In this paper, a novel energy pricing and sharing strategy is proposed to solve the energy management and market bidding problems of a virtual energy station (VES) in multi-carrier energy systems. First, the energy cell-tissue-based group interaction framework and the multiagent-based communication and control architecture are established in the VES. Second, the general model of an energy cell is built, in which the integrated demand response process and the automatic generation control mode of a combined heat and power unit are designed. Third, according to the classification of energy cells, the aggregation rules of the VES without the participation of third-party agents are proposed, and the internal trading mechanism of the VES led by a higher energy cell is designed based on a Stackelberg game. Moreover, a three-stage hybrid stochastic robust optimization strategy is proposed to address uncertainties in market prices and renewable energy output. Finally, the optimization model is linearized and solved by duality theory, KKT conditions, and column-and-constraint generation (CC&G) algorithm. Simulation results prove the rationality and effectiveness of the framework and business model for the VES.

Under the digitalization trend in the energy sector, utilities are devoted to providing better service to their customers by mining knowledge in fine‐grained electricity consumption data. Understanding the group behaviour of customers by clustering method is essential to achieving this end. Different from shape‐based clustering methods, an f ‐divergence based hierarchical clustering model is proposed to group customers by their dynamic electricity consumption patterns. Modelling the electricity consumption by Markov chains, the customers’ consumption patterns are first summarized into transition probability matrixes. Then, dissimilarity measures based on f‐ divergence are calculated. Specifically, due to their superiority, squared Hellinger distance and total variation distance are used. The hierarchical clustering is then conducted based on the obtained distance matrixes. Using real‐world smart meter dataset, the proposed method is compared with other dynamic clustering candidates by using the revised silhouette score. And consumers’ dynamic consumption patterns are not only analysed from the global to local levels, but also the relationship between clustering results and external factors are delved into. The results show that the proposed method can produce highly representative clusters, and is able to provide insights on the implementation of the demand‐side management program.

The widespread adoption of distributed energy resources (DERs) leads to resource redundancy in grid operation and increases computation complexity, which underscores the need for effective resource management strategies. In this paper, we present a novel resource management approach that decouples the resource selection and power dispatch tasks. The resource selection task determines the subset of resources designated to participate in the demand response service, while the power dispatch task determines the power output of the selected candidates. A solution strategy based on contextual bandit with DQN structure is then proposed. Concretely, an agent determines the resource selection action, while the power dispatch task is solved in the environment. The negative value of the operational cost is used as feedback to the agent, which links the two tasks in a closed-loop manner. Moreover, to cope with the uncertainty in the power dispatch problem, distributionally robust optimization (DRO) is applied for the reserve settlement to satisfy the reliability requirement against this uncertainty. Numerical studies demonstrate that the DQN-based contextual bandit approach can achieve a profit enhancement ranging from 0.35% to 46.46% compared to the contextual bandit with policy gradient approach under different resource selection quantities.

Multi-microgrids (MMGs) interconnect microgirds (MGs) with geographical adjacency and improve the overall efficiency, stability, and reliability of a regional energy system. The uncertainty brought by renewable energy resources (RESs) is one of the challenges facing the schedule of MMGs. To cope with it, a multi-timescale schedule strategy is proposed. Specifically, in day-ahead schedule, the on/off states of the units are determined. Then, based on the day-ahead plan and the more accurate estimation of RESs, the refined schedule is achieved in the intraday. And to enhance the flexibility of the MMGs system, multienergy complementarity is considered in this work. Moreover, how to achieve the coordinated schedule between MGs owned by different parties is another problem facing the MMGs system operation. To solve this, a distributed algorithm, namely predictor corrector proximal multiplier, is introduced. During the solution process, each MG only needs to reveal the exchange power to the virtual controller, which protects the privacy and reduces communication burden. Numerical simulation of an MMGs system with four MGs is carried out. The results show that the proposed distributed method has good convergence performance. Besides, the absolute relative differences of objective function results obtained using the proposed method with the centralized counterpart are less than 2% in the day-ahead timescale and which can be less than 0.08% in the intraday timescale. Therefore, the economy and flexibility of the system can be achieved.