基于多智能体强化学习的发电商竞价策略模型

随着越来越多的新能源发电商加入电力现货市场的竞价行列,各发电商都面临着如何调整报价策略来使自身利益最大化的问题。为了解决各发电商的报价策略问题,提出了基于多智能体强化学习的MARL-SCCP模型来模拟各发电商的竞价行为以学习报价策略。上述模型首先将每一个发电商建模为一个智能体。其次在建模过程中使用随机机会约束规划来解决风力发电商的不确定性。最后,将神经网络引入WoLF-PHC算法来更好应对智能体较大的状态空间并大幅提高求解速度。实验表明,使用多智能体强化学习来模拟各发电商的竞价过程是可行的,并且能够在较少的迭代次数后学习到较优的策略。在此策略下,各发电商均能实现利益最大化,且新能源发电商能够减少由外界不确定性带来的影响。     

决策理论在信息安全风险管理中的应用

信息安全是近年兴起的一个新兴的领域，对于一个组织来说，信息安全需要的是保障企业信息的机密性、完整性和可用性三项安全属性，控制由于信息安全属性被破坏对企业产生的风险。如何选择适当的措施实现风险控制目标，是组织实现风险管理面临的首要问题。从管理学的角度来看，上述的问题可以看作是决策的问题，本文将根据决策理论，根据信息安全风险管理的特点提出解决上述问题的一种思路。     

一个基于决策粗糙集理论的信息过滤模型

介绍了决策粗糙集理论,提出了一个基于决策粗糙集理论的通用信息过滤模型,并通过对电子邮件进行过滤,与传统的基于文本内容的信息过滤方法——朴素贝叶斯方法进行了比较,比较结果证明该文提出的基于决策粗糙集理论的信息过滤模型可以降低误判率,有较高的正确率。     

共摊成本分配决策的公理化研究

深入研究分配决策的理论体系,对分配问题进行了科学定义,在对分配问题分类的基础上,建立了各类分配问题的数学模型.同时指出,公理化决策方法是经济学与决策理论交叉学科的一个前沿分支,是解决分配问题的根本途径,并对公理化研究的主要特征、研究对象及研究内容进行了详尽阐述.     

决策信息不完全确知的模糊决策集成模型

从模糊模式识别概念出发，建立决策方案集对全体级别加权广义欧氏权距离平方和最小的非线性规划模型，导出决策信息不完全确知的多目标模糊决策集成模型，该模型将模糊优选，模糊模式识别，模糊交叉迭代，模糊聚类等多种决策方法有机地结合到一起，用于处理决策人偏好，方案评价，分级标准等决策信息不完全确知情况的决策问题，为解决复杂系统的不完全信息多目标决策提供了一条新途径。     

非精确信息下基于证据理论的融资策略分析

由于市场环境的复杂性,企业在选择融资业务时所获取的信息往往表现为非精确性信息,因此难以做出有效的决策。针对此问题,基于D-S证据理论提出了一种定量化的决策模型。将不同类型的非精确信息转化为D-S证据理论的焦元表示,以不同融资业务下企业利润的差额为目标函数,根据证据推理,利用信任函数和似然函数构造了目标函数的上下界概率分布,并据此给出企业融资行为的决策依据。实例仿真表明,根据该模型的计算结果,企业可以很直观地做出最佳融资方式的选择。     

基于Bayes 决策理论的数据融合方法

提出一种基于Bayes决策理论的多元优化数据融合方法，给出更具一般性的数据融合算法、判决准则以及系统性能计算公式，并给出几种不同情况下的数据仿真结果。仿真结果证明了该方法的正确性和有效性。     

基于前景理论的交互式群组风险决策方法

为了克服现有方法因立论假设过于理想而存在决策结果的科学性和满意性较差以及决策过程效率低下等缺陷,基于前景理论构建了能够吸纳多种模糊信息且能从中识别有效前景的优选模型及判别定理,并针对结果价值的交互学习提出了具有收敛性的交互式决策方法。数值模拟分析表明,所提出的方法既能反映群组成员风险偏好,保证决策结果具有科学性、满意性,又能平衡信息完善程度与其获取成本之间的矛盾关系,保证决策过程具有有效性和可行性。     

基于可能性理论的案例决策方法研究

提出基于可能性理论与基于案仍推理相结合的双层CBDT决策方法。第1层：决策者应用基于案例推理方法，通过建立在连续集合上问题的可能性分布，结合不同的决策方法对决策问题的不确定性进行定性分析；第2层：利用期望效用理论在与问题的可能性分布相关联的方案中选择具体方案。该方法可避免以往基于案例决策方法中所蕴含的一些技术难题。     

基于资产全寿命成本数据模型的配变更换策略的研究

目前,在配电变压器改造调整的研究中,绝大部分都是围绕高耗能或老旧变压器的大修以延长寿命,针对单一备选配变时直接更换低损耗变压器以降低成本,通过这两个方面的对比来确定规划方案。当存在多种备选配变时,本文提出一种基于全寿命周期成本(Life Cycle Cost, LCC)的高耗能配电变压器更换策略。通过基于设备级的全寿命周期成本构建规划方案的比选模型,对本文所提的更换策略进行评估,以兼顾最小化经济成本、满足节能减排需要、减少故障处置成本为目标,得出最合理的改造方式和最佳的更换时机,最终采用相关算例验证该策略的可行性和有效性,验证从全寿命周期成本角度、选择低能耗变压器和运用合理的检修方式降低LCC,提升经济性,降低电网的规划投资成本。     

多用户NC-OFDM动态频谱分配策略研究*

为提高基于非连续正交频分复用（NC-OFDM）的多用户动态频谱分配的频谱利用率,分析了两种物理层特性——用户干扰和信道衰落对动态频谱分配性能的影响,并在此基础上提出了两种改进的频谱分配策略;改进的策略依次将NC-OFDM系统的物理层特性纳入动态频谱分配策略的设计中。仿真分析验证了改进策略的有效性,其频谱分配的中断概率相比改进前的策略平均降低了约13%,提高了频谱利用率。因此,充分利用物理层特性是动态频谱分配策略提高效率的可行途径。     

Modelling and asset allocation for financial markets based on a stochastic volatility microstructure model

On the basis of the market microstructure theory, a continuous time microstructure model is proposed for describing the dynamics of financial markets with stochastic volatility property. From the microstructure model, one may obtain the estimates of two state variables, which represent the market excess demand and liquidity respectively but cannot be directly observed. Based on the indirectly obtained excess demand information instead of the prediction of price, a simple asset dynamic allocation approach is investigated. The local linearization method, nonlinear Kalman filter and maximum likelihood method-based estimation approach for the microstructure model proposed is presented. Case studies on the financial markets modelling and the estimated model-based asset dynamic allocation control for the JPY/USD (Japanese Yen/US Dollar) exchange rate and Japan TOPIX (Tokyo stock Price IndeX) show a satisfactory modelling precision and dynamic allocation performance.     

An adaptive modeling and asset allocation approach to financial markets based on discrete microstructure model

In previous works, it was verified that the discrete-time microstructure (DTMS) model, which is estimated by training dataset of a financial time series, may be effectively applied to asset allocation control on the following test data. However, if the length of test dataset is too long, prediction capability of the estimated DTMS model may gradually decline due to behavior change of financial market, so that the asset allocation result may become worse on the latter part of test data. To overcome the drawback, this paper presents a semi-on-line adaptive modeling and trading approach to financial time series based on the DTMS model and using a receding horizon optimization procedure. First, a long-interval identification window is selected, and the dataset on the identification window is used to estimate a DTMS model, which will be used to do asset allocation on the following short-term trading interval that is referred to as the trading window. After asset allocation is over on the trading window, the length-fixed identification window is then moved to a new window that includes the previous trading window, and a new DTMS model is estimated by using the dataset on the new identification window. Next, asset allocation continues on the next trading window that follows the previous trading window, and then the modeling and asset allocation process will go on according to the above steps. In order to enhance the flexibility and adaptability of the DTMS model, a comprehensive parameter optimization method is proposed, which incorporates particle swarm optimization (PSO) with Kalman filter and maximum likelihood method for estimating the states and parameters of DTMS model. Based on the adaptive DTMS model estimated on each identification window, an adaptive asset allocation control strategy is designed to achieve optimal control of financial assets. The parameters of the asset allocation controller are optimized by the PSO algorithm on each identification window. Case studies on Hang Seng Index (HSI) of Hong Kong stock exchange and S&P 500 index show that the proposed adaptive modeling and trading strategy can obtain much better asset allocation control performance compared with the parameters-fixed DTMS model.     

An M-ary detection approach for asset allocation

We develop a continuous-time asset allocation model which incorporates both model uncertainty and structural changes in economic conditions. A “dynamic” M-ary detection framework for a continuous-time hidden Markov chain partially observed in a Gaussian process is used to model the price dynamics of the risky asset and the hidden states of an economy. The goal of an investor is to select an optimal asset portfolio mix so as to maximize the expected utility of terminal wealth. Filtering theory is used first to turn the problem into one with complete observations and then to derive M-ary detection filters for the hidden system. The Hamilton-Jacobi-Bellman dynamic programming approach is used to solve the asset allocation problem with complete observations. An explicit solution is obtained for the power utility case.     

A decision support system for strategic asset allocation

Strategic asset allocation is a crucial activity for any institutional or individual investor. Given a set of asset classes, the problem concerns the definition and management over time of the best asset mix to achieve favorable returns subject to various uncertainties, policy and legal constraints, and other requirements. Although a considerable attention has been placed by the scientific community to address this problem by proposing sophisticated optimization models, limited effort has been devoted to the design of integrated framework that can be systematically used by financial operators. The paper presents a decision support system which integrates simulation techniques for forecasting future uncertain market conditions and sophisticated optimization models based on the stochastic programming paradigm. The system has been designed to be accessed via web and takes advantages of the increased computational power offered by high performance computing platforms. Real-world instances have been used to assess the performance of the decision support system also in comparison with more traditional portfolio optimization strategies.     

Adaptive stock trading with dynamic asset allocation using reinforcement learning

Stock trading is an important decision-making problem that involves both stock selection and asset management. Though many promising results have been reported for predicting prices, selecting stocks, and managing assets using machine-learning techniques, considering all of them is challenging because of their complexity. In this paper, we present a new stock trading method that incorporates dynamic asset allocation in a reinforcement-learning framework. The proposed asset allocation strategy, called meta policy (MP), is designed to utilize the temporal information from both stock recommendations and the ratio of the stock fund over the asset. Local traders are constructed with pattern-based multiple predictors, and used to decide the purchase money per recommendation. Formulating the MP in the reinforcement learning framework is achieved by a compact design of the environment and the learning agent. Experimental results using the Korean stock market show that the proposed MP method outperforms other fixed asset-allocation strategies, and reduces the risks inherent in local traders.     

Intertemporal asset allocation when the underlying factors are unobservable

The aim of this paper is to develop an optimal long-term bond investment strategy which can be applied to real market situations. This paper employs Merton’s intertemporal framework to accommodate the features of a stochastic interest rate and the time-varying dynamics of bond returns. The long-term investors encounter a partial information problem where they can only observe the market bond prices but not the driving factors of the variability of the interest rate and the bond return dynamics. With the assumption of Gaussian factor dynamics, we are able to develop an analytical solution for the optimal long-term investment strategies under the case of full information. To apply the best theoretical investment strategy to the real market we need to be aware of the existence of measurement errors representing the gap between theoretical and empirical models. We estimate the model based on data for the German securities market and then the estimation results are employed to develop long-term bond investment strategies. Because of the presence of measurement errors, we provide a simulation study to examine the performance of the best theoretical investment strategy. We find that the measurement errors have a great impact on the optimality of the investment strategies and that under certain circumstance the best theoretical investment strategies may not perform so well in a real market situation. In the simulation study, we also investigate the role of information about the variability of the stochastic interest rate and the bond return dynamics. Our results show that this information can indeed be used to advantage in making sensible long-term investment decisions.     

Strategic asset allocation and market timing: a reinforcement learning approach

We apply the recurrent reinforcement learning method of Moody, Wu, Liao, and Saffell (1998) in the context of the strategic asset allocation computed for sample data from US, UK, Germany, and Japan. It is found that the optimal asset allocation deviates substantially from the fixed-mix rule. The investor actively times the market and he is able to outperform it consistently over the almost two decades we analyze.     

Buffer allocation strategies with blocking requirements

The problem of choosing buffer allocation strategies occurs in the design of any store-and-forward computer network. A good buffer allocation strategy can reduce message blocking; and hence provide more efficient use of network storage resources. We first summarize five buffer allocation strategies and then provide algorithms for determining the minimum buffer sizes required by these strategies given that each outgoing channel must satisfy certain blocking requirements. After that, we compare them under different network conditions such as heavy or light input traffic rate, uniform or non-uniform server utilization and different blocking requirements. Guidelines on which strategy to use under different conditions are also given.