Accurate diagnosis of clinically significant prostate cancer (csPCa) is central to patient management, with the clinical gold standard relying on the interpretation of multi-parametric Magnetic Resonance Imaging (mpMRI) using the PI-RADS v2.1 score [1]. However, this standard is critically challenged by lesion subtlety and substantial interobserver variability, especially within the ambiguous PIRADS 3 category, presenting a significant research gap for automated systems. To address this, we propose a novel twostage deep learning framework designed to systematically separate the tasks of high-recall lesion localization and finegrained PI-RADS classification, while effectively modeling the synergistic relationship between anatomical (T2W) and functional (ADC/DWI) sequences. The first stage introduces a Multi-modal Latent Diffusion Model (LDM) for normative reconstruction and a Learned Difference Sub-network for anomaly scoring, which learns the distribution manifold of healthy tissue to efficiently generate high-recall candidate Regions of Interest (ROIs). Stage 2 employs a dedicated 3D Swin Transformer classifier to perform 5-class PI-RADS prediction on these ROIs. This classifier achieves robust performance by utilizing a Multi-Head Cross-Attention mechanism for dynamic, deep-level feature fusion across T2W and ADC/DWI modalities, and by incorporating prostatic zonal priors to enhance its clinical contextawareness in the final prediction layer. Our framework is rigorously validated on the large-scale, public benchmark PICAI dataset. Quantitative ablation studies confirm that our proposed cross-modal fusion and prior-injection modules are critical drivers of this superior performance, demonstrated across a comprehensive suite of metrics evaluating classification accuracy, clinical utility, and prediction reliability. Our work provides a robust solution that achieves state-of-the-art accuracy and balanced performance, demonstrating strong potential for clinical translation.

This paper proposes a distributionally robust optimal operation methodology to coordinate multi-energy interactions and facilitate the emission mitigation for multi-energy systems (MESs) with uncertainty couplings in electricity and carbon markets. A carbon recycling model is proposed to exploit the operational flexibility of multi-energy synergies to enhance economic profits of MES operators under market incentives. Then, a generalized cost model incorporating the lifetime cost of carbon capture and power-to-gas degradation is formulated to provide a quantitative analysis for the coordinated electricity and carbon trading. The co-movements of price fluctuations in electricity and carbon markets are explored through a tailored explainable neural network and uncertainty couplings in the markets are further revealed by a Clayton copula based joint probability distribution (PD) model of price prediction residuals. Moreover, a distributionally robust optimization method is formulated for the optimal coordinated operation of MESs to cope with uncertainties from interrelated fluctuating prices. Numerical studies corroborate the effectiveness and superiority of the proposed methodology in the enhancement of economic and environmental benefits.

An improved analytical energy operator (IAEO) and novel three-spectral line interpolation discrete Fourier method is proposed in this article to estimate voltage flicker parameter. First, the analytic energy operator is improved based on Taylor series to better extract the amplitude and frequency features of voltage flicker envelope signal, and simplify the envelope extraction formula to avoid the square root operation. Then, a novel three-spectral line interpolation discrete Fourier transform (DFT) algorithm is constructed by using Kaiser window and Blackman-Harris mutual convolution, and the amplitude and frequency correction formulas of voltage flicker are derived based on the novel three-spectral line interpolation DFT. Finally, the voltage flicker parameter estimation is realized on the virtual instrument based on the proposed method. The applicability and accuracy of the IAEO and novel three-spectral line interpolation DFT method for parameter estimation of voltage flicker are verified by a series of simulations and experiments.

The frequency and voltage stability of grid-forming virtual synchronous generator (GFM-VSG) grid-tied system becomes significant in inertia and damping support when GFM-VSG is attached to the power network. In this article, we propose a generic open-loop system model for the frequency–voltage induced-stability analysis, where the dynamics of rate of change of frequency (RoCoF) is a dynamic process that acts on the rate of change of voltage and then, in turn, reacts on RoCoF. In addition, frequency self-stability is evaluated by magnitude–phase feedback analytical model, where the frequency dynamics are identified by the interaction between RoCoF and frequency bias (FB). Also, it is found that inertia is the origin of occurrence of low-frequency oscillation, which induces a natural phase bias between RoCoF and FB. It is found that GFM-VSG can operate stably in weak grid but cannot operate well in ultrastrong grid condition. Finally, theoretical analysis is validated by simulations and experiments.

Developing efficient defensive strategies against cyber-attacks is a major concern of modern power system research. With the goal of minimizing the expected load loss, this article proposes a robust probabilistic substation-based defender-attacker-defender (DAD) model to allocate the substation's defensive resources. The proposed model aims to minimize the risk of cyber-attacks on intelligent electronic devices (IEDs). The game between the defender and the attacker concerning multiple substations, IEDs, and their connected lines is particularly modeled. In addition, we extend the proposed probabilistic DAD model to an observability-ensured DAD model where the existing phasor measurement units in the power grids are considered in the defensive resource allocation. Integrated with the logarithmic transformation and piecewise linearization techniques, a customized column-and-constraint generation algorithm is developed to solve the proposed model. Finally, the numerical results on IEEE RTS 24-bus and 118-bus systems validate the proposed model.

This paper presents a variable-current charging strategy of Li-ion batteries. Since the battery characteristics vary with state of charge (SOC), it is more reasonable to divide the charging process based on SOC than on cut off voltage. We find an optimal charging pattern of the proposed strategy by Non-dominated Sorting Genetic Algorithm-III (NSGA-III). The Second-order Thevenin model of battery is established to simulate the charging process. Verification experiments are performed and results show that the obtained charging pattern has a temperature and loss reduction of 2.9 °C and 0.5% compared with constant current-constant voltage (CC-CV) strategy under the same charging time and capacity.

In the above article[1], the first-page affiliation information should appear as follows: Li Jiang, Yuduo Huang, Yong Li, Xuebo Qiao, Chun Huang, and Yijia Cao are with the College of Electrical and Information Engineering, Hunan University, Changsha 410082, China, and also with the State Key Laboratory of Advance Design and Manufacturing for Vehicle Body, Hunan University, Changsha 410082, China.

The use of integrated shipboard power system (SPS) has greatly contributed to the next-generation vessels development. In this sense, how to realize the reasonable power distribution between hybrid zones in SPS is becoming one of the key problems to ensure system robustness and reliability. In this paper, a flexible power control strategy is proposed for the coordinated operation of the hybrid ac/dc zones in SPS. First, the interactive relationship of the ac/dc interface is analyzed, and the virtual inertia and capacitance are defined to reveal the interactive influence of the ac and the dc subgrids, which leads to a new V-f droop principle. Then, the flexible control strategy is designed based on the droop principle as well as the characteristics of the analogous virtual synchronous generator, and the key parameters' determination are discussed in detail, which can realize a proper assignment of cross-zone supportive power and improve the system dynamic response. In addition, the coordinated control loops are designed with the distributed energy storages and interlinking converters for the implementation of the strategy. Finally, the proposed strategy is validated by the simulation, which shows that the strategy can enhance the power quality and dynamics of the hybrid zones and contribute to the robustness of the whole SPS.

This paper proposes an optimal locating and sizing method of distributed generations (DGs) considering local consumption and power export potential. Based on the analysis of seasonal and temporal characteristics of different types of DGs and load, the proposed DGs locating and sizing model, is to minimize the total costs of DGs depreciation, network power losses, and redundant power. Under the premise of load demand locally satisfied, the optimal location and size of DGs is obtained by reducing the redundant power of DGs. Finally, the IEEE 33-bus test system is applied to validate the effectiveness and practicability of the proposed method.

This paper proposes a mixed-integer quadratic programming (MIQP) model for optimal day-ahead distribution networks dispatch considering Wind Generators (WGs) and topology reconfiguration. Firstly, linearized current injection model is introduced for generators by a series of approximations. Then the day-ahead Switching Operations (SOs) of reconfiguration could be calculated in a linear form based on the fixed characteristic of network topology. Finally, the costs of power loss and SOs are minimized by our model while the linear constraints, e.g. nodal voltage (NV) constraints and branch current constraints, are considered. The simulation results on IEEE-33 system demonstrate that the proposed model is feasible and effective.

Due to the inverter used, DG can not only integrate the active power into power grid but also support the grid with reactive power. This paper proposes an optimal configuration methodology of renewable DG so as to maximize the penetration level of DG considering the temporal characteristics of active-reactive power (P-Q). Further, the uncertainty output of the wind generator, photovoltaic and small hydropower is taken into account by forming typical scenarios based on the cluster analysis of historical data. Simulation on a modified IEEE33-bus distribution system show that a significant increase in maximum penetration can obtain by considering the reactive power of DGs.

This paper proposes a multiperiod optimal dispatch model for hybrid voltage source converter based multi-terminal DC (VSC-MTDC) system and AC grids with consideration of optimal coordination of offshore wind farm (OWF) and battery energy storage (BES). The OWF is connected to onshore AC grid by VSC-MTDC. The VSC capacity limits and Grid Code for OWF connection to AC grid are taken into consideration. Scenario method is employed to model the wind energy output uncertainty. Simulation on the modified IEEE 118-bus system with three OWFs integration via seven terminal VSC-MTDC network is used to validate the availability and effectiveness of the proposed method.

Battery energy storage (BES) and distributed generation (DG) play an important role in active distribution networks. However, harmonic problems could be caused by the inverters in BES and DG, resulting in a poor power quality (PQ). In addition, ensuring acceptable voltage unbalance level is also another crucial PQ issue in distribution networks. Therefore, in this paper, an optimal distribution network operational model (ODNOM) is proposed to consider PQ problems caused by BES and DG. In this model, additional network power losses due to harmonics are considered into the objective function, and the harmonic constraints and voltage unbalance constraints are also taken into account. The particle swarm optimization is used to solve the proposed ODNOM. The simulations on the IEEE 13-bus, IEEE 37-bus, and IEEE 123-bus systems show that a satisfactory PQ can be achieved by the proposed approach while optimizing the total branch active power losses. This paper aims to obtain a satisfactory PQ level while minimizing the total branch active power losses in the day-ahead dispatch of active distribution networks, since inverters-based BES and DG can inject harmonic pollution into distribution networks and voltage unbalance level is also an important issue for supplying good quality electricity to end users. To achieve such an objective, PQ constraints such as the total voltage harmonic distortion (THD) constraints, the individual voltage distortion constraints, and the voltage unbalance factor constraints are considered into the day-ahead scheduling. In addition, the network active power losses of the concerned harmonic frequencies are also considered into the objective function. The simulation results of the unbalanced IEEE 13-bus, IEEE 37-bus, and IEEE 123-bus systems show that the proposed approach can give a satisfactory day-ahead schedule of good quality power for active distribution networks. Also, the case studies indicate that total network power losses and the satisfactory PQ are the two contradictory objectives. The proposed approach can be applied to ensure a satisfactory PQ when making a dispatch plan in distribution networks with inverter-based BES and DG.

A novel hybrid algorithm EPLSE is proposed to design fuzzy rule bases automatically, which is based on the combination of EP (evolutionary programming) and LSE (least squares estimate). By utilizing the consequent parameters of the super 1/sup st/-order Sugeno model, the training error is decreased greatly. Compared with the original work, the proposed algorithm has remarkably improved the fuzzy model's precision and simplified its structure. In the simulation, EPLSE is employed to predict a chaotic time series. Comparisons with some typical fuzzy modeling methods and artificial neural networks are presented and discussed. Other promising applications of the proposed EPLSE are also suggested.