Residential Energy Consumption Forecasting Based on Federated Reinforcement Learning with Data Privacy Protection

Most studies have conducted experiments on predicting energy consumption by integrating data formodel training.However, the process of centralizing data can cause problems of data leakage.Meanwhile,many laws and regulationson data security and privacy have been enacted, making it difficult to centralize data, which can lead to a datasilo problem. Thus, to train the model while maintaining user privacy, we adopt a federated learning framework.However, in all classical federated learning frameworks secure aggregation, the Federated Averaging (FedAvg)method is used to directly weight the model parameters on average, which may have an adverse effect on te model.Therefore, we propose the Federated Reinforcement Learning (FedRL) model, which consists of multiple userscollaboratively training the model. Each household trains a local model on local data. These local data neverleave the local area, and only the encrypted parameters are uploaded to the central server to participate in thesecure aggregation of the global model. We improve FedAvg by incorporating a Q-learning algorithm to assignweights to each locally uploaded local model. And the model has improved predictive performance. We validatethe performance of the FedRL model by testing it on a real-world dataset and compare the experimental results withother models. The performance of our proposed method in most of the evaluation metrics is improved comparedto both the centralized and distributed models.

Review of Black Start on New Power System Based on Energy Storage Technology

With the continuous development of new energy generation technology and the increasingly complex power grid environment,the traditional black start scheme cannot meet the requirements of today’s power grid in order to ensure the stable operation of the power system can be restored quickly in the face of large power outages,so a more complete black start scheme needs to be developed to cope with the new power system.With the development of energy storage technology,the limitations of the traditional black-start scheme can be solved by new energy farms with energy storage configuration.Therefore,this paper investigates the problems faced by black-start,the key technologies of energy storage assisted new energy black-start,and introduces the research related to new energy black-start technology to provide reference for future research and application of new energy black-start.

In-situ ultrasonic calibrations of pressure and temperature in a hinge-type double-stage cubic large volume press

Here,simultaneous in-situ calibration of pressures and temperatures was performed in a hinge-type second-stage cubic large volume press(LVP)up to 15 GPa and 1400 K by an acoustic travel-time approach.Based on the recently reported P-tSand P-T-tP-tSequations for Al2O3buffer rod,the cell pressures and temperatures in the chamber of LVP were insitu determined,in comparison with those by conventional off-line(or fixed-points)pressure calibration method and direct thermocouple measurement,respectively.It is found that the cell pressures of the LVP chamber are significantly reduced after annealing at simultaneous high pressures and high temperatures,owing to the stress relaxation as accumulate in the LVP chamber.This acoustic travel-time method is verified to be a good way for precise determination of thermal(cell)pressures at high temperature conditions,and is of great importance and necessity to conduct in-situ physical property measurements under extreme high P-T conditions,especially when the precious synchrotron x-ray/neutron diffraction beams are not available.

Gigahertz-rate-switchable wavefront shaping through integration of metasurfaces with photonic integrated circuit

Achieving spatiotemporal control of light at high speeds presents immense possibilities for various applications in communication,computation,metrology,and sensing.The integration of subwavelength metasurfaces and optical waveguides offers a promising approach to manipulate light across multiple degrees of freedom at high speed in compact photonic integrated circuit(PIC)devices.Here,we demonstrate a gigahertz-rate-switchable wavefront shaping by integrating metasurface,lithium niobate on insulator photonic waveguides,and electrodes within a PIC device.As proofs of concept,we showcase the generation of a focus beam with reconfigurable arbitrary polarizations,switchable focusing with lateral focal positions and focal length,orbital angular momentum light beams as well as Bessel beams.Our measurements indicate modulation speeds of up to the gigahertz rate.This integrated platform offers a versatile and efficient means of controlling the light field at high speed within a compact system,paving the way for potential applications in optical communication,computation,sensing,and imaging.

Neural network assisted high-spatial-resolution polarimetry with non-interleaved chiral metasurfaces

Polarimetry plays an indispensable role in modern optics.Nevertheless,the current strategies generally suffer from bulky system volume or spatial multiplexing scheme,resulting in limited performances when dealing with inhomogeneous polarizations.Here,we propose a non-interleaved,interferometric method to analyze the polarizations based on a tri-channel chiral metasurface.A deep convolutional neural network is also incorporated to enable fast,robust and accurate polarimetry.Spatially uniform and nonuniform polarizations are both measured through the metasurface experimentally.Distinction between two semblable glasses is also demonstrated.Our strategy features the merits of compactness and high spatial resolution,and would inspire more intriguing design for detecting and sensing.

Immobilization and characterization of the Lactarius deliciosus mycelia-embedded polylysine-alginate beads and their decolorization performance

Liquid fermented fungal mycelia with decolorization capability have potential applications in scale-up. In this work, the Lactarius deliciosus mycelia were immobilized on ε-polylysine-alginate beads, and the decolorization effects of ε-polylysine-alginate beads were demonstrated along with Coomassie brilliant blue G-250 as a model dye. Morphology observation confirmed the beads had an exterior film and interior capsule with honeycomb microstructures suitable for mycelia growth. It was manifested that the maximum decolorization efficiency for mycelia was 98.5% at a removal rate of 0.68 mg·L^(-1)·h after 3 days. In comparison, the decolorization efficiency of the immobilized mycelia reached the maximum value of 97.3% at a removal rate of 6.1 mg·L^(-1)·h after 8 h. The enzyme activities of lignin peroxidase and laccase tested in the immobilized mycelia were significantly higher than in that of the free ones, such as the lignin peroxidase had the highest enzyme activity of 77.6 ± 7.4 U·L^(-1) in the former, while of 27.4 ± 8.7 U·L^(-1) in the latter. The immobilization of L. deliciosus mycelia could improve the decolorization of Coomassie brilliant blue G-250 efficiently. The prepared ε-polylysine-alginate beads embedded with L. deliciosus mycelia have very good reusability and a great potential in decolorizing analog dyes.

Investigating the interlayer electron transport and its in?uence on the whole electric properties of black phosphorus

Two-dimensional(2D) nanomaterials have attracted great attention in next generation electronic and optoelectronic technologies due to the unique layered structure and excellent physical and chemical properties. However, the mechanism of transmission along the vertical direction of 2D semiconductor materials has not been investigated. Here, we use first-principles calculations to explore the bandgap energies along different directions, and fabricate a vertical, a lateral and a mixture-structured black phosphorus field effect transistor(BPFET) to study the electrical characteristics along different directions under variable temperatures. The variable temperature test indicates that the mixture-structured device performs more like a lateral device, while the conductance along the vertical direction is hard to be tuned by temperature and electrical field. The unchanged conductance under electric field and variable temperatures allows the vertical device to act as a fixed resistor, promising possible application for the prospective electronic and optoelectronic devices.

Combination of graphene oxide and platelet-rich plasma improves tendon-bone healing in a rabbit model of supraspinatus tendon reconstruction

The treatment of rotator cuff tear is one of the major challenges for orthopedic surgeons.The key to treatment is the reconstruction of the tendon-bone interface(TBI).Autologous platelet-rich plasma(PRP)is used as a therapeutic agent to accelerate the healing of tendons,as it contains a variety of growth factors and is easy to prepare.Graphene oxide(GO)is known to improve the physical properties of biomaterials and promote tissue repair.In this study,PRP gels containing various concentrations of GO were prepared to promote TBI healing and supraspinatus tendon reconstruction in a rabbit model.The incorporation of GO improved the ultrastructure and mechanical properties of the PRP gels.The gels containing 0.5 mg/ml GO(0.5 GO/PRP)continuously released transforming growth factor-b1(TGF-b1)and platelet-derived growth factor(PDGF)-AB,and the released TGF-b1 and PDGF-AB were still at high concentrations,1063.451 pg/ml and814.217 pg/ml,respectively,on the 14th day.In vitro assays showed that the 0.5 GO/PRP gels had good biocompatibility and promoted bone marrow mesenchymal stem cells proliferation and osteogenic and chondrogenic differentiation.After 12 weeks of implantation,the magnetic resonance imaging,microcomputed tomography and histological results indicated that the newly regenerated tendons in the 0.5 GO/PRP group had a similar structure to natural tendons.Moreover,the biomechanical results showed that the newly formed tendons in the 0.5 GO/PRP group had better biomechanical properties compared to those in the other groups,and had more stable TBI tissue.Therefore,the combination of PRP and GO has the potential to be a powerful advancement in the treatment of rotator cuff injuries.