Search

Tourism Recommendation Systems (TRS) are increasingly important in the tourism industry to provide personalized recommendations based on diverse tourist preferences. Technology and big data have transformed TRS from traditional travel agencies to modern digital platforms, enabling the processing of vast amounts of user-generated data for precise recommendations. The study aims to identify strengths and weaknesses within existing TRS frameworks and techniques, propose recommendations to mitigate these weaknesses, and provide insights for practitioners and researchers. Key findings are the effectiveness of personalized and context-aware recommendations, the importance of multimodal data integration, the need for ethical and fair recommendation practices. Future directions in TRS research should focus on exploring and developing explainable AI and transparency, personalization at scale, enhancing multimodal recommendation capabilities, and ensuring ethical and fair recommendation. This review contributes to a deeper understanding of contemporary TRS methodologies and provides actionable insights for enhancing TRS performance. By addressing current trends and proposing recommendations for future research, this paper aims to advance the field of TRS and improve travel experiences for tourists.

The construction of microgrid has fully promoted the large-scale access of distributed power and the rapid development of electric vehicles (EVs). And microgrid system faces operational issues such as strong random disturbances from distributed power sources and loads, as well as unexpected events during operation. These issues can lead to unstable microgrid frequency, excessive discharge of EVs, and increased control costs. To solve the issues, a frequency cooperative control strategy for multimicrogrids with EVs based on improved evolutionary-deep reinforcement learning (EDRL) is proposed in this paper. First, consider the effect of the vehicle-to-grid (V2G) process on the minimum time required to fully charge an EV, and the impact of the output distribution of micro turbines (MTs) on the regulation cost, and based on the coupling relationship between generator terminal voltage regulation and system frequency control, a multimicrogrid comprehensive control model is constructed. Second, in order to deal with engineering tasks with deceptive rewards and sparse rewards such as integrated frequency control, evolutionary algorithms and deep reinforcement learning algorithms are combined to effectively assist the training process to jump out of local optimal solutions and approach optimal control strategies. Meanwhile, the algorithm is improved based on the novelty search and intelligent partition strategy, so that the strategy has better convergence characteristics and can reduce the cost of information transmission and computational complexity under the premise of ensuring the control effect. Furthermore, the state space, action space and reward function of the controller are defined. Finally, the simulation results show that the proposed controller has the ability of coordinated control, can effectively reduce the adjustment cost of MT unit and the unnecessary discharging of EVs while ensuring the frequency regulation requirements of each submicrogrid, which is far superior to PID control, fuzzy control, and traditional deep reinforcement learning control.

The large-scale application of distributed power generation and the prospects of vehicle to grid (V2G) technology lead to unstable operating voltage of the distribution network, but also new possible approaches to the regulation of the power system. Therefore, a multilayer voltage intelligent control strategy is proposed for a distribution network with V2G and power energy production-consumption units (PECUs). First, a model of the PECU includes facilities such as electric vehicle (EV) charging stations (CSs), urban loads, and distributed energy. The model includes a basic energy unit that can accept distribution network scheduling, provide flexible resources for the power system, and enhance system regulation capabilities. Second, based on the impact of V2G process on the demand of EV users, a CS frequency modulation power controllable boundary evaluation model and a sum power response model were obtained, which enable the CSs to participate in power regulation. Furthermore, to address complex engineering tasks with hidden rewards such as comprehensive control, an evolutionary deep reinforcement learning (EDRL) algorithm is applied and improved based on novelty search operations. This algorithm further enhances the scalability of intelligent agent learning to design a multilayer voltage control structure for the distribution network. Finally, the simulation results show that the applied models can fully utilize the power regulation capabilities while satisfying the internal power supply and demand balance in the PECUs. The proposed strategy has the best coordinated control ability, compared to particle swarm optimization (PSO), network losses are reduced by 23.93 %, and voltage deviations are significantly lowered by 71.95 %, it also ensures the charging demands of EV users, reducing the discharge process of EVs by 6 times.

Abstract System reliability and stability can be significantly improved by the interconnected operation of multimicrogrids, and electric vehicles (EVs) provide a more flexible solution for frequency control, which also present challenges for frequency control. Therefore, a load frequency control (LFC) strategy for multimicrogrids with vehicle to grid (V2G) dependent on learning‐based model predictive control (MPC) is proposed. First, a controller‐interconnected multimicrogrid topology is proposed; thus, a multimicrogrid consisting of microturbines (MTs), distributed power sources, and EVs and their random power constraints is established. Second, a control parameter adaptive algorithm based on learning‐based MPC is designed. The real‐time frequency offset and EV station output power boundary are used as the state set, adjustable parameters of the MPC controller are used as the action set, and reward function is set with frequency deviation so that the adaptive adjustment of the weight parameters of the MPC controller is realised. Additionally, the improved MPC controller designed in this paper can transform the frequency control process into an optimization problem, which is well adapted to various random constraints in the control process. In addition, the deep deterministic policy gradient (DDPG)‐MPC double‐layer controller can prevent machine learning controller failure. Finally, the simulation results show that, compared with traditional control and MPC algorithms, the learning‐based MPC controller applied to the controller interconnection structure can exchange information between submicrogrids. Moreover, based on the experience accumulated in the prelearning process, the controller parameters can be updated according to the environmental state in real time, thereby significantly improving the robustness and rapidity of the multimicrogrid frequency control process. Meanwhile, compared with a traditional DDPG controller, the proposed controller with double‐layer coupling structure can better ensure the safe operation of the multimicrogrid system when the machine learning agent fails and cannot output actions normally.

The Cu–15Ni–8Sn alloy ingot was prepared in the medium-frequency induction melting furnace. The hot extruded alloy was treated by solid solution at 840 °C for 60 min and aging at 400 °C for different times (0 miñ480 min). The effect of aging time on the evolution of the nanophase of Cu–15Ni–8Sn alloy and the strengthening-toughening mechanism were studied. The results show that at the beginning of aging, the alloy undergoes spinodal decomposition, the wavelength of the modulated structure is approximately 3∼7 nm, the ordered phase transformation of D022 and L12 occurs simultaneously, and the ordered phase size is approximately 5 nm. With the extension of aging time, the modulated structure became coarser, and the wavelength of the modulated structure increased to 5–9 nm. At the same time, the D022 ordered phase changed to the L12 ordered phase, and a continuous distribution of elliptical discontinuous precipitation appeared at the grain boundary. The ratio of the long and short axes of the discontinuous precipitation was approximately 4.7. In the late aging period, the D022 ordered phase was basically transformed into the L12 ordered phase, and discontinuous precipitation, which is incompatible with the matrix, extended into the crystal. After 120 min of aging at 400 °C, the hardness, strength, and elongation of the alloy are 105.4 HRB, 839.8 MPa and 9.6 %, respectively. The peak-aging states D022 and L12 coexist in an orderly phase at the nanoscale, and this nanoscale strengthening phase is completely integrated with the matrix, which improves the strength and toughness of the alloy. The research results can provide support for the development of high-performance copper alloys in the ocean.