Stochastic optimization, which aims at optimizing the expected value of a stochastic objective function, is challenging and commonly-seen in engineering applications. One crucial challenge of stochastic optimization problems (SOPs) is that the objective function value is impossible to calculate accurately due to the existence of uncertainty. As probability distribution is a common mathematical tool for handling uncertainty, this paper intends to explore the use of probability-distribution-based evolutionary algorithms (EAs) for solving complicated SOPs. First, an in-depth analysis of how to sample and construct probability distributions for probability-distribution-based EAs in SOPs is performed through both empirical and theoretical studies. Based on the analysis, it can be concluded that the implicit averaging method is helpful for probability-distribution-based EAs to solve SOPs. Second, evolutionary algorithm based on multiple probability distribution models (EA-mPD) framework is proposed. Instead of using a single probability distribution, the whole population is divided into several clusters by clustering, and several local probability models are built for different clusters. Finally, probability-distribution-based EAs such as estimation of distribution algorithm (EDA) and ant colony optimization (ACO) are introduced in the proposed EA-mPD to solve SOPs. Experimental results show that the proposed EA-mPD method is promising in terms of both accuracy and efficiency.

Stochastic optimization problems, which involve random variables in the optimization process, are commonly seen in many applications such as engineering design and logistics management. The challenge of stochastic optimization is how to accurately evaluate the value of the objective function, while using a large number of Monte Carlo simulations for evaluation can result in significant computational costs. In this paper, we propose a surrogate-assisted continuous ant colony optimization method for stochastic optimization (SAACO). First, instead of using a lot of Monte Carlo simulations, SSACO estimates the approximated fitness values of the individuals in the population by a surrogate model. Second, the continuous ant colony optimization is used as the optimizer, where the population is evolved by constructing a Gaussian kernel function from global information to construct the promising solutions. The surrogate model is a forward model from the solution space to the objective space, while the Gaussian kernel function can be regarded as an inverse model from the objective space to the solution space. By combining two models, the performance of solving stochastic optimization problems can be improved. Experimental results demonstrate the promising performance of the proposed SAACO.

In recent years, China’s rural energy supply guarantee capacity has been continuously enhanced, and the effectiveness of energy structure adjustment has been significant. However, there are problems such as relatively weak infrastructure, extensive energy utilization, and low proportion of clean energy. Aiming at the problems of rural energy development and utilization such as the irrational structure of rural energy consumption and low level of energy consumption in China, focusing on rural domestic energy consumption, this paper combs and analyzes the current situation of rural energy consumption in China, the internal and external situations faced by energy development, analyzes the potential points of replacing fossil energy in various fields of rural production and life, estimates rural carbon sinks and carbon emissions from a multi-dimensional trend, and lays the foundation for studying and judging the “carbon neutrality” capacity of rural energy. In view of the particularity of China’s national conditions and the specific characteristics of different regions, through the study of key issues such as the energy utilization of rural waste, the application of rural energy electrification, and the construction of rural energy service system, it is proposed that rural energy transformation and development is an important means to promote the “carbon neutrality” in rural areas, and proposed measures and suggestions to promote the scientific development of China’s rural energy.

当前,传统配电网规划已无法适应分布式电源的快速发展,为了实现对分布式电源配电网的科学优化,以本文以"分布式电源接入交直流混合微电网群"为研究对象,对其网络架构进行设计.其次,在构建该微电网群优化规划模型的基础上,确定该微电网群优化规划求解流程.最后,探讨了实际工程算例.结果表明:本文所提出的混合微电网群优化配置方法具有较高的可靠性和可行性,使得分布式电源表现出较高的就地消纳水平,同时,还大幅度降低系统成本,完全满足实际应用需求.

在光伏发电等可再生能源发电下,供需平衡能力问题应该在未来的电力系统中进行评估和解决.改进现有的平衡措施和新技术,如电力供需双侧协同和储能将解决这个问题.在这种情况下,远程电力系统供需分析应具有评估平衡对策的能力.基于负荷持续时间曲线的供需分析,与时间序列分析相比该方法具有一定的局限性.但有一个很大的优点是在维护各种电气设备时可以进行供需评估.采用机器学习和深度学习的模型,为预测消费者需求和分布式可再生能源提供了新的解决方案.提出的动力系统供需分析模型ESPRIT为电力供需双侧平衡提供了新的解决方案.

In the context of a significant increase in the charging and discharging scale of electric vehicles accessing the distribution network, a distribution network reliability robust optimization evaluation method considering vehicle-grid interaction is proposed in order to improve the distribution system reliability. Based on the proposed EV driving model, charging and discharging incentive model, and the reliability evaluation index system considering the differentiation of EV users, a two-stage distributed robust fault recovery model is constructed. In the first stage, the power supply range is determined, and the second stage finds the worst-case probability distribution that makes the cost the largest. The results of the case study show that the proposed reliability improvement method can make full use of EV resources, and the resulting optimization scheme is applicable to various operation scenarios.

Abstract With the increasing development of integrated energy systems and the continuous promotion of integrated demand response (IDR) research, residential users with a large amount of demand response resources are drawing more and more widespread attention. In order to fully exploit the IDR potential of residential users and analyse the influence of user comfort and consumer psychology (UCCP) on IDR, the optimised operation study of load aggregator (LA) based on UCCP‐IDR model is proposed. Firstly, a self‐organising map algorithm for clustering is introduced, from which various types of users with differentiated consumption psychology are obtained. Secondly, user comfort and consumption psychology are taken into account to establish a user curtailable, shiftable and transformable load model. Thirdly, the user IDR optimisation model is established based on the load model considering the user response uncertainty. Finally, based on the optimisation strategy of user IDR, the total energy demand of LA is obtained, and thus the optimal operation model of LA equipment is established. The analysis shows that the proposed strategy can provide a more reliable and targeted integrated demand response strategy for residential users, and achieve a win–win situation for both LA and residential users.

For outdoor measurements of large-sized targets at higher frequencies, the far-field condition for plane wave illumination is impractical to satisfy in many applications. As a replacement, near-field tests followed by a near-field to far-field transform (NFFFT) are usually considered. In this paper, an optimized array design is proposed to synthesize a cylindrical wavefront with suppressed clutter in the test zone. To this end, multiple performance of synthetic wavefront is considered systematically. Numerical method is exploited to optimize the excitations to form flat mainlobe and low sidelobes while the corresponding optimizing strategy for wideband measurement is constructed. The effect of ground plane is incorporated and the grating lobe (GL) clutter is reduced by aligning the antenna elements to a slightly higher altitude. Meanwhile, the impacts of ground reflection coefficient and wideband antenna pattern are discussed. Simulation results of a K-band array is presented, demonstrating that the optimized array produces cylindrical wavefront with specified metrics of performance.

With the rapid development of carbon trading market, the volatility trend of carbon emission trading price (CETP) becomes one of the factors that cannot be ignored in energy system planning. Based on this, this paper proposes a multi-objective expansion planning model for park-level integrated energy system (PIES) that takes into account the volatility trend of CETP. First, the influencing factors of CETP prediction are filtered and downscaled, and a kernel extreme learning machine (KELM) model based on the improved multi-objective grey wolf algorithm optimizer (IMOGWO) is used for probabilistic interval prediction of CETP. Next, the operational characteristics of each carbon emission device are analysed and a model for calculating the cost of carbon trading is proposed. Then, a two-layer PIES planning model is developed with the objective of minimizing the annualized system cost and carbon emissions during the expansion planning cycle, the upper-layer model is a planning model for solving equipment expansion scenarios, and the lower-layer model is an operation model for calculating typical operation schemes. Finally, the simulation effect of the prediction model is verified by the European carbon trading data, and the planning schemes are compared and analysed to prove the effectiveness of the proposed method.

电力负荷同时率是表征电力负荷特性的重要参数，同时率的合理取值是进行负荷预测的重要环节之一，进而可以为电力系统规划设计和运行管理提供可靠依据。在很多具体工程实践中，同时率的选取往往缺乏科学依据，依靠现场专家人为给定，这种传统方法没有统一的模型和理论分析作为基础，缺乏理论依据又存在较大的偶然因素，降低了负荷预测的准确度，不利于电力系统规划工作的有效开展。

Traditional integrated energy market has problems such as single transaction type, opaque dispatch subsidies, and lack of institutions that can provide professional and fair services in the integrated energy market. Therefore, based on the smart contract of blockchain, this paper designs the cloud service platform for integrated energy market. The participants in the integrated energy market are divided into integrated energy suppliers and integrated energy users. The two can use the Digital Currency Electronic Payment (DCEP) to trade energy (carbon) in the blockchain smart contract provided by cloud service platform, as well as implement decentralized intelligent dispatch by using blockchain Internet of things technology. The smart contract designed by Antchain is used to simulate the energy trading and dispatch process of cloud service platform, and the verifiable simulation results are given. It is proved that the integrated energy market cloud service platform based on the blockchain smart contract designed in this paper can effectively realize not only the security and convenience of energy trading, but also the efficiency and intelligence of energy dispatch.

With the development and improvement of carbon trading mechanism and the promotion of energy internet strategy, integrated energy system (IES) as the physical carrier of energy internet has an important strategic positioning. Taking electricity-gas-heat multi-energy flow model of IES as the research object, it has important theoretical value and engineering significance to carry out the planning and design research of IES on the basis of quantitative and qualitative analysis of the operational coupling mechanism between different systems and full consideration of the uncertainty of carbon trading market. Based on this, a regional integrated energy system expansion planning model based on the uncertainty of carbon trading price is proposed in this paper. First, a combined forecasting model based on fast integrated empirical modal decomposition (FCEEMD), improved segmented adaptive gray wolf optimization (SAGWO) and least squares support vector machine (LSSVR) was used to simulate the trend of carbon price fluctuations. Second, a stochastic probability distribution model for carbon trading prices was designed using a mean regression model in combination with a sample of carbon trading forecasts. Then, a two-stage stochastic planning model taking into account the grid constraints and system operation constraints is constructed with the objective of minimizing the whole life cycle cost. Finally, the planning schemes under different carbon trading models are compared and analyzed by means of calculation examples, and then the effectiveness of the proposed method is demonstrated.

Scenarios generation is a critical part in planning and operation in high renewable energy penetratied power systems. However, the statistical assumptions of traditional parametric methods may not hold for all types of wind farms. In this paper, a data-driven artificial intelligence approach is presented to generate wind power output scenarios based on generative adversarial networks (GANs). Unlike traditional probabilistic model-based techniques which are typically difficult to scale or sample, the proposed method is data-driven and captures patterns of wind power generation. First, the GAN network structure is constructed, and the Wasserstein distance is employed as the discriminator’s loss function. The GAN training then enables the generator to learn random noise and actual history data. Finally, the scenario generation approach based on Monte Carlo simulation and GANs are compared. It shows that the scenarios generated by proposed method can accurately describe the uncertainty of wind power output.

There are some problems in the traditional integrated energy market, such as single transaction mode, difficulty in effective dispatch, and lack of targeted subject to provide integrated energy market services. Therefore, this paper designs an integrated energy market service system based on the blockchain smart contract. The participants in the integrated energy market are divided into integrated energy suppliers, integrated energy users and integrated energy service providers. The integrated energy service providers set up energy trading centres and energy dispatch centres according to the needs of integrated energy suppliers and integrated energy users, and provide energy trading and dispatch services for them by using the Digital Currency Electronic Payment (DCEP) of the central bank and the blockchain smart contract. “Antchain” platform is used to simulate the energy trading and dispatch process, and the verifiable simulation results are given. It is proved that the integrated energy market service system based on the blockchain intelligent contract designed in this paper can effectively realize the security and convenience of energy trading and the efficiency and intelligence of energy dispatch.

AbstractIn order to reduce the impact of renewable energy output and load fluctuations and improve the flexibility of the integrated energy system (IES), it is necessary to further promote user participation in integrated demand response (IDR). Therefore, this paper constructs a hierarchical framework that enables the transaction of IDR resources among users by combining the information interaction network established by blockchain and the energy management network established by energy management system. This paper also analyses the comfort of users, the cost of energy purchase by users and the cost of energy use by load aggregators, and then develops a two‐layer optimization model. The results of the simulation show that the model and trading framework constructed in this paper can realize the trading of IDR resources among users, which effectively promotes the participation of users in IDR, reduces the cost of users and load aggregators, reduces the loss of IDR resources, enables more effective integration of dispersed IDR resources and improves the flexibility of IES.

With the continuous research on integrated demand response (IDR), the analysis of residential customers' IDR characteristics and the exploration of IDR potential are drawing more and more attention. Therefore, load aggregators(LA) are considered to participate in the study of integrated demand response based on user comfort and consumption psychology. Firstly, we establish various types of response load models taking into account user comfort and consumption psychology, and then establish the IDR model of users. Secondly, the LA equipment optimization operation model is established based on the LA internal equipment modeling. Finally, the analysis shows that the proposed strategy can provide a more detailed and accurate comprehensive demand response strategy for residential customers and achieve a win-win situation for both LA and residential customers.

Propose a demand response uncertainty model based on price incentives, describe the relationship between the incentive price and the demand response coefficient. Constructed energy coupling matrices for integrated community energy systems considering demand response based on traditional energy hub models. The uncertainty of the demand response is depicted using the interval approach. Considering the load characteristics and various constraints of the integrated community energy system, optimized operating model with the goal of minimizing operating costs. Using an example of an integrated community energy system for a campus, considering multiple operating scenarios to investigate the effect of integrated demand response under different approaches, the impact of price incentives and incentive schemes on integrated community energy systems. The results show that compared with the traditional method, this method effectively reduces system operating costs and improves the load profile, which helps to achieve a win-win situation for both energy companies and users.

Query weight optimization, which aims to find an optimal combination of the weights of query terms for sorting relevant documents, is an important topic in the information retrieval system. Due to the huge search space, the query optimization problem is intractable, and evolutionary algorithms have become one popular approach. But as the size of the database grows, traditional retrieval approaches may return a lot of results, which leads to low efficiency and poor practicality. To solve this problem, this paper proposes a two-stage information retrieval system based on an interactive multimodal genetic algorithm (IMGA) for a query weight optimization system. The proposed IMGA has two stages: quantity control and quality optimization. In the quantity control stage, a multimodal genetic algorithm with the aid of the niching method selects multiple promising combinations of query terms simultaneously by which the numbers of retrieved documents are controlled in an appropriate range. In the quality optimization stage, an interactive genetic algorithm is designed to find the optimal query weights so that the most user-friendly document retrieval sequence can be yielded. Users’ feedback information will accelerate the optimization process, and a genetic algorithm (GA) performs interactively with the action of relevance feedback mechanism. Replacing user evaluation, a mathematical model is built to evaluate the fitness values of individuals. In the proposed two-stage method, not only the number of returned results can be controlled, but also the quality and accuracy of retrieval can be improved. The proposed method is run on the database which with more than 2000 documents. The experimental results show that our proposed method outperforms several state-of-the-art query weight optimization approaches in terms of the precision rate and the recall rate.

For the outdoor measurements of large-sized targets and phased arrays at high frequencies, an extremely long distance is required to satisfy the far-field criterion, which is impractical in many applications. As a replacement, near-field tests followed by a near-field to far-field transform (NFFFT) are usually considered. In this paper, an optimized sparse uniform linear array design is proposed for the synthesis of quasi-cylindrical wave in the test zone. To this end, the performance of synthetic wavefront and system complexity are considered systematically. The genetic algorithm (GA) is exploited to optimize the excitation amplitudes and phases. Both uniformity and gain of the electric field (E-field) are considered for wideband measurement while the corresponding optimizing strategy is constructed. Besides, the impacts of uncertainties in practical implementation are discussed. Simulation results for an X-band array are presented, demonstrating that the optimized array produces cylindrical wavefront with specified metrics of performance.

With the rapid development of carbon trading m arket, carbon price volatility has become one of the factors that cannot be ignored in energy system planning. Based on this, th is paper proposes a park-level integrated energy system expans ion planning method based on dynamic carbon trading model. A combined prediction model based on Fast Integrated Empiri cal Modal Decomposition (FCEEMD), Multi-Objective Gray $W$ olf Optimization (MOGWO) and Least Squares Support Vecto r Machine (LSSVR) is used to simulate the future carbon price data, and a calculation model of carbon trading cost is establish ed. Then, set the maximize system net revenue over the extende d planning cycle as the objective, and a park-level integrated en ergy system considering the cost of carbon trading is establishe d. Finally, the accuracy of the prediction model is verified by E uropean carbon trading data, and the performance of the plan ning scheme under different carbon trading models is compare d and analyzed to verify the effectiveness of the proposed method.