Over the past decade, typhoons have emerged as a primary natural hazard threatening the secure operation of power grids in coastal urban areas. Addressing the day-ahead dispatch challenge for power systems that integrate offshore wind generation, this paper presents a multi-scenario stochastic programming framework that explicitly incorporates typhoon-related uncertainties. Firstly, considering typhoon uncertainty, a typhoon scene set is constructed using the typhoon path, maximum wind speed error model, and probability circle. On this basis, a system loss risk cost model and an offshore wind power output uncertainty set under typhoon uncertainty are proposed. Then, the optimal scheduling model of power system with offshore wind power based on multi-scenario stochastic programming is constructed. With the goal of minimizing the total cost of load loss risk cost, scheduling cost and wind power operation cost under the influence of typhoon, solve the model to get day-ahead scheduling case. Finally, simulations are performed on a modified IEEE 39-bus example. The outcomes demonstrate that the presented method can more accurately reflect the actual uncertainty of typhoons, lessen the uncertainty and conservatism of day - ahead scheduling based on a single typhoon forecast situation, and demonstrate the validity of the proposed method and model.

With the rapid development of large-scale renewable energy integration and flexible DC transmission technologies, modular multilevel converter (MMC)-based high-voltage direct current (HVDC) systems have emerged as a core solution for next-generation DC transmission projects, owing to their modular structure, active/reactive power decoupling control capability, and absence of commutation failure risks. This technology plays a pivotal role in long-distance offshore wind power transmission. However, existing studies predominantly focus on submodule capacitor voltage balancing and arm circulating current suppression, while paying insufficient attention to the reactive power support and dynamic voltage regulation capabilities of MMC during receiving-end grid faults. Current control strategies primarily aim to ensure MMC’s stable operation, failing to fully leverage its rapid power regulation characteristics to provide STATCOM-like dynamic reactive power compensation for the receiving-end grid, thereby limiting system fault recovery capabilities. To address these challenges, this paper proposes a hybrid MMC-STATCOM control strategy integrated with submodule fluctuation suppression. First, a common-mode voltage injection and circulating current suppression method based on a quasi-proportional resonant (quasi-PR) controller is designed to effectively regulate submodule capacitor voltage fluctuations and circulating currents. Second, a phase-angle control variable (λ) is introduced into the conventional power outer-loop control as an additional control parameter. By adjusting the modulation wave phase angles of the upper and lower arms, dynamic power balance is achieved, forming the MMC-STATCOM composite control framework. This strategy enables proactive reactive power support during receiving-end grid short-circuit faults while maintaining continuous active power transmission, significantly enhancing the transient voltage stability and fault ride-through capability of interconnected grids. Finally, a simulation model of the receiving-end grid integrated with offshore wind farms via MMC-HVDC is established in Simulink. Experimental results validate the effectiveness of the proposed strategy, and provide a new technical path for the flexible and direct system to participate in the active grid support.

With the development of large-scale renewable energy sources (RESs) and voltage source converter-based high voltage direct current (VSC-HVDC) technologies, integrating RESs into power systems through VSC-HVDC systems has become increasingly popular. The four-quadrant power control characteristics of VSC converters enable them to function as flexible reactive power sources, which help alleviate voltage stability issues in power systems. However, the implicit functional relationship between the reactive power limits of VSC converters and their output active power, as well as the nonlinear DC power flow between VSC converters in a multi-terminal VSC-HVDC system, make the reactive power boundary of each VSC converter a nonlinear dynamic variable. This adds further complexity to calculating the static voltage stability region boundary (SVSRB). In this paper, an approximate computation model for the SVSR of power systems integrated with large-scale RESs through VSC-HVDC systems is proposed, considering the influences of DC network topology, DC control strategies, control parameters, and other factors. The SVSR is displayed from the perspective of RESs, which helps intuitively evaluate the influence of the DC integration system on the SVSR.

This paper presents an improved pitch control strategy for wind turbines (WTs) by integrating Model Predictive Control (MPC) with a Kalman filter to address control signal fluctuations under variable wind conditions. While MPC effectively handles system constraints and dynamic optimization, it often produces abrupt control outputs that can increase actuator wear and reduce system stability. To overcome this, a Kalman filter is applied at the output stage to smooth the control signal in real time. Simulation results on a three-turbine wind farm demonstrate that the proposed method not only improves pitch control smoothness but also enhances power generation and reduces mechanical loads. In a 300 -second test scenario, the strategy increases total power output by $8214.60 ~\mathrm{W} \cdot ~\mathrm{h}$ and significantly reduces tower base bending moment and spindle torque, confirming its effectiveness and practicality in wind turbine control applications.

The emerging of modern power system poses significant out-of-distribution (OOD) challenges to machine learning (ML)-based cascading failure (CF) analysis. This paper pioneering proposes a Causal Graph Attention Network (CGAT) model, integrating structural causal model (SCM) identify pivotal information within CF events, thereby guiding the predictive accuracy of CF propagation path. Specifically, graph attention mechanism is employed to extract both causal and environmental features as distinctive subgraphs from the topology of power system. The subgraphs help distinguish confounding factors between causal variables and predictions, and their visual representation enables to clarify critical components driving CF propagation. Furthermore, by distinguishing between causal and environmental features, CGAT model predicts CF sequences across diverse topology configurations and varying scenarios of renewable energy sources (RES). Extensive experiments on an augmented IEEE 30-bus system illustrate the effectiveness and superiority of CGAT model.

With the integration of large-scale renewable energy sources into modern power systems, coal-fired power plants are frequently forced into deep peak-shaving operations to manage fluctuating power outputs. Under these operational conditions, coal consumption exhibits significant non-stationary characteristics, posing considerable challenges to intelligent dispatch optimization and coordinated pollutant control systems. Effective forecasting of coal consumption is thus critical. While conventional long short-term memory (LSTM) and Transformer models are capable of capturing both short-term and long-term temporal dependencies, their performance deteriorates significantly when handling highly volatile coal consumption data due to the absence of uncertainty modeling mechanisms. To address these challenges, this paper proposes a novel coal consumption forecasting method, termed DDPMInformer, that integrates an Informer architecture with a Denoising Diffusion Probabilistic Model (DDPM). First, the Informer network effectively captures long-term dependencies using a sparse attention mechanism, enhancing computational efficiency and preliminary forecasting accuracy. Second, we innovatively introduce a DDPM-based diffusion mechanism into the latent layers of the Informer model to implicitly capture and model uncertainties embedded in the data. Unlike traditional explicit uncertainty modeling methods, the proposed DDPM mechanism requires no manual specification of modeling functions or parameters, as it implicitly models uncertainties through a latent diffusion-denoising process. Experimental validation using real operational data from a 2 x 1000 MW coal-fired power plant in Wuhan, China, demonstrates the superior accuracy of the proposed DDPM-Informer method compared with existing state-of-the-art models. The proposed method provides a new technical pathway for intelligent dispatch, combustion efficiency optimization, and emission control in coal-fired power plants under deep peak-shaving scenarios.

To improve the prediction accuracy of offshore wind power, an ultra-short-term wind power prediction method based on data decomposition and dimensionality reduction of input variables is proposed. First, the original wind speed, wind direction and temperature data are decomposed using the improved complete ensemble empirical mode decomposition (ICEEMD) to mitigate the data fluctuations and extract the internal hidden information. Secondly, in order to strengthen the correlation between the input variables and wind power and eliminate the redundant information, the extracted features were nonlinearly downscaled using Kernel Principal Component Analysis (KPCA) to retain the important feature information. Finally, rolling prediction of the reconstructed power components is carried out using long short term memory (LSTM), and the validity of the combination model proposed in this paper is verified by empirical analysis and selected comparison models. The experimental results show that the prediction method for offshore wind power based on ICEEMD-KPCA-LSTM is able to extract more key information within the wind power data, reduce the dimensionality of the input data, and effectively improve the prediction accuracy.

The widespread adoption of renewable energy sources presents significant challenges for power system dis-patching.This paper proposes a dynamic optimal power flow(DOPF)method based on reinforcement learning(RL)to ad-dress the dispatching challenges.The proposed method consid-ers a scenario where large-scale offshore wind farms are inter-connected and have access to an onshore power grid through multiple points of common coupling(PCCs).First,the opera-tional area model of the offshore power grid at the PCCs is es-tablished by combining the prediction results and the transmis-sion capacity limit of the offshore power grid.Built upon this,a dynamic optimization model of the power system and its RL en-vironment are constructed with the consideration of offshore power dispatching constraints.Then,an improved algorithm based on the conditional generative adversarial network(CGAN)and the soft actor-critic(SAC)algorithm is proposed.By analyzing an improved IEEE 118-node system,the proposed method proves to have the advantage of economy over a longer timescale.The resulting strategy satisfies power system opera-tion constraints,effectively addressing the constraint problem of action space of RL,and it has the added benefit of faster so-lution speeds.

With the rise of integrated energy system (IES), some regions have formed integrated energy system cluster (IESC). Multi-energy interaction in IESC can be realized through heat pipelines and powerlines, which improves energy utilization efficiency. Therefore, this paper introduces an optimal operation model of IESC that considers energy transmission losses and aims for the lowest operation cost. Due to the proposed model being nonlinear, a parallel salp swarm algorithm (PSSA) is proposed to solve it. The parallel technique improves the solution accuracy of SSA. Experimental research shows the effectiveness of the optimal operation model of IESC, which reduces the total cost (up to 11.2 %). Moreover, compared with some common algorithms, the proposed PSSA performs better.

The scale and cluster development of offshore wind power faces the constraints of high construction cost, limited submarine corridor resources, etc. Under the background of offshore wind power parity development, it is urgent to consider the actual constraints of the project and the impact of project income on the owner, and the construction of offshore public station and the optimal selection of transmission method have become an important measure to reduce the cost and increase the efficiency of offshore wind power. A life-cycle cost model for offshore wind farm cluster grid-connection system planning is constructed to consider the project income, and the offshore public station location and capacity, transmission method, and high-voltage cable selection and path are optimized, which are solved by an improved single parent genetic algorithm and a topology repair strategy based on graph theory. The results show that the proposed planning scheme can effectively improve the life-cycle project income of the grid-connection system and provide technical support for the grid-connection planning of large-scale offshore wind farm clusters.

The exploration of offshore wind power has shown a definite trend of clustering and rapid development from the shore to the far ocean. This has created new challenges for offshore electrical system (OES) planning for offshore wind farm clusters (OWFCs) because high-voltage alternating current (HVAC) transmission is no longer the only optimal choice. The limitations of transmission capacity and distance restrict the applications of HVAC transmission systems and have led to research on AC&DC hybrid OES. Distributed offshore wind farms (OWFs) in the OWFC and nonpredetermined alternating current/direct current (AC/DC) transmission systems for OWFs demonstrate some new features. This paper presents a mixed-integer linear programming (MILP) model for the OES optimization of the OWFC. Based on a definition of a set of 0-1 decision variable matrices and the linilization of nonlinear variables with auxiliary binary decision variables, CPLEX is introduced to solve the problem. The case results show the effectiveness of the proposed methodology. Some suggestions for the AC/DC hybrid OES planning of the OWFC have also been proposed.

随着海上风电场规模不断扩大,离岸距离变远,传统的集中式海上变电站面临安装容量过大、建设困难等问题.针对以上问题,引入一种海上轻型变电站,提出基于海上轻型变电站的海上风电场电气系统博弈优化方法.建立基于海上轻型站的电气系统全寿命周期成本模型,提出适用于轻型变电站选址的改进k-medoids聚类方法,对不同电压等级的电气系统进行优化,并基于组合权重法和混合策略对规划方案进行多方博弈评估.以江苏省某海上风电场为例进行分析,结果表明,基于海上轻型站的电气系统博弈优化方案能有效提高海上风电场电气系统的综合性能.

With the change of power industry, power and energy, information, transportation and other fields are deeply integrated; therefore, the field of energy and power urgently needs to have “composite” professionals with good knowledge,ability and attainment. To serve the national energy strategy and dock the industrial revolution, a “composite” new power talents training system is designed. Through the “One-body two-wing, interconnected, time-varying” knowledge training,“all-round, multi-level, application focused” ability-building and “production and education integration, international leadership, moral talent and both” based literacy promotion, the comprehensive innovation reform of all-round and wholeprocess training has been carried out to realize the integration of the composite new power talents’ knowledge, the complexity of their abilities and the comprehensiveness of their accomplishments. After ten years of practice and application at Shanghai University of Electric Power, the “composite” new power talents project, which meets the needs of the times, has been successfully developed, providing reference for the training of composite engineering talents in other colleges and universities.

Electrical system planning of the large-scale off-shore wind farm is usually based on $N-1$ security for equipment lectotype. However, in this method, owing to the aggregation effect in large-scale offshore wind farms, offshore electrical equipment operates under low load for long periods, thus wasting resources. In this paper, we propose a method for electrical system planning of the large-scale offshore wind farm based on the $N+$ design. A planning model based on the power-limited operation of wind turbines under the $N+$ design is constructed, and a solution is derived with the optimization of the upper power limits of wind turbines. A comprehensive evaluation and game analysis of the economy, risk of wind abandonment, and environmental sustainability of the planned offshore electrical systems have been conducted. Moreover, the planning of an infield collector system, substation, and transmission system of an offshore electrical system based on the $N+$ design is integrated. For a domestic offshore wind farm, evaluation results show that the proposed planning method can improve the efficiency of wind energy utilization while greatly reducing the investment cost of the electrical system.

针对海上风电机组对故障特征的增量式学习及主动维护的问题,提出了一种基于状态自适应评估的海上风电机组预防性维护策略.首先,采用非正态总体假设检验量化机组实时状态与典型状态的信息差异,通过增量字典学习捕捉机组典型状态特征,基于支持向量机构建了机组状态自适应评估模型.然后,结合部件有效役龄,以机组状态概率向量为决策依据、单次维护费用最小为目标,优化部件维护策略.同时计入部件成组时由于提前或延迟维护的损失,以维护总费用最小为目标、日维护时长为约束,建立了基于状态自适应评估的海上风电机组预防性维护模型.最后,以某海上风电机组为例,验证了所提维护策略的有效性,分析了维护次数、可及性对维护策略的影响.

随着大规模海上风电的发展,多端直流(MTDC)系统由于其灵活的网络结构与控制能力,在海上风电并网规划中获得了越来越多的关注.围绕海上风电集群经MTDC系统接入陆上电网的规划需求,针对接入陆上电网的公共连接点数量、位置、容量等MTDC网络拓扑优化问题,提出一种MTDC网络拓扑矩阵的定义方法,可直观用于MTDC系统不同网络拓扑结构下的小信号模型构建与投资成本计算,并构建了一种兼顾MTDC系统投资经济性与MTDC系统接入对陆上交流电网稳定性影响的综合优化模型.算例分析结果表明,所提模型与方法能够有效进行MTDC系统的多网络拓扑方案优化选择,在保证系统经济性的同时,也有助于提升规划方案的静态稳定水平.

运行环境对海上风电机组状态判别的影响不可忽视，而运行环境因素与风电机组状态变量间耦合关系复杂，文中提出一种基于贝叶斯决策理论和Copula函数的海上风电机组状态判别方法。首先，挖掘运行环境与风电机组状态变量间的相关性特征，分别在风电机组正常和故障两种情况下，利用多元Copula函数构建对应变量的联合密度函数。然后，依托贝叶斯决策理论进行风电机组状态判别。最后，以国内某海上风电场实际运行工况为例进行分析。结果表明：运行环境对风电机组状态判别影响较大，考虑运行环境影响可提高风电机组判别结果的准确率，为利用海上环境因素进行风电机组早期状态预测提供新的参考依据。

传统的贝叶斯网络方法对于新型智能化风电机组获取的"多元异质"状态信息、机组部件故障与状态信息间的耦合关联描述不全面,易造成可靠性评估结果不准确.为此,建立一种融合故障树、云模型及无标度网络的改进贝叶斯网络.引入迭代更新的思路,将改进贝叶斯网络与时序分析方法相结合,提出一种风电机组动态可靠性评估方法.算例结果表明,该方法不仅可以有效地利用风电机组的实时状态信息进行定量的动态可靠度计算,而且可以利用贝叶斯网络、状态结构洞以及无标度网络实现对状态信息与"部件-状态"结构关联特性的表达,提高了动态可靠性评估的准确性.

风功率精确预测是实现大规模海上风电友好并网的重要手段.大型海上风电场机组台数众多,状态各异.机组状态、尾流影响和时空特性对风功率预测的影响不可忽略.该文基于长短期神经网络(long short-term memory,LSTM)–时间卷积神经网络(temporal convolutional network,TCN),提出了一种考虑机组状态、风机尾流和场群空间分布特性的海上风电超短期功率预测方法.首先分析了机组状态和尾流数据对于功率预测的影响,然后基于LSTM建立了风电机组运行数据深度学习预测模型,实现机组健康状态到运行数据的映射,并通过数据的实时滚动对机组健康状态进行持续修正;在此基础上,加入注意力强化和随机空间特性弱化模块的改进LSTM-TCN模型.通过实际运行数据算例分析,相比TCN算法、LSTM算法,该文方法可提升风功率预测的精度,尤其对于海上常见的风速骤变工况适应性较强,对TCN算法过于强化空间特性的问题进行改进.以该模型的精确预测为基础,可进一步用于大规模海上风电场内机组的协调优化控制,提升海上风电出力可靠性.

针对风光储系统中,现有的储能容量优化配置方案无法兼顾分布式电源的发电概率问题,提出一种基于风光概率分布的储能容量优化配置方法.首先建立风电场和光伏电场出力特性数学模型,得出其概率分布曲线;其次研究了储能充放电特性及建设成本;搭建储能容量优化配置模型,并提出一种快速求全局解的改进萤火虫算法.最后结合某地区风光储系统进行算例分析,得到储能装置容量最优配置方案.结果表明:通过该储能容量优化配置方法可以得到不同风光配比下储能容量配置,进一步得到最优容量配置方案;提出的改进萤火虫算法,提高了全局和局部搜索的能力,能够快速求解得到最优储能容量.