Search

With the emergence of precision medicine, estimating optimal individualized decision rules (IDRs) has attracted tremendous attention in many scientific areas. Most existing literature has focused on finding optimal IDRs that can maximize the expected outcome for each individual. Motivated by complex individualized decision making procedures and the popular conditional value at risk (CVaR) measure, we propose a new robust criterion to estimate optimal IDRs in order to control the average lower tail of the individuals' outcomes. In addition to improving the individualized expected outcome, our proposed criterion takes risks into consideration, and thus the resulting IDRs can prevent adverse events. The optimal IDR under our criterion can be interpreted as the decision rule that maximizes the "worst-case" scenario of the individualized outcome when the underlying distribution is perturbed within a constrained set. An efficient non-convex optimization algorithm is proposed with convergence guarantees. We investigate theoretical properties for our estimated optimal IDRs under the proposed criterion such as consistency and finite sample error bounds. Simulation studies and a real data application are used to further demonstrate the robust performance of our methods. Several extensions of the proposed method are also discussed. for this article are available online. [ABSTRACT FROM AUTHOR]

This study investigates the properties of risk measure, value at risk (VaR) and conditional VaR (CVaR), using high-frequency Bitcoin data. These data allow us to conduct a high statistical analysis. Our findings reveal a disparity in VaR and CVaR values between the left and right tails of the return probability distributions. We refer to this disparity as "long–short asymmetry". In the high-frequency domain, the tail distribution can be accurately described by a power-law function. Moreover, the ratio of CVaR to VaR is expected to be determined solely by the power-law exponent. Through empirical analysis, we confirm that this ratio property holds true for high confidence levels. Furthermore, we investigate the relationship between risk measures (VaR and CVaR) and realized volatility. We observe that they trace a trajectory in a two-dimensional plane. This trajectory changes gradually, indicating periods of both high and low risk. [ABSTRACT FROM AUTHOR]

The existing distribution system planning methods do not fully consider improving power supply capacity and reliability through the coordination of multiple planning factors, and they are not comprehensive enough in quantifying planning risks. Therefore, this paper proposes a collaborative planning method for sources and networks that considers risk measurement. A multi-layer planning model is first constructed that includes a grid planning layer, a power planning layer, a switch planning layer, and an operation optimization layer. In the model, a risk measurement method combining opportunity constraints and conditional value-at-risk objectives is used to comprehensively assess the risk of the node voltage and branch current exceeding the limit caused by load uncertainty. Then, a solution strategy based on a genetic algorithm and a sparrow search algorithm is proposed to coordinate the contradiction between the solution time and the accuracy of the multi-layer model. Finally, taking a planned area to be expanded as an example, the results show that compared to the existing collaborative planning methods for sources and networks, the proposed method in this paper reduces the planning risks caused by load uncertainty by more than 50% and increases the annual net income of the power distribution company and the DG operators by RMB 1.5 million and RMB 1.1 million, respectively. [ABSTRACT FROM AUTHOR]

In this article, we explore multiscale extreme risk interdependence between four soft agricultural markets – coffee, cocoa, cotton and orange juice. Wavelet correlation and cross-correlation are used to investigate this interlink, and dynamic conditional Value at Risk is used to measure extreme risk. Wavelet correlation results suggest a very weak connection between the markets in the short-term and midterm horizons, which means that investors who operate in the short term or midterm do not have to apply hedging measures against extreme risk. However, the situation is different in the long term, where relatively high correlations are found on the highest wavelet scale in all pairs, except coffee–cocoa. Complementary cross-correlation analysis indicates a lead–lag relationship between the markets. The results are mostly in line with expectations, as bigger markets lead smaller markets. Only in the cases of cocoa–cotton and cocoa–orange juice does the opposite happen. [ABSTRACT FROM AUTHOR]

Because the average treatment effect (ATE) measures the change in social welfare, even if positive, there is a risk of negative effect on, say, some 10% of the population. Assessing such risk is difficult, however, because any one individual treatment effect (ITE) is never observed, so the 10% worst-affected cannot be identified, whereas distributional treatment effects only compare the first deciles within each treatment group, which does not correspond to any 10% subpopulation. In this paper, we consider how to nonetheless assess this important risk measure, formalized as the conditional value at risk (CVaR) of the ITE distribution. We leverage the availability of pretreatment covariates and characterize the tightest possible upper and lower bounds on ITE-CVaR given by the covariate-conditional average treatment effect (CATE) function. We then proceed to study how to estimate these bounds efficiently from data and construct confidence intervals. This is challenging even in randomized experiments as it requires understanding the distribution of the unknown CATE function, which can be very complex if we use rich covariates to best control for heterogeneity. We develop a debiasing method that overcomes this and prove it enjoys favorable statistical properties even when CATE and other nuisances are estimated by black box machine learning or even inconsistently. Studying a hypothetical change to French job search counseling services, our bounds and inference demonstrate a small social benefit entails a negative impact on a substantial subpopulation. This paper was accepted by J. George Shanthikumar, data science. Funding: This work was supported by the Division of Information and Intelligent Systems [Grant 1939704]. Supplemental Material: The data files and online appendices are available at https://doi.org/10.1287/mnsc.2023.4819. [ABSTRACT FROM AUTHOR]

Copyright of Electric Power Automation Equipment / Dianli Zidonghua Shebei is the property of Electric Power Automation Equipment Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Summary: We deal with a multivariate conditional value at risk. Compared with the usual notion for the single random variable, a multivariate value at risk is concerned with several variables, and thus, the relation between each risk factor should be considered. We here introduce a new definition of copula‐based conditional value at risk, which is real valued and ready to be computed. Copulas are known to provide a flexible method for handling a possible nonlinear structure; therefore, copulas may be naturally involved in the theory of value at risk. We derive a formula of our copula‐based conditional value at risk in the case of Archimedean copulas, whose effectiveness is shown by examples. Numerical studies are also carried out with real data, which can be verified with analytical results. [ABSTRACT FROM AUTHOR]

Abstract We propose a new model formulation for a three-echelon supply network design problem incorporating the concept of relocatable modular capacities. A robust supply network configuration must be determined based on uncertain demand. Furthermore, by incorporating the conditional value at risk (CVaR), the risk induced by uncertain demand is explicitly considered. The derived supply network configuration should maximize the weighted sum of the expected net present value and the CVaR. The resulting nonlinear model formulation is approximated by a piecewise linearization. Our numerical investigation shows that the derived supply network configuration is robust and stable in the presence of uncertain demand.

As an emerging network paradigm, the space–air–ground integrated network (SAGIN) has garnered attention from academia and industry. That is because SAGIN can implement seamless global coverage and connections among electronic devices in space, air, and ground spaces. Additionally, the shortage of computing and storage resources in mobile devices greatly impacts the quality of experiences for intelligent applications. Hence, we plan to integrate SAGIN as an abundant resource pool into mobile edge computing environments (MECs). To facilitate efficient processing, we need to solve the optimal task offloading decisions. In contrast to existing MEC task offloading solutions, we have to face some new challenges, such as the fluctuation of processing capabilities for edge computing nodes, the uncertainty of transmission latency caused by heterogeneous network protocols, the uncertain amount of uploaded tasks during a period, and so on. In this paper, we first describe the task offloading decision problem in environments characterized by these new challenges. However, we cannot use standard robust optimization and stochastic optimization methods to obtain optimal results under uncertain network environments. In this paper, we propose the 'condition value at risk-aware distributionally robust optimization' algorithm for task offloading, denoted as RADROO, to solve the task offloading decision problem. RADROO combines the distributionally robust optimization and the condition value at risk model to achieve optimal results. We evaluated our approach in simulated SAGIN environments, considering confidence intervals, the number of mobile task offloading instances, and various parameters. We compare our proposed RADROO algorithm with state-of-the-art algorithms, such as the standard robust optimization algorithm, the stochastic optimization algorithm, the DRO algorithm, and the Brute algorithm. The experimental results show that RADROO can achieve a sub-optimal mobile task offloading decision. Overall, RADROO is more robust than others to the new challenges mentioned above in SAGIN. [ABSTRACT FROM AUTHOR]

The continuing evolution of insurance and banking regulation has raised interest in the calibration of different risk measures associated with suitable confidence levels. In particular, Li and Wang (2019) have introduced a probability equivalent level (called PELVE) for the replacement of Value at Risk (VaR) with Conditional Value at Risk (CVaR). Extending their work, we propose two generalizations of PELVE that combine useful theoretical properties with empirical benefits in risk analysis. The former, termed d-PELVE, establishes a correspondence between VaR and suitably parameterized distortion risk measures. The latter, termed g-PELVE, iterates the construction of CVaR starting from VaR to a general coherent risk measure. We state conditions for the existence and uniqueness of the proposed measures and derive additional properties for specific classes of underlying risk functionals. A study of Generalized Pareto Distributions reveals an interesting correspondence between PELVE and g-PELVE, and explores their relationship with the tail index. An empirical application illustrates the usefulness of (g-)PELVE in characterizing tail behavior not only for individual asset returns, but also for possible portfolio combinations. [ABSTRACT FROM AUTHOR]

Wind energy is a clean, renewable and green energy. Compared to land-based wind power, offshore wind power does not occupy land resources. Meanwhile offshore wind resources is much richer and its wind direction is more stable. Meteorological hazards have a major impact on offshore wind facilities. Typhoons, lightning, rainstorms and other meteorological hazards that occur during operation can not only cause fatal damage to offshore wind facilities, but often also trigger a chain reaction of marine hazards, making them more difficult to maintain. In this paper, we analyze the impact of various types of meteorological hazards on offshore wind facilities with examples and select the most important ones. A comprehensive risk assessment model CVAR for offshore wind projects is developed in combination with other types of risk elements to predict the damaging of offshore wind facilities so that managers can respond in a timely manner. In addition, A nonlinear stepwise regression (NLSR) approach is then used to forecast the meteorological elements in offshore grid facilities. [ABSTRACT FROM AUTHOR]

Maritime shipping is an important driver of global economic growth. Efficient green maritime technologies are critical for both the profitability and sustainability of shipping carriers due to the fact that fuel consumption has already made up 45–55% of the total operational cost of a ship. Moreover, the application of green maritime technologies also challenges the input/output of the maritime industry. Currently, there is a lack of coordination between the two strategies of maritime bunker management: one is the bunker procurement, which is faced with the fierce volatility of bunker fuel prices, and the other is the bunker consumption of vessel operation scheduling with applicable maritime technologies. To address the challenge posed by the new sulfur emission regulations, the two isolated strategies are inefficient. This study presents an integrated model that takes both the financial technology (bunker hedging) and the operational bunker cost efficiency (sailing speed and routing optimization under emission regulations) into account. The objective is to maximize the total rate of portfolio return considering the revenue and the cost simultaneously. By analyzing the Conditional Value at Risk (CVaR) risk measure, we examined the effects of the bunker spot, contract, and hedging in futures markets on the optimal joint solution. Numerical results from a real-world case study show that the optimized integrating financial and operational strategies yield the lowest expected total costs as well as the highest revenue with CVaR constraints. The findings provide a prospect for maritime shipping as an effective decision tool for bunker management under environmental regulations. The management insights of our study will benefit the corporate participants, policy makers, and researchers in liner shipping revenue and risk management. [ABSTRACT FROM AUTHOR]

The complexity and uncertainty of construction projects contribute to low efficiency in the construction industry. This research applied the Takt-time planning method to optimize the construction working process, and proposed a risk control framework based on Value at Risk (VaR) and Conditional Value at Risk (CVaR) approaches to explore and predict a project schedule and cost performance under different scenarios. This research selected a high-rise residential building project for a case study and collected 1672 productivity data samples. Arena Simulation models were established based on 90 combinations of labor assignments to assess Takt-time planning strategies’ impact on project performance in four scenarios. The VaR and CVaR evaluations at 75% and 90% confidence levels were compared to balance project benefits and risks. Without any overtime or additional workers, this research found a Takt-time planning method that can reduce the project duration by 20.2% and labor costs by 2.1% at the same time, using a labor assignment of 12 bar placers, 12 carpenters, and 5 pipefitters. The findings can assist construction managers to achieve a shorter duration, reduced cost, and safer work environment, which will be very effective and beneficial to improve project overall performance.

This paper aims to provide the best approach to optimize the multi-asset portfolio of five asset classes including cryptocurrencies, foreign currencies, gold, stock and investment funds in three groups of fixed income investment funds, stock investment funds and Mutual investment funds. Purposely, the mean-value at risk and mean-conditional value at risk models have been developed and solved using the artificial bee colony algorithm. The performance of the value at risk based models is compared with the mean-variance, mean-semi variance and mean–absolute deviation models. Also, the profitability of the models is evaluated in the presence of three real world constrains, i.e. quantity constrains, class constrains and the both. Our investigation time period is from August 2015 to December 2020. The in-sample and out-of-sample results showed that the conditional value at risk model outperforms the other models, whether in the presence of constraints or not. Also, the artificial bee colony algorithm was superior to the imperialist competitive and particle swarm optimization algorithms in multi asset portfolio management, based on Sharpe, conditional Sharpe and return on risk ratios.

We propose a new model formulation for a three-echelon supply network design problem incorporating the concept of relocatable modular capacities. A robust supply network configuration must be determined based on uncertain demand. Furthermore, by incorporating the conditional value at risk (CVaR), the risk induced by uncertain demand is explicitly considered. The derived supply network configuration should maximize the weighted sum of the expected net present value and the CVaR. The resulting nonlinear model formulation is approximated by a piecewise linearization. Our numerical investigation shows that the derived supply network configuration is robust and stable in the presence of uncertain demand. [ABSTRACT FROM AUTHOR]

For the treatment of outliers, the paper "Risk-Based Robust Statistical Learning by Stochastic Difference-of-Convex Value-Function Optimization" by Junyi Liu and Jong-Shi Pang proposes a risk-based robust statistical learning model. Employing a variant of the conditional value-at-risk risk measure, called the interval conditional value-at-risk (In-CVaR), the model aims to exclude the risks associated with the left and right tails of the loss. The resulting nonsmooth and nonconvex model considers the population In-CVaR risk and distinguishes the upside and downside losses with asymmetric weights. For the solution of the model in both regression and classification, the authors show that the objective function is the difference of two convex functions each being the optimal objective value of a univariate convex stochastic program. A sampling and convex programming-based algorithm is developed with the appropriate control of incremental sample sizes, and its subsequential almost-sure convergence to a critical point is established. Numerical results illustrate the practical performance of the model and methodology. This paper proposes the use of a variant of the conditional value-at-risk (CVaR) risk measure, called the interval conditional value-at-risk (In-CVaR), for the treatment of outliers in statistical learning by excluding the risks associated with the left and right tails of the loss. The risk-based robust learning task is to minimize the In-CVaR risk measure of a random functional that is the composite of a piecewise affine loss function with a potentially nonsmooth difference-of-convex statistical learning model. With the optimization formula of CVaR, the objective function of the minimization problem is the difference of two convex functions each being the optimal objective value of a univariate convex stochastic program. An algorithm that combines sequential sampling and convexification is developed, and its subsequential almost-sure convergence to a critical point is established. Numerical experiments demonstrate the effectiveness of the In-CVaR–based estimator computed by the sampling-based algorithm for robust regression and classification. Overall, this research extends the traditional approaches for treating outliers by allowing nonsmooth and nonconvex statistical learning models, employing a population risk-based objective, and applying a sampling-based algorithm with the stationarity guarantee for solving the resulting nonconvex and nonsmooth stochastic program. Funding: The first author's research is partially supported by the National Science Foundation of China [Grant 72188101]. This work was also based on research supported by the National Science Foundation [Grant IIS-1632971] and the Air Force Office of Scientific Research [Grant FA9550-18-1-0382]. [ABSTRACT FROM AUTHOR]

Conditional value at risk (CVaR) is widely used to account for the preferences of a risk-averse agent in extreme loss scenarios. To study the effectiveness of randomization in interdiction problems with an interdictor that is both risk- and ambiguity-averse, we introduce a distributionally robust maximum flow network interdiction problem in which the interdictor randomizes over the feasible interdiction plans in order to minimize the worst case CVaR of the maximum flow with respect to both the unknown distribution of the capacity of the arcs and the interdictor's own randomized strategy. Using the size of the uncertainty set, we control the degree of conservatism in the model and reformulate the interdictor's distributionally robust optimization problem as a bilinear optimization problem. For solving this problem to any given optimality level, we devise a spatial branch-and-bound algorithm that uses the McCormick inequalities and reduced reformulation linearization technique to obtain a convex relaxation of the problem. We also develop a column-generation algorithm to identify the optimal support of the convex relaxation, which is then used in the coordinate descent algorithm to determine the upper bounds. The efficiency and convergence of the spatial branch-and-bound algorithm is established in numerical experiments. Further, our numerical experiments show that randomized strategies can have significantly better performance than optimal deterministic ones. History: Accepted by David Alderson, Area Editor for Network Optimization: Algorithms & Applications. Funding: The first author's research is supported by a Group for Research in Decision Analysis postdoctoral fellowship and Fonds de Recherche du Québec–Nature et Technologies postdoctoral research scholarship [Grants 275296 and 301065]. The second author acknowledges support from the Canadian Natural Sciences and Engineering Research Council and the Canada Research Chair program [Grants RGPIN-2016-05208, 492997-2016, and 950-230057]. Supplemental Material: The e-companion is available at https://doi.org/10.1287/ijoc.2022.1257. The data file and codes are posted on GitHub (https://github.com/Utsav19/Value-of-Randomization). [ABSTRACT FROM AUTHOR]

Since the change of conditional value at risk (CVaR) in different confidence levels is very effective in portfolio optimization, the meta-Malmquist index (MMI) is utilized. For this purpose, mean-CVaR models by MMI in the presence of negative data are introduced. Like Markowitz theory in mean)variance framework, we use CVaR as a risk measure and propose our models without considering the skewness and kurtosis of assets return. In our study there are some negative data, so our models is based on Range Directional Measure (RDM) model that can be taken positive and negative data. In this paper efficiencies are obtained in all confidence levels by mean-CVaR models and MMI is calculated on confidence levels as periods in the presence of negative data. This method could help the investors to construct their profitable portfolio by using MMI index. We, also carry out an empirical study within Iran stock exchange market. [ABSTRACT FROM AUTHOR]

We present a polynomial-time online algorithm for maximizing the conditional value at risk (CVaR) of a monotone stochastic submodular function. Given T i.i.d. samples from an underlying distribution arriving online, our algorithm produces a sequence of solutions that converges to a ( 1 - 1 / e )-approximate solution with a convergence rate of O (T - 1 / 4) for monotone continuous DR-submodular functions. Compared with previous offline algorithms, which require Ω (T) space, our online algorithm only requires O (T) space. We extend our online algorithm to portfolio optimization for monotone submodular set functions under a matroid constraint. Experiments conducted on real-world datasets demonstrate that our algorithm can rapidly achieve CVaRs that are comparable to those obtained by existing offline algorithms. [ABSTRACT FROM AUTHOR]

Objective: To produce a proper reaction when confronted with market uncertainties (booms and busts), before making any investment decisions, investors and financial institutions tend to obtain some level of assurance about the market’s future and also the market’s probable feedback on their performance in the future. This study seeks to identify optimized robust portfolios with the best performance in the face of market uncertainties than can minimize the investors’ regret about their portfolio selection.Methods: To create optimal portfolios, in the study, scenarios pertaining to various market situations based on daily returns of the Tehran Stock Exchange Price Index (TEDPIX) were designed, and the particle swarm optimization algorithm and minimax regret criterion were applied. This study also explored the application of multivariate objective functions and the Omega Conditional Value at Risk ratio as the fitting functions in particle mass optimization. To calculate optimal portfolios, the data from 50 companies on Tehran Stock Exchange (TSE) from 2009 to 2016 were analyzed. Also, the data from the year 2017 were evaluated as out of sample data.Results: Research findings indicated optimized robust portfolios in monthly periods had higher information ratios and lower tracking errors than the benchmark portfolios.Conclusion: Making market scenarios and applying the minimax regret criterion improves the performance of optimized robust portfolios. Additionally, compared with the semi-variance benchmark model, applying the multi-objective function and Omega-Conditional Value at Risk ratio in portfolio optimization leads to improve performance of the robust portfolios.

In the operation optimization of community integrated energy system (CIES), the implementation of integrated demand response (IDR) can guide users to adjust energy consumption behavior, optimize load curve and reduce system operation cost. However, due to different energy users have different preferences and behaviors resulting in uncertain load response. The probabilistic scenario method is used to deal with the uncertainty of load response. The operator of CIES faces the risk of operation cost fluctuation associated with the uncertainty of load response. Then, conditional value at risk (CVaR) is adopted to measure the risk of operation cost fluctuation and control the risk level to minimize the operation cost. A CVaR-based operation optimization method for CIES is proposed to determine the operation strategies under different risk preferences. The case study verifies the effectiveness of the proposed method. The relationship between the economy and risk level of the system under different risk preferences is discussed.

• A day-ahead self-scheduling system was proposed for managing residential loads, a storage system, and renewable/non-renewable resources in the presence of uncertainties in electrical rationing programs and photovoltaic energy generation. • A mixed-integer non-linear programming model was developed to solve the risk-constrained self-scheduling problem of residential loads, aiming to reduce the expected operational cost and minimize the utilization of the diesel generator and energy storage system in the electrical rationing hours. • The separate and joint effects of demand response and risk management on the smart home energy management were presented. • The effects of demand response and risk management on the worst-case scenario cost under different electrical rationing scenarios were discussed. • A gas-based heating and cooling system was Integrated into the proposed home energy management system, and the effect of this integration on the expected cost was discussed. With the recent global energy crisis, some countries have implemented electrical rationing (ER), making it necessary for smart homes to play a pivotal role in optimizing energy consumption and contributing to sustainable practices. To effectively manage smart home consumption, a stochastic programming approach for a grid-connected smart home energy management system (SHEMS) is proposed in this paper. The system includes PV, battery, diesel, and gas-based heating/cooling systems (HCS). Additionally, a demand response program (DRP) has been employed under time-of-use tariffs in the Syrian energy market. The main objective is to minimize the day-ahead expected cost and consumer discomfort by optimizing the operation of dispatchable units and loads. To manage the risks associated with the expected cost due to potential uncertainties in PV energy generation and electrical rationing programs, the conditional value-at-risk (CVaR) approach is adopted. Two methods are proposed to model the uncertainty in PV energy generation; interval bands and interval-based scenarios. The problem is modeled as a mixed-integer non-linear programming (MINLP) model, and coded in GAMS to test different cases. Based on the results obtained, substantial reductions reached 56.2% in worst-case cost scenarios when employing concurrent DRP-risk management. [ABSTRACT FROM AUTHOR]

In this paper, we address the chance-constrained safe Reinforcement Learning (RL) problem using the function approximators based on Stochastic Model Predictive Control (SMPC) and Distributionally Robust Model Predictive Control (DRMPC). We use Conditional Value at Risk (CVaR) to measure the probability of constraint violation and safety. In order to provide a safe policy by construction, we first propose using parameterized nonlinear DRMPC at each time step. DRMPC optimizes a finite-horizon cost function subject to the worst-case constraint violation in an ambiguity set. We use a statistical ball around the empirical distribution with a radius measured by the Wasserstein metric as the ambiguity set. Unlike the sample average approximation SMPC, DRMPC provides a probabilistic guarantee of the out-of-sample risk and requires lower samples from the disturbance. Then the Q-learning method is used to optimize the parameters in the DRMPC to achieve the best closed-loop performance. Wheeled Mobile Robot (WMR) path planning with obstacle avoidance will be considered to illustrate the efficiency of the proposed method.

As a step towards establishing reliable broadcast wireless local area networks (WLANs), this paper proposes acknowledgement (ACK)-less rate adaptation to alleviate reception failures at broadcast recipient stations (STAs) using distributional reinforcement learning (RL). The key point of this study is that the algorithms for learning the strategy of ACK-less rate adaptation are evaluated in terms of the broadcast performance, which is composed of the data rate of the broadcast access point (AP) and the reception success rate at the recipient STAs. ACK-less rate adaptation framework was realized using the received signal strength (RSS) of the uplink frames transmitted by the non-broadcast STAs to the non-broadcast APs, which correlated with the broadcast performance with a confounding effect from the deployment of the broadcast recipient STAs. However, this rate adaptation framework has the problem that it incurs the reception failures at a part of the broadcast recipient STAs, because deep Q-learning used in the previous framework cannot deal with the wide distribution of the broadcast performance. To address this challenge, this paper further discusses the rate adaptation using distributional RL, which approximates the entire distribution of the broadcast performance. The simulations confirmed the following: 1) Using the expected broadcast performance learned by deep Q-learning improved the performance in terms of the Pareto efficiency. 2) Learning the entire distribution of the broadcast performance enabled the broadcast AP to determine the tail of the distribution using risk measure, and to alleviate reception failures while implementing the rate adaptation in the same way as the method that learns only expected broadcast performance.

In order to reveal the leading role of the securities dealers sector in the overall stock market volatility, based on the risk measure theory, this paper uses both the theoretical analysis and empirical testing measures in testing risk correlation between the securities dealers sector and the overall stock market by constructing the Copula-GARCH-CoVaR model. The results show that the securities dealers sector and the overall stock market have a significant risk spillover effect, but it shows that there is an asymmetric leading effect in the process of stock market rise and fall. Asymmetric information shocks easily lead to systemic risk. The research conclusions can provide a basis for the regulatory authorities to take effective countermeasures for the stock market. [ABSTRACT FROM AUTHOR]

This study took online lending as the main research object to quantitatively measure FinTech risk in China. A theoretical model was built to analyse the relationship between the assets and liabilities of peer-to-peer platforms and the risk of the entire online lending industry. The conditional value at risk method was used to measure the risk spillover effect of the online lending industry and the different types of platforms. Index smoothing and moving average were used to examine risk contagion. When the risk rate of the portfolio of the platform generally increases, the systemic risk of the whole industry also increases, and if the systemic risk of the industry spreads to the portfolio of the platform, it could affect the stability of the capital flow of the platform, and then affect the risk expectation of the platform itself. Most platforms with risk concerns were private. Banking platforms and public platforms were greatly affected by market risk; however, their own risks had relatively little impact on the overall market. The greater the market risk, the more platforms become risk platforms, and the smaller the impact on transition platforms. Regulatory sandboxes may be an effective means of preventing and controlling Fintech risks. [ABSTRACT FROM AUTHOR]

Reverse logistics is attracting attention due to the increasing concerns over environmental issues and the important economic impacts. The design of a reverse logistics network is a major strategic problem in the field of reverse logistics. As cost pressures in product returns continue to mount, a growing number of manufacturers have begun to outsource reverse logistics operations to third-party logistics (3PL) providers. On the other hand, considering disruption risks caused by natural or man-made factors in the reverse logistics network design is inevitable. This paper studies third-party reverse logistics network designs under uncertain disruptions. The problem is formulated as a risk-averse two-stage stochastic programming model with a mean risk objective. Two types of risk measures, value at risk (VaR) and conditional value at risk (CVaR), were examined, respectively. Finally, the sensitivity analysis of the model was carried out. The validity of the mean risk criteria is proved by comparison with risk-neutral approach. Moreover, the performance of the proposed model was examined by stochastic measures. [ABSTRACT FROM AUTHOR]

In order to study the two-way risk spillovers between financial and real industries under major public emergencies in the Chinese market from 2007 to 2020, the sample period of major emergencies was determined based on the value at risk (VaR) time series, and it was found that the impact of major emergencies would lead to the rise of systemic risks in the financial industry. Secondly, the real sectors are taken as the main research object to measure the value of systemic risk spillover by using DCC-GARCH, and it shows that the industry with significantly systemic vulnerability from the overall financial risk spillover is the real estate industry, material industry, and energy industry. The results of subdividing financial sectors show that the banking sector has the most significant contribution to financial risk spillover in the real sectors. At the same time, identify the systemically important industries with high spillover risk to the financial industry, namely, utilities, consumer discretionary and industrials. Among the financial sub-industries, the risk spillover to the securities industry from the real sectors is the most significant. Finally, it was found that the system vulnerability and importance characteristics of the real entity industry depend on the nature of events and have certain rules. [ABSTRACT FROM AUTHOR]

One of the most fundamental problems in investment decisions and portfolio optimization is choosing a suitable measure for risk assessment and management. In this study, the performance of the krill herd Algorithm is investigated for solving the mean-value at risk and mean-conditional value at risk portfolio optimization models considering the cardinality constraints, among 35 active companies in Tehran Stock Exchange. For algorithm training, the rolling window method has been used in 2011-2018 and 2012-2019. The Sharpe ratio and the conditional Sharpe ratio of the models have been evaluated and they are compared using the Wilcoxon test. According to the numerical results, the mean-conditional value at risk model outperforms the mean-value at risk model in terms of the rate of return. Also, the model's profitability improved using cardinality constraint with 5 stocks. Based on the empirical studies, we concluded that there is no significant difference between the performance of the value at risk and conditional value at risk based models. Furthermore, the portfolios with lower number of stocks have shown the better performance. [ABSTRACT FROM AUTHOR]

The existing distribution system planning methods do not fully consider improving power supply capacity and reliability through the coordination of multiple planning factors, and they are not comprehensive enough in quantifying planning risks. Therefore, this paper proposes a collaborative planning method for sources and networks that considers risk measurement. A multi-layer planning model is first constructed that includes a grid planning layer, a power planning layer, a switch planning layer, and an operation optimization layer. In the model, a risk measurement method combining opportunity constraints and conditional value-at-risk objectives is used to comprehensively assess the risk of the node voltage and branch current exceeding the limit caused by load uncertainty. Then, a solution strategy based on a genetic algorithm and a sparrow search algorithm is proposed to coordinate the contradiction between the solution time and the accuracy of the multi-layer model. Finally, taking a planned area to be expanded as an example, the results show that compared to the existing collaborative planning methods for sources and networks, the proposed method in this paper reduces the planning risks caused by load uncertainty by more than 50% and increases the annual net income of the power distribution company and the DG operators by RMB 1.5 million and RMB 1.1 million, respectively.

Since the change of conditional value at risk (CVaR) in different confidence levels is very effective in portfolio optimization, the meta-Malmquist index (MMI) is utilized. For this purpose, mean-CVaR models by MMI in the presence of negative data are introduced. Like Markowitz theory in mean-variance framework, we use CVaR as a risk measure and propose our models without considering the skewness and kurtosis of assets return. In our study there are some negative data, so our models is based on Range Directional Measure (RDM) model that can be taken positive and negative data. In this paper efficiencies are obtained in all confidence levels by mean-CVaR models and MMI is calculated on confidence levels as periods in the presence of negative data. This method could help the investors to construct their profitable portfolio by using MMI index. We, also carry out an empirical study within Iran stock exchange market. [ABSTRACT FROM AUTHOR]

Copyright of Electric Drive is the property of Electric Drive Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Recently, renewable power plants utilize clean and sustainable resources for electricity generation. The Ocean Thermal Energy Conversion (OTEC) system uses ocean surface water as a high-temperature source and the water at a depth of the ocean as a low-temperature source. The difference between these temperatures is 20°C or greater, and the working uid with a low boiling point can be used for electricity generation. In a closed-cycle OTEC system, the working uid through a thermodynamic cycle based on the Rankine cycle can rotate the turbine and generate electricity. Due to the ocean surface temperature variation, the output power of the OTEC system changes and yields numerous states concerning the generated power of this plant. Thus, for integrating the OTEC systems with the power system, many aspects of power system including reliability may be affected and thus, new approaches must be developed for investigation of these effects. In this paper, the reliability of the power system containing the OTEC system based on the multi-state reliability model and the conditional value at risk concept is evaluated and the valuable indices used for generation expansion planning of the power system are calculated. [ABSTRACT FROM AUTHOR]

As a new retail model, the front distribution center (FDC) has been recognized as an effective instrument for timely order delivery. However, the high customer demand uncertainty, multi-item order pattern, and limited inventory capacity pose a challenging task for FDC managers to determine the optimal inventory level. To this end, this paper proposes a two-stage distributionally robust (DR) FDC inventory model and an efficient row-and-column generation (RCG) algorithm. The proposed DR model uses a Wasserstein distance-based distributional set to describe the uncertain demand and utilizes a robust conditional value at risk decision criterion to mitigate the risk of distribution ambiguity. The proposed RCG is able to solve the complex max-min-max DR model exactly by repeatedly solving relaxed master problems and feasibility subproblems. We show that the optimal solution of the non-convex feasibility subproblem can be obtained by solving two linear programming problems. Numerical experiments based on real-world data highlight the superior out-of-sample performance of the proposed DR model in comparison with an existing benchmark approach and validate the computational efficiency of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Quota systems play a crucial role in regulating public-interest goods and controlling negative externalities, with a primary focus on social impacts rather than economic benefits. This paper examines the decision-making process for quota release, aiming to control growth rates and ensure price stability over time. We first develop a chance-constrained problem for quota systems, solving it using sample average approximation. Due to computational demands, alternative approximation methods are explored. We consider two types of quota systems: mature systems with known distributions and newly established systems with distributional ambiguity. For mature systems, Conditional Value-at-Risk (CVaR) is used to approximate the chance constraint, while for newly established systems, worst-case CVaR is employed within a robust optimization framework and the binary search algorithm is derived to efficiently solve the problem. The proposed models' effectiveness is validated through computational studies using data from Singapore's Vehicle Quota System. With known distributions, our CVaR sample average approximation (CVaR-SAA) model outperforms traditional models, reducing violation probability by more than 56.32%. With distributional ambiguity, worst-case CVaR approximation robust optimization (WCVaR-RO) model provides superior solutions, particularly in maximum violation probability (MVP). In the most notable case, WCVaR-RO reduces the MVP by over 53.37%. This research offers valuable insights into the management of quota systems. • We introduce a fresh perspective to model the quota system problem, focusing on controlling price fluctuations and quota-increasing rates. • We formulate the quota system management problem as a chance-constrained program, considering two distinct scenarios: known distribution for mature systems with sufficient data and newly established systems with distributional ambiguity. • We develop two methods to approximate the chance constraint with available distributional information: applying the Sample Average Approximation (SAA) method and using Conditional Value-at-Risk (CVaR) as a convex approximation. • We develop a distributionally robust optimization framework that employs worst-case CVaR to approximate the chance constraint in the presence of distributional ambiguity. [ABSTRACT FROM AUTHOR]

• A unified energy market integrates electrical, thermal, and natural gas in day-ahead trades. • ILRP-based trading strategy maximizes integrated energy company revenue and grid security. • Classification of end-user loads enables flexible ILRP use for different energy needs. • Mean-variance CVaR model optimizes trading portfolios, mitigating price uncertainty risks. • CVaR model ensures robust portfolio strategies, enhancing resilience to price fluctuations. The emergence of Integrated Energy Systems (IESs) has shifted energy management from traditional electricity paradigms to a more diverse approach involving electricity, thermal energy, and natural gas. This study introduces a framework for an Integrated Energy Network (IEN) that enables simultaneous trading across these interconnected markets. The objective is to maximize the profitability of integrated energy companies by optimizing energy trading strategies. The proposed business strategy incorporates integrated load response, addressing constraints within electric distribution systems, heating networks, and natural gas pipelines. A three-stage process is used: information sharing in the unified energy market, energy conversion in hubs, and flexible load planning in the retail market. Flexible loads are categorized as displaceable, reducible, or transformable. A Conditional Value-at-Risk (CVaR) mean-variance model addresses market price volatility. Simulations on a test system validate the model, demonstrating its effectiveness in improving profitability and operational efficiency for integrated energy companies. [ABSTRACT FROM AUTHOR]

The accurate measurement and management of energy risk have become important issues of the economic development and energy security for all countries. The existing literature generally adopts the Value at Risk (VaR). However, VaR does not satisfy the subadditivity axiom to measure the energy risk, which makes the calculation defective. In this paper, we use the Conditional VaR (CVaR) with the characteristics of coherent and convex risk measurement to measure energy risk under nonparametric kernel (NPK) framework. We consider how to use the energy derivatives to hedge the price risk of energy so that the result is more reasonable and effective. The empirical results show that the NPK method that we propose is more effective to measure the actual energy risk and carry out more effective risk hedging.

Global supply chains are increasingly exposed to operational and disruption risks that threaten their business continuity. This paper presents a novel two-stage scenario-based mixed stochastic-possibilistic programming model for integrated production and distribution planning problem in a two-echelon supply chain over a midterm horizon under risk. Operational risks are handled by introducing imprecise (i.e. possibilistic) parameters while disruption risks are accounted for through stochastic disruption scenarios. The proposed model accounts for the risk mitigation options and recovery of lost capacities in an integrated manner. In the first stage, the structure of the chain and proactive risk mitigation decisions are determined, while the second stage specifies the recovery plan of lost capacities in addition to production and distribution plans. Considering extra capacities in the production facilities, backup routes for transportation links and pre-positioning of emergency inventory in distribution centres are considered as feasible options to improve the resilience level of the supply chain. We propose a new indicator for optimising the resilience level of the chain based on restoration of lost capacities. For the sake of robustness, the expected worst case of the second stage's objective function is considered by utilising the conditional value at risk (CVaR) measure. The validation and applicability of the proposed model are examined through several numerical experiments. [ABSTRACT FROM AUTHOR]

Objective: Nowadays, the capital market is considered an important source of financing for companies and if a suitable model for portfolio selection by considering different preferences of investors is designed, the existing capital can be directed to this market and support domestic products. This study develops the Markowitz model to consider the non-financial preferences of investors in addition to financial indicators. Methods: Range Adjusted Measure (RAM) and Conditional Value at Risk (CVaR) model on Cross-efficiency were applied respectively to measure the Corporate Social Responsibility (CSR) score and risk, and then the multi-objective portfolio optimization model was proposed using the LP-Metric method. Results: Single-objective and multi-objective models (LP-Metric) with different powers were implemented in GAMS software. Examining the performance of these models using the Sharpe ratio showed that the single-objective models of maximizing returns and minimizing risk have the highest performance and the single-objective model of maximizing social responsibility have the lowest performance, respectively. The proposed model also meets at least 74.5 percent of the triple and contradictory goals according to the Sharpe ratio. Conclusion: While the proposed model optimizes the three objective functions simultaneously and establishing a trade-off between these conflicting goals, has obtained a good Sharpe score compared to other models and market portfolio and a suitable portfolio on a Pareto Front has been selected and introduced among the companies with maximum return and minimum risk that have a high score of social responsibility, and if the model is applied with more powers, it will provide more companies and scenarios to investors.

As an emerging network paradigm, the space–air–ground integrated network (SAGIN) has garnered attention from academia and industry. That is because SAGIN can implement seamless global coverage and connections among electronic devices in space, air, and ground spaces. Additionally, the shortage of computing and storage resources in mobile devices greatly impacts the quality of experiences for intelligent applications. Hence, we plan to integrate SAGIN as an abundant resource pool into mobile edge computing environments (MECs). To facilitate efficient processing, we need to solve the optimal task offloading decisions. In contrast to existing MEC task offloading solutions, we have to face some new challenges, such as the fluctuation of processing capabilities for edge computing nodes, the uncertainty of transmission latency caused by heterogeneous network protocols, the uncertain amount of uploaded tasks during a period, and so on. In this paper, we first describe the task offloading decision problem in environments characterized by these new challenges. However, we cannot use standard robust optimization and stochastic optimization methods to obtain optimal results under uncertain network environments. In this paper, we propose the ‘condition value at risk-aware distributionally robust optimization’ algorithm for task offloading, denoted as RADROO, to solve the task offloading decision problem. RADROO combines the distributionally robust optimization and the condition value at risk model to achieve optimal results. We evaluated our approach in simulated SAGIN environments, considering confidence intervals, the number of mobile task offloading instances, and various parameters. We compare our proposed RADROO algorithm with state-of-the-art algorithms, such as the standard robust optimization algorithm, the stochastic optimization algorithm, the DRO algorithm, and the Brute algorithm. The experimental results show that RADROO can achieve a sub-optimal mobile task offloading decision. Overall, RADROO is more robust than others to the new challenges mentioned above in SAGIN.

• A novel scenario generation method capturing extreme scenarios is proposed. • The correlation between energy prices is modelled by the Frank-Copula function. • A conditional-value-at-risk-based planning method is proposed. • The effectiveness and advantages of the proposed method are validated. The uncertainty and correlation of energy prices pose challenges to the planning and operation of park-level integrated energy systems. Especially, the extreme scenarios in both electricity and natural gas prices would result in significant economic losses, which have not been fully studied in the planning of park-level integrated energy systems. In this regard, this paper proposes a conditional-value-at-risk-based planning method for the park-level integrated energy system that considers both the extreme scenarios of energy prices and the correlation between the electricity price and natural gas price. First, the Gaussian mixture model is used to model the probability distribution function of the electricity price and natural gas price with high accuracy. Then, the Frank-Copula function is adopted to model the correlation between energy prices in different energy markets. Furthermore, a novel scenario generation method preserving extreme scenarios of energy prices is proposed, where extreme price scenarios are identified in the scenario generation process and subsequently preserved in scenario reduction. Finally, a conditional-value-at-risk-based planning model is proposed to optimize the overall investment and operation costs of the park-level integrated energy system, where the operational risks introduced by renewable generation and energy markets are effectively handled by the conditional value at risk. Case studies demonstrate that compared with the model without the consideration of extreme scenarios of energy prices, the potential risk loss of the proposed model is reduced by 3% in the same generated scenarios. The proposed model is more beneficial in enhancing the system's resilience to the risk. [ABSTRACT FROM AUTHOR]

Underfrequency load shedding is the third level protection measure to ensure the safe and stable operation of power systems, which can effectively prevent the rapid decrease in system frequency caused by power system failure. To compensate for the power deficit resulting from faults during the island operation of a microgrid, a two-stage underfrequency load shedding strategy for microgrid groups considering risk avoidance is proposed in this paper. The proposed strategy divides underfrequency load shedding into a fast load shedding stage and a risk avoidance load shedding strategy. The first stage is fast underfrequency load shedding considering the load frequency characteristics and voltage characteristics; the fast underfrequency load shedding in the first stage reduces the fast frequency decrease before the second stage load shedding operation. The second stage of load shedding is risk avoidance under frequent load shedding. The load shedding in this stage accounts for the risk loss caused by the nondeterminacy of the demand side load to the system load shedding while accounting for the load frequency and voltage characteristics. First, the conditional value at risk (CVaR) theory is introduced in this paper to analyze and determine the risk loss caused by load nondeterminacy on load shedding, and the severity of load shedding (SoLS) is adopted as the CVaR value of load shedding. Second, the underfrequency load shedding optimization model is constructed by taking the risk value of the load shedding conditions of the microgrid as the optimization index of load shedding. Finally, the performance of the proposed strategy is verified based on the improved IEEE-37 node system microgrid group model. The results show that the proposed two-stage load shedding strategy can effectively prevent a rapid decrease in system frequency and effectively reduce the risk loss caused by load nondeterminacy during load shedding. • A novel two-stage underfrequency load shedding strategy is proposed. • The two-stage strategy consists of fast load shedding and risk avoidance strategy. • A quantitative method of load shedding risk loss based on CVaR theory is proposed. • The optimal load shedding ratio distribution quantity is obtained. [ABSTRACT FROM AUTHOR]

The increasing share of renewable distributed generations has raised a challenge about the frequency stability. Under-frequency load shedding (UFLS) can deal with this challenge, but it usually considers a prorated load-shedding strategy and neglects the impact of uncertainty from renewable generation. This may result in unnecessary additional economic losses from the system blackout. In this paper, a risk-decision-based optimal adaptive decentralized UFLS method is proposed to coordinate the distribution of shedding load in the smart distribution network to avoid unnecessary additional economic losses, while considering the wind power uncertainty. Firstly, the uncertainty from wind power generation is modeled by confidence intervals and evaluated by the calculation of the conditional value at risk (CVaR). Then, to economically distribute the power deficit among load agents, a decentralized consensus on the incremental cost among decentralized agents is reached, where the interruption cost of the local agent varies with its load as a nonlinear relationship. Finally, a two-layer adaptive risk-decision decentralized UFLS control framework is proposed to enable the frequency stability and economic operation of the smart distribution network. With the proposed strategy, local information sharing and important global information discovery are achieved in a distributed way. Simulations on an improved IEEE 33-bus system show that the proposed strategy can effectively avoid rigid shedding and implement the optimal allocation of the system power deficit. • An adaptive risk-decision UFLS strategy is proposed to consider the uncertainty of wind power. • A confidence level selection method is designed to improve the accuracy of the reference of CVaR. • A CVaR-based deficiency estimation method to minimize the risk of load shedding under wind power uncertainty. • The shedding load is distributed among different load agents from the perspective of the overall social welfare. [ABSTRACT FROM AUTHOR]