Multienergy load forecasting technique is the basis for the operation and scheduling of integrated energy system. Different types of loads in an integrated energy system, i.e., electricity load, heat load, cold load, might have complex and strong coupling relationships among them. If the internal relationship of multienergy load can be considered to realize joint prediction, the accuracy of multienergy load forecasting could be improved. This paper proposes a multi-task model, MultiDeT (Multiple-Decoder Transformer), which firstly adopts the one-encoder multi-decoder structure to realize the multi-task architecture and perform joint prediction of multienergy load. Based on the encoder-decoder architecture, the proposed model encodes all the input data by a uniform encoder and performs each forecasting task by multiple decoders. All tasks share the same encoder parameters, but have dedicated decoders for subtask learning. Therefore, the proposed multi-decoder structure can achieve different levels of attention to the output representation of the encoder by multi-head attention. The entire model is jointly trained end-to-end with losses from each task. Finally, the proposed model is tested on the publicly available datasets. Compared with other forecasting models, the results show that the proposed model has more accurate load forecasting results and has higher generalization capability.

Probabilistic multi-energy load forecasting in an integrated energy system is very complex, because it needs to consider the following three aspects simultaneously: 1) Complex coupling relationship exists between multi-energy loads. 2) The intrinsic distribution of load uncertainties and dynamic changes of the distributions should be captured. 3) The probability distribution containing sufficient information should be generated. To address these issues, this paper proposes a multi-task Bayesian neural network, Bayesian Multiple-Decoder Transformer (BMDeT), which can capture both epistemic and aleatoric uncertainty, and achieve the joint probabilistic forecasting of the multi-energy loads considering their complex coupling relationship and related uncertainties. Firstly, the proposed model adopts the one-encoder multi-decoder framework, which could catch the multi-load coupling information by one Bayesian encoder and perform respective subtasks by multiple Bayesian decoders. Specifically, the Bayesian multi-head attention mechanism is proposed to capture the complex coupling relationship and uncertainties between multi-energy loads by optimizing the distribution of network parameters. Then, a multi-task balance method based on Bayesian theory is proposed to quantify the uncertainties of different tasks by giving trainable weights. Finally, the proposed model has been verified on a real-world load data set, the results show that it has superior performance over other benchmark models.

The safety and security of load frequency control (LFC) system are menaced by cyber attacks and physical attacks. Sophisticated attackers can launch cyber-physical attacks (CPAs), in which cyber attacks are used to increase the impacts of physical attacks by sending wrong instructions to the LFC controller. Considering that parameters of cyber attacks in CPAs may be either fixed or variable, a novel detection scheme is designed against two potential CPAs on an LFC system, namely fixed cyber-physical attacks (FCPAs) and variable cyber-physical attacks (VCPAs), respectively. As for FCPAs, dynamic characteristics of Area Control Error (ACE) are utilized to detect the compromised data. Compared with FCPAs, VCPAs are more deceptive. A relation-based (RB) feature extraction method is introduced to distinguish the signals compromised by VCPAs from the normal ones. A detection model that does not require compromised samples is developed with the aid of support vector domain description. In the end, a comprehensive detection scheme is designed to detect both FCPAs and VCPAs on the LFC system.

This paper proposes a prospect theory (PT)-based bidding model of a prosumer in the power market. Unlike existing efforts of the bidding model that assume the rational behavior of the prosumers, the model incorporates irrationality and individual preferences to capture the prosumer-related subjective perceptions on the bidding results. Considering the impacts of the bidding rules of the power market, we build up the PT-based bidding models with 1-segment and multi-segment bidding rules, respectively. A case study with four different prosumers, i.e., rational, conservative, neutral, and aggressive prosumers is conducted, and the simulation results between expected value theory-based and the PT-based methods are compared. Simulation results validate the effectiveness of the proposed method.

This paper first points out and carefully analyzes the complementary regulation characteristics (CRC) of wind power generators (WGs) and demand response resources (DRRs), which indicate the fact that their regulation capacities and costs of upward and downward regulation are significantly different and complementary. Based on the CRC of WGs and DRRs, this paper proposes a coordinated control to achieve a more robust and cost-efficient primary frequency regulation (PFR). In the proposed coordinated control, the droop gains of WGs and DRRs for upward and downward regulation are designed in a coordinated way so that the resources with larger capacities and lower costs could provide more frequency support. Meanwhile, the stability and robustness conditions of their coordinated droop gains are constructed by small-signal analysis method and the potential instability risks arising from unreasonable coordinated droop gains and time delays are addressed. An optimal $H_{\infty }$ control method and an updated mechanism are supplemented to obtain the optimal droop gains under the proposed coordinated structure for ensuring optimal system robustness under different CRCs. The robust performances and costs of the proposed coordinated control are evaluated on the IEEE 39-bus test system and its advantages are verified.