Supplying Electricity Plan of Multiobjective Average Conditional Value-at-Risk Model

摘要

Researchers and financial institutions have developed and implemented a variety of sophisticated risk models for market risk in trading portfolios. As a tool in optimization modeling, conditional value-at-risk (CVaR) has superior properties in many respects. It maintains consistency with VaR by yielding the same results in the limited settings where VaR computations are tractable, i.e., for normal distributions. Because many practical risk problems are multiobjective in loan portfolios of bank, supply electricity plan of Electricity Board and so on, it is important question to develop multiobjective risk model. This paper proposes a general multiobjective average conditional value-at-risk model with multiple losses and period. We introduce the concept of average α-CVaR for the case of multiple losses with random variable under the multiple confidence level vector αat period. The average a-CVaR indicates the conditional expected losses corresponding to the α-VaR. The problem of solving the minimal α-CVaR results in a nonlinear optimal problem, which another optimal problem based on weight is shown that its optimal solutions is the solutions. Finally, we build multiobjective average CVaR model to find out the robust period and portfolios for supplying electricity plan. The numerical results means that supplying electricity plan may be regulated with price and quantity to evade loss of risk.