Integrated energy system (IES) has the advantages of improving energy efficiency, optimizing energy structure and reducing pollutant emissions, so it has become one of the most effective measures to solve the energy and environmental problems. To solve the planning problem of regional integrated energy system (RIES) without a given system structure, a zoning planning method (ZPM) based on energy hub (EH) model and the concept of directed acyclic graph is presented. That is, by analyzing the energy coupling relationship of EH, the EH zoning model based on equipment type is obtained, and the RIES system structure planning model is proposed. This method not only solves the problem that the planning results are influenced by the unfixed number of system structure planning model layers, but also can jointly plan the system structure and equipment configuration of RIES and improve computational efficiency. An illustrative example of RIES planning is given to make comparative analysis of the planning schemes obtained by hierarchical planning method (HPM), three-tier planning method (TPM) based on the equipment type and ZPM. The results show that ZPM can avoid the influence of the unfixed number of system structure planning model layers on the planning results, and can obtain more economical planning schemes and improve the solution speed of the planning model.

A novel distributed reinforcement learning (DRL) strategy is proposed in this study to coordinate current sharing and voltage restoration in an islanded DC microgrid. Firstly, a reward function considering both equal proportional current sharing and cooperative voltage restoration is defined for each local agent. The global reward of the whole DC microgrid which is the sum of the local rewards is regarged as the optimization objective for DRL. Secondly, by using the distributed consensus method, the predefined pinning consensus value that will maximize the global reward is obtained. An adaptive updating method is proposed to ensure stability of the above pinning consensus method under uncertain communication. Finally, the proposed DRL is implemented along with the synchronization seeking process of the pinning reward, to maximize the global reward and achieve an optimal solution for a DC microgrid. Simulation studies with a typical DC microgrid demonstrate that the proposed DRL is computationally efficient and able to provide an optimal solution even when the communication topology changes.

In this paper, we address the energy scheduling issue in a hybrid energy micro grid, which consists of photovoltaic (PV), wind power, combined heat and power (CHP), energy storage and electric vehicles (EVs). The optimal scheduling model of these power sources is presented with consideration of the demand response. The objective function is minimum total operation costs, including gas cost, electric power purchase from the main grid and storage and EV charging-discharging costs. In the process of optimization, multi-team particle swarm optimization (MTPSO) is proposed, which uses units, groups and swarm information to update the velocity (position) with faster and more stable convergence. With simulation analysis, it is found that the proposed model is effective, and the presented MTPSO has a better global search ability than PSO.

Since renewable energy resource is universally accepted as a promising method to solve the global energy problem, optimal planning and utilization of various distributed generators (DG) and energy storage (ES) devices deserve special concern. ES devices possess various characteristics in power density, energy density, response speed (switching speed) and lifetime. Besides, as different load types have various requirements on power supply reliability according to their importance, coordinated planning with consideration of reasonable matching between power source and load can efficiently improve power supply reliability and economic efficiency via a customized power supply and compensation strategy. This paper focuses on optimization of power source capacity in microgrid and a coordinated planning strategy is proposed with integrated consideration of characteristics of DG, ES and load. An index named additional compensation ratio (ACR) for balancing economic efficiency and reliability is proposed and considered in the strategy. The objective function which aims to minimize life cycle cost (LCC) is established considering economic efficiency, reliability and environmental conservation. The proposed planning strategy and optimizing model is calculated and verified through case study of an autonomy microgrid.

With increasingly predominant renewable energy sources and market deregulation in the distribution network, considerable research effort has been devoted to safe reinforcement learning (RL). Network-constrained peer-to-peer (P2P) transaction is particularly challenging, as the system-wide global constraint is implicitly determined by the joint behavior of individual agents. Existing safe RL methods are burdened of addressing this type of constraint. In this context, this paper proposes a decentralized Multi-Agent Safety-Aware Learning (MASAL) method based on trust region concept. It treats system operation safety as a prerequisite and realizes safety-aware target. Furthermore, a system-wide safety condition classification is proposed, categorizing trading policy optimization into five operation conditions. Endogenous and exogenous violations can be distinguished. Building on the classification of system operation conditions, the method conducts preventive trading policy under normal conditions, and responsive policy under critical conditions when exogenous violations occur. Case studies show that the proposed method outperforms state-of-the-art safety layer method and Lagrangian relaxation method under normal and critical conditions. Numerical results also highlight the effectiveness of the method in terms of interpretable trading policies, scalability performance, and training robustness with multiple constraints.

Accurate wind power forecasting is an important factor in ensuring the stable operation of a power system. In this paper, we propose a wind power forecasting method based on feature analysis and error correction in order to further improve its accuracy. Firstly, the correlation analysis is carried out on the features using the maximal information coefficient (MIC), and the main features are selected as the model input items. Then, the two primary factors affecting wind power forecasting—the wind speed and wind direction provided by numerical weather prediction (NWP)—are analyzed, and the data are divided and clustered from the above two perspectives. Next, the bidirectional long short-term memory network (BiLSTM) is used to predict the power of each group of sub data. Finally, the error is forecasted by a light gradient boosting machine (LightGBM) in order to correct the prediction results. The calculation example shows that the proposed method achieves the expected purpose and improves the accuracy of forecasting effectively.