Accurately predicting photovoltaic output power is one of the most important basic tasks for the rapid development of the smart grid. The factors that influence photovoltaic output power are not fully considered in the current forecast model. To this end, an all‐factor photovoltaic short‐term output power prediction model based on improved ensemble empirical mode decomposition (EEMD) and the seeker optimization algorithm (SOA) ‐BP neural network model is proposed here. First, different similarity algorithms are used in the selection of similar days of different weather types. Second, the factors that affect the PV output power are divided into deterministic parameters and stochastic parameters. The stochastic parameters of similar daily samples are used to constitute a time series, which is decomposed into several stationary signals by EEMD, and then, these signals are trained separately by the SOA‐BPNN model. Finally, the final forecast result can be synthesized with the deterministic parameters and the accumulation of the predicted data of individual signals. Compared with the results of different prediction models, the prediction accuracy of the proposed model is much higher.

Electric vehicles (EVs) not only serve as significant loads for the power grid but also play a crucial role in the operation of the traffic. Their travel and charging behaviors have an impact on both the power grid and the road network. In order to address the potential impacts of a large-scale deployment of EVs on the power grid and the exacerbation of traffic congestion, this paper first establishes a dynamic road network model based on graph theory and time-varying traffic data combined with a road impedance model. Then, the spatio-temporal distribution characteristics of EV travel are modeled. Furthermore, by incorporating real-time road network data, the traditional Dijkstra’s algorithm for finding the optimal path is improved. At each node, the current real-time road impedance is used as the objective for EV path updates, thus accurately capturing the energy consumption of the EVs. Finally, using a standard testing problem on a typical working day based on data from a real case, the impacts of EV travel and charging behaviors on power distribution network operation and traffic congestion are analyzed under scenarios with no guidance and guidance for the shortest travel time. The results show that this method can significantly reduce the time cost by approximately 18% in travel time, which is of particular concern to users. This method balances the load of the charging stations, elevates the voltage level within the safety requirement of 7%, and simultaneously alleviates traffic congestion near the stations.

Wind energy is one of the most important renewable energy resources. Wind speed forecasting is a critical tool for wind energy conversion system implementation. However, the uncertainty and intermittency of wind speed always affect the prediction accuracy. This paper proposes a novel wind speed forecasting method based on ensemble empirical mode decomposition (EEMD) and GA-BP neural network. The wind speed data are decomposed into certain signals with different frequencies by EEMD. Each signal is taken as input data to establish GA-BP neural network forecasting model. Final forecasted wind speed data are then obtained by adding up the predicted data of each signal. A case study of a wind farm in Inner Mongolia, China shows that this method is more accurate than traditional GA-BP forecasting approach. The study also shows that method with EEMD is more accurate than that with empirical mode decomposition (EMD).

As an important supporting technology for carbon neutrality strategy, the combination of an integrated energy system and hydrogen storage is expected to become a key research direction. To address the insufficient flexibility of multi-energy coupling in the integrated energy system and the overall strategic demand of low-carbon development, a multi-storage integrated energy system architecture that includes electric storage, heat storage and hydrogen storage is established. Then, according to the system status factors, such as energy cost, response characteristics and energy storage status, a hierarchical energy supply control strategy focusing on the energy supply priority of energy storage units is proposed. NSGA-II-MOABC is created as the optimization algorithm to meet the demand of multi-energy coupling energy supply in the integrated energy system. Next, considering the system operational cost and carbon emission cost as the optimization goal, a comprehensive energy optimization scheduling model of multi-storage combined hierarchical energy supply is constructed. Based on the simulation example, the scheduling results of the multi-storage combined system are obtained, through comparative analysis, the addition of hydrogen storage can effectively improve the flexibility of system scheduling. Then, taking several scenarios as simulation examples, the hierarchical energy supply strategy can effectively reduce the system operation cost and carbon emission cost, and it also has a certain role in realizing the local consumption of renewable energy.