Search

Improving energy efficiency is a crucial aspect of building a sustainable smart city and, more broadly, relevant for improving environmental, economic, and social well-being. Non-intrusive load monitoring (NILM) is a computing technique that estimates energy consumption in real-time and helps raise energy awareness among users to facilitate energy management. Most NILM solutions are still a single machine approach and do not fit well in smart cities. This work proposes a model-agnostic hybrid federated learning framework to collaboratively train NILM models for city-wide energy-saving applications. The framework supports both centralised and decentralised training modes to provide a cluster-based, customisable and optimal learning solution for users. The proposed framework is evaluated on a real-world energy disaggregation dataset. The results show that all NILM models trained in our proposed framework outperform the locally trained ones in accuracy. The results also suggest that the NILM models trained in our framework are resistant to privacy leakage. [ABSTRACT FROM AUTHOR]

China has built four stations in Antarctica so far, and Zhongshan Station is the largest station among them. Continuous power supply for manned stations mainly relies on fuel. With the gradual increase in energy demand at the station and cost of fuel traffic from China to Zhongshan station in Antarctica, reducing fuel consumption and increasing green energy utilization are urgent problems. This research considers a standalone renewable energy system. The polar environments and renewable energy distribution of area of Zhongshan station are analyzed. The physical model, operation principle, and mathematical modeling of the proposed power system were designed. Low-temperature performance and state of charge (SOC) estimation method of the lead–acid battery were comprehensively tested and evaluated. A temperature control strategy was adopted to prevent the battery from low-temperature loss of the battery capacity. Energy management strategy of the power system was proposed by designing maximum power point tracking (MPPT) control strategies for wind turbine and PV array. The whole power system is broadly composed of a power generator (wind turbine and PV array), an uploading circuit, a three-phase rectifier bridge, an interleaved Buck circuit, a DC/DC conversion circuit, a switch circuit, a power supply circuit, an amplifier, a driver circuit, a voltage and current monitoring, a load, battery units and a control system. A case study in Antarctica was applied and can examine the technical feasibility of the proposed system. The results of the case study reveal that the scheme of standalone renewable energy system can satisfy the power demands of Zhongshan Station in normal operation. [ABSTRACT FROM AUTHOR]

From the perspective of energy providers, accurate short-term load forecasting plays a significant role in the energy generation plan, efficient energy distribution process and electricity price strategy optimisation. However, it is hard to achieve a satisfactory result because the historical data is irregular, non-smooth, non-linear and noisy. To handle these challenges, in this work, we introduce a novel model based on the Transformer network to provide an accurate day-ahead load forecasting service. Our model contains a similar day selection approach involving the LightGBM and k-means algorithms. Compared to the traditional RNN-based model, our proposed model can avoid falling into the local minimum and outperforming the global search. To evaluate the performance of our proposed model, we set up a series of simulation experiments based on the energy consumption data in Australia. The performance of our model has an average MAPE (mean absolute percentage error) of 1.13, where RNN is 4.18, and LSTM is 1.93. [ABSTRACT FROM AUTHOR]