks in the investment appraisal process tends to be a complicated process. Project risks are evaluated using Monte Carlo simulation (MCS) and are based on the fuzzy analytic hierarchy process (AHP). MCS provides a useful means of evaluating variabilities (i.e. aleatoric risks) in oil drilling operations. However, many of the economic risks in oil drilling processes are unanticipated, and, in some cases, are not readily expressible in quantitative values. The fuzzy AHP is therefore used to appraise the qualitatively defined indirect revenues comprising risks that affect future flexibilities, schedule certainty and health and safety performance. Both the Monte Carlo technique and the fuzzy AHP technique found that a cumulative revenue variation of up to 30% is possible in any of the considered drilling options. The fuzzy AHP technique estimates that the chances of profitability being less than NOK 1 billion over a five-year period is 0.5%, while the Monte Carlo technique estimates suggest a more conservative proportion of 10%. Overall, the fuzzy AHP technique is easy to use and flexible, and it demonstrates increased robustness and improved predictability.

This study introduces a new method for calculating operational risk levels in selecting audit units at the Central Bureau of Statistics (BPS). The key novelty of this study lies in its two-level assessment framework, which systematically compares different risk calculation methods to determine the most effective approach for operational risk evaluation. Using exploratory factor analysis, the study identifies four key operational risk factors: operational costs, internal control, investment and guarantees, and financial performance. The analytic hierarchy process (AHP) is then applied to systematically assign weight scores to these factors and their corresponding subcriteria based on expert judgment. Integrating these approaches results in a more structured, comprehensive, and accurate risk assessment model. Compared with the previous method, this new method shows a narrower but more optimal risk-level range, a slightly higher average operational risk level, and fewer cases of underestimation or overestimation. This new method enhances the precision of risk assessment in selecting BPS audit units, enabling the internal audit team to allocate resources more effectively by prioritizing high-risk work units. Consequently, the overall efficiency and effectiveness of BPS's internal audit process improved.

Many evaluation problems in product scheme design belong to multi-person, multi-level and multi-objective comprehensive evaluation problems. At present, the analytic hierarchy process (AHP) is widely used in the evaluation of complex product design scheme. In the establishment of judgment matrix, experts compare the value of each evaluation index and give them scores, with strong subjective factors. And another commonly used method of determining the weight -- the entropy weight method is to determine the objective weight according to the size of the index variance. According to the characteristics of complex product scheme evaluation and the actual needs, this paper will establish the decision-making model with the AHP method and entropy method, realizing the comprehensive evaluation of the scheme of complex products.

Light pollution is a serious and growing problem worldwide. How to develop a widely applicable light pollution indicator analysis model to help people monitor and mitigate light pollution is a question worthy of our consideration. This paper uses the TOPSIS integrated evaluation and decision method based on Entropy Weight Method (EWM) and Analytic Hierarchy Process (AHP) to identify indicators and establish a widely applicable LPI (Light Pollution Index) analyze Model for the global light pollution problem. Then this model is used for analyzing specific differentiated areas and develop optimal intervention strategies. In order to build an accurate model to assess global light pollution hazard levels, this paper have to take three key aspects into account: Light Trespass, Glare, Spill Light. For each aspect, six to eight sub-indicators were selected to measure different aspects of light pollution. This paper evaluated all indicators and by combining EWM and AHP, this paper obtained a Light Pollution Index Analyze Model. To verify the rationality and reliability of this model, this paper uses TOPSIS integrated evaluation and decision method based on EWM to predict and rank 20 countries worldwide in terms of light pollution risk index. The results show that comparing our data with monitoring data of Light Pollution Map, the two rankings show a high degree of agreement. Therefore, the model of this paper is reasonable and reliable. And the research of this paper can provide effective help to the research and monitoring of light pollution.

In this study, potential quality markers(Q-markers) of Schisandrae Chinensis Fructus for treating bronchial asthma were predicted based on analytic hierarchy process(AHP), entropy weight method(EWM), fingerprint, and network pharmacology. AHPEWM was employed to quantitatively identify the Q-markers of Schisandrae Chinensis Fructus. AHP was used to weight the primary indicators(effectiveness, measurability, and specificity), while EWM was employed to analyze the secondary indicators of each primer indicator. Further, through fingerprint combined with network pharmacology, a ″component-target-pathway″ network was constructed to screen the components of Schisandrae Chinensis Fructus for treating bronchial asthma. It was finally determined that schisandrol A,schisandrin A, and schisandrin B were potential Q-markers of Schisandrae Chinensis Fructus in the treatment of bronchial asthma. This study is the first to comprehensively use AHP-EWM, fingerprint, and network pharmacology to screen the key Q-markers of Schisandrae Chinensis Fructus in the treatment of bronchial asthma. This study provides a scientific basis for improving the quality standard of Schisandrae Chinensis Fructus and lays a foundation for studying its material basis in treating bronchial asthma.

In order to study the fracture ability classification of rock mass under the cracking action of supercritical CO2 phase transition, based on the classification theory of rock mass in blasting engineering, an analytic hierarchy process (AHP)-entropy weight method (EWM) and the cloud model classification method for rock mass cracking under CO2 phase transformation are proposed. In this method, rock density, rock tensile strength, rock wave impedance, and rock mass integrity coefficient are used as the factors to determine the level of rock mass fracturing, and the evaluation index system of rock mass fracturing is established. Through this evaluation method, the rock mass in a reconstruction project section of Nyingchi, Tibet, is classified and evaluated. The results present that this new classification method of rock mass fracture ability uses AHP–EWM to carry out the weight distribution of the classification index. In addition, it is combined with the cloud model for the classification division, overcoming the traditional classification method fixed with appraisal pattern flaw. Therefore, it has validity and feasibility. According to the characteristics of fracture ability, the rock masses in the area to be rebuilt on the Tibet Highway are divided into grade II, grade III, and grade IV, which provides scientific guidance for the construction of the project.

Generation of realistic scenarios is an important prerequisite for analyzing the reliability of renewable-rich power systems. This paper satisfies this need by presenting an end-to-end model-free approach for creating representative power system scenarios on a seasonal basis. A conditional recurrent generative adversarial network serves as the main engine for scenario generation. Compared to prior scenario generation models that treated the variables independently or focused on short-term forecasting, the proposed implicit generative model effectively captures the cross-correlations that exist between the variables considering long-term planning. The validity of the scenarios generated using the proposed approach is demonstrated through extensive statistical evaluation and investigation of end-application results. It is shown that analysis of abnormal scenarios, which is more critical for power system resource planning, benefits the most from cross-correlated scenario generation.

Wind and photovoltaic (PV) power outputs are highly dependent on meteorological factors, leading to significant variability that introduces uncertainty into power system operation and planning. The existing scenario generation methods for renewable energy that incorporate meteorological information typically employ a static correlation scheme, in which meteorological data are concatenated with noise vectors only at the input layer. However, meteorological signals tend to degrade as they propagate through the network, which obscures the dynamic relationship between weather conditions and wind-PV power generation. To address this limitation, this paper proposes a scenario generation scheme for wind and PV power based on an improved Wasserstein generative adversarial network with gradient penalty (WGAN-GP). The proposed architecture integrates feature-wise linear modulation (FiLM) with bidirectional gated recurrent units (GRUs). Specifically, the affine transformation parameters are dynamically generated from meteorological inputs and applied to modulate features across multiple layers of the generator at each time step, thereby enabling explicit modeling of the dynamic correlation between meteorological conditions and renewable power output. Case studies demonstrate that the proposed scheme effectively captures the dynamic dependency between wind-PV power and meteorological factors.

The growing integration of renewable energy into power systems is accompanied by significant output variability due to meteorological fluctuations. Conventional scenario generation approaches often depend on predefined distributions and exhibit limited diversity. To address these limitations, a day-ahead scenario generation framework is proposed based on a Conditional Generative Adversarial Network (CGAN), incorporating Wasserstein distance and gradient penalty for enhanced stability. A multilayer perceptron processes multidimensional weather inputs—including irradiance, temperature, and wind speed—enabling dynamic control without one-hot encoding. By fusing forecast data with high-dimensional noise, the generator learns the conditional distribution of renewable output through adversarial training. Validation on the GEFCom2014 dataset shows improved modeling of temporal dynamics, uncertainty representation, and scenario variety, yielding physically plausible and statistically sound outputs for robust power system scheduling.

Security constrained generation scheduling for grids incorporating wind, photovoltaic and thermal power

It is an important requirement for the operators to control the power grid to evaluate the operation performance of the smart power distribution network reasonably and accurately. This paper from the perspective of the smart grid efficiency, effect and benefit, build up a set of evaluation index of the performance of the smart grid distribution network state system. First, through the expert method, experts from the perspective of three index system screen the center index and the non-central index, next using the improved fuzzy clustering method to correct the center index and the non-central index again, and then using the analytic hierarchy process (AHP) to improve the group gray correlation method to correct the rest of the center again and eliminate redundant indicators. The mixed weight obtained by analytic hierarchy process and entropy weight method is used to evaluate the final determined evaluation system. Finally, an example of a regional power grid is used to verify that the evaluation system and method proposed in this paper can easily and accurately reflect the smart power grid efficiency status.