Search

Background: With the further opening of the electricity sales market, based on the current power reform situation, it is more emphasized to focus on the market and customers and carry out value marketing. Therefore, further mining the user value has become a necessary means for the transformation of power grid enterprises, and the construction of power user behavior portraits has very practical significance for the business expansion of power grid companies and the improvement of customer service levels. Objective: In order to further explore user value, a method of user electricity behavior portrait based on QFPAK-means (quantum flower pollination K-means) clustering is proposed. Methods: Through the quantum flower pollination algorithm, considering the overhead cost, the optimal classification number is automatically determined, and on this basis, K-means clustering is completed. In the meantime, the typical power consumption patterns of users are extracted by using the K-means clustering algorithm based on quantum flower pollination, and the features are extracted as the power consumption behavior portraits of users. Results: Through the comparative simulation of different methods, the effectiveness of the proposed algorithm is verified, which can provide outstanding guidance for power grid companies to expand their business and improve customer service levels. Conclusion: A method of user electricity behavior portrait based on QFPAK-means clustering is proposed to further explore user value, and the experimental results demonstrate the effectiveness and advantage of the proposed method.

Background: Electric load forecasting plays an essential role in the dispatching operation of power systems. It can be divided into long-term, medium-term, and short-term according to the forecast time. Accurate short-term electric forecasting helps the system operate safely and reliably, reduces resource waste, and improves economic efficiency. Objective: To fully use the time-series characteristics in load data and improve the accuracy of short-term electric load forecasting, we propose an improved Informer model called Nysformer. Methods: Firstly, the input of data is improved, and the information is input into the model in the form of difference. Then, the Nystrom self-attention mechanism was proposed, approximating the standard self-attention mechanism using an approximation with O(n) time complexity and memory utilization. Results: We conducted experiments on a publicly available dataset, and the results show that the proposed Nysformer model has lower time complexity and higher accuracy than the standard Informer model. Conclusion: An improved informer network is proposed for short-term electric load forecasting, and the experimental results demonstrate the proposed model Nysformer can improve the accuracy of short-term electric load forecasting.

Background: Oil-immersed distribution transformer is an important power transmission and distribution equipment in the power system. If it fails, it will cause huge economic losses and safety hazards. It is of great significance to identify and diagnose its faults, find potential faults in time, and restore normal operation. Objective: To detect transformer fault, a transformer fault diagnosis method based on Graph Markov Neural Networks for Particle Swarm Optimization algorithm (PSO-GMNN) is proposed. Methods: Five common dissolved gases in transformer oil are used to construct a 22-dimensional feature set to be selected, and then the similarity between each feature vector is calculated by using Mahalanobis Distance. The graph structure is constructed with feature vectors as vertices and similarities as edges. Finally, the Particle Swarm Optimization algorithm is used to optimize the initial weights of Graph Markov Neural Networks, and then transformer fault diagnosis is realized. Results: The experiments are performed in the environment of Python 3.7, PyTorch 1.6.0, and the validity of the proposed method is verified by a comparative analysis of the detection accuracy between the proposed method and existing mainstream methods. Conclusion: A transformer fault diagnosis method based on Graph Markov Neural Networks for Particle Swarm Optimization algorithm is proposed to detect transformer fault, and the experimental results demonstrate the effectiveness and advantage of the proposed method.

Apple is one of the most successful companies in the electronic products industry. Its success is indispensable to its effective marketing strategies. This paper focuses on analyzing the psychological trick it used in its marketing strategy, mainly the endowment effect and status quo bias. It investigates how Apple uses these cognitive biases to attract newcomers to use its products and how it cultivates loyal consumers. The endowment effect refers to a circumstance to which an individual attaches higher importance to the object that they own than the same object they do not own. Apple's showroom enables consumers to play around with its products which gives the consumer a sense of ownership that make consumers become more painful to relinquish its product. Status quo bias describes the circumstance where people prefer to maintain the current state and are reluctant to change. It helps Apple to keep the existing consumers around, which also gives Apple more incentive to constantly upgrade its products and induce consumers to buy. Lastly, this paper will discuss what consumers could do to avoid being “manipulated” by Apple’s marketing strategy and falling into the consumption trap.

Background: As many EVs (EVs) are connected to the grid, transactions between EVs and the grid will have problems such as poor privacy and affecting the stability of the grid. This paper uses consortium blockchain to design a safe and privacy-preserving scheme for the two-way power transaction between EVs and the grid. Objective: : To reduce the adverse impact of disorderly charging of large-scale EVs on the power grid, the total load variance is minimized by optimizing EVs' charging/discharging period. Methods: We propose to use a heuristic algorithm, an improved multi-objective gray wolf algorithm, to solve this problem. Results: The simulation results show that the model can effectively smooth load fluctuations and improve user benefits. Conclusion: Our method can effectively reduce the load fluctuation of the grid while ensuring the economic benefits of users. Qualitative security and privacy analysis show that the solution helps to improve the security and privacy of electricity transactions.

Although cloud computing is one of the promising technologies for online business services, how to schedule real-time cloud jobs with high quality of service (QoS) is still challenging current techniques. With the advancing of machine learning, deep reinforcement learning (DRL) has demonstrated its outstanding capability in dispatching time-sensitive tasks. However, the reinforced rewards in DRL are typically unavailable until the completion of the scheduling for all the jobs. Considering the fact that the trajectory of jobs in cloud is always long, current DRL-based solutions will meet challenges in finding the trajectories with high rewards, and thus would have issues such that the finally trained scheduling policy is suboptimal. To improve the problem, in this article, we propose a more advanced approach called a deep adversarial imitation reinforcement learning (AIRL) framework for scheduling time-sensitive cloud jobs. Specifically, we focus on scheduling user requests in a way to maximize job successful rate along with a significant reduction on job response time. We present the detailed design of our method, and our experimental results demonstrate that AIRL can generally outperform the existing cloud job scheduling approaches, including the DRL-based method, in the presence of different real-time workload and computing resource configurations.

Background: Complex structures such as a high proportion of power electronic equipment has brought new challenges to the safe and stable operation of new-type power system, increasing the possibility of the system being attacked, especially the more complex Advanced Persistent Threat (APT). This kind of attack has a long duration and strong concealment. Objective: Traditional detection methods target a relatively single attack mode, and the time span of APT processed is relatively short. None of them can effectively capture the long-term correlation in the attack, and the detection rate is low. These methods can’t meet the safety requirements of the new-type power system. In order to solve this problem, this paper proposes an improved transformer model called STSA-transformer algorithm, and applies it to the detection of APT in new-type power systems. Method: In the STSA-transformer model, the network traffic collected from the power system is first converted into a sequence of feature vectors, and the location information and local feature of the sequence, is extracted by combining position encoding with convolutional embedding operations, and then global characteristics of attack sequences is captured using the multi-head self-attention mechanism of the transformer encoder, the higher-frequency features of the attention are extracted through the self-learning threshold operation, combined with the PowerNorm algorithm to standardize the samples, and finally classify the network traffic of the APT. Results: After multiple rounds of training on the model, the expected effect can be achieved and applied to the APT detection of a new-type power system. Conclusion: The experimental results show that the proposed STSA-transformer algorithm has better detection accuracy and lower detection false-alarm rate than traditional deep learning algorithms and machine learning algorithms.

Super-enhancers (SEs) are important transcriptional regulators in tumorigenesis; however, the functional characterization and clinical significance of SEs in lung adenocarcinoma (LUAD) remain unclear. By using H3K27ac ChIP-seq data of two LUAD cell lines and eight lung tissues, we detected 1045 cancer-specific and 5032 normal-specific SEs. Compared to normal-specific SEs, cancer-specific SEs have different regulatory mechanisms where associated target genes were enriched in critical tumor-related pathways and tended to be regulated by transcription factors of Fos Proto-Oncogene, AP-1 Transcription Factor Subunit and Jun Proto-Oncogene, AP-1 Transcription Factor Subunit families. By using expression data of 513 LUAD and 57 adjacent samples from The Cancer Genome Atlas and 80 tumor-normal paired LUAD samples from the Nanjing Lung Cancer Cohort study, we performed differential expression analysis of target genes for SEs and defined 243 crucial SEs. Unsupervised clustering of crucial SEs revealed two subtypes with different levels of genomic aberrations (i.e., mutation and copy number alteration) and clinical outcomes (progression-free interval: p = 0.030; disease-free interval: p = 0.047). In addition, patients with adverse clinical outcomes were more sensitive to three small molecule inhibitors (bortezomib, doxorubicin, and etoposide), and their targets (PSMB5 and TOP2A) also have elevated expression levels among these patients. Taken together, our findings provided a comprehensive characterization of SEs in LUAD and emphasized their clinical significance in LUAD therapy.

Background: As the integration of communication networks with power systems is getting closer, the number of malicious attacks against the cyber-physical power system is increasing substantially. The data integrity attack can tamper with the measurement information collected by Supervisory Control and Data Acquisition (SCADA), which can affect important decisions of the power grid and pose a significant threat to normal operation. Objective: In order to defend against the data integrity attack, and safeguard the normal operation of the power system, we propose a defense method based on improved WGAN (Wasserstein Generative Adversarial Networks). Method: Firstly, through the training of the discriminator and generator, the discriminator identifies and eliminates the measurements damaged by the data integrity attack, and the generator uses the temporal and spatial correlation of the power grid measurements to generate complementary measurements which are infinitely close to the original normal data. Meanwhile, using the improved WGAN, the training stability and the convergence speed are significantly improved, and the quality of complementary data is much higher. Results: Extensive simulation experiments were carried out in the IEEE-14 and IEEE-118 standard bus systems. By comparing the deviations between the complementary data and normal data under different iteration times and methods, the mean squared error of the deviations with the proposed method is greatly reduced than traditional methods. The excellent recovery performance of the defense method based on improved WGAN is verified. Conclusion: A smart grid data integrity attack defense method based on improved WGAN is proposed to detect data integrity attacks, and the experimental results demonstrate the recovery effectiveness of the proposed method.

Background: With the development of technologies such as the Internet of Things (IoT) and cloud/edge computing, a large number of edge devices in the smart grid accomplish information interconnection and generate massive amounts of data. On the one hand, smart grids need to obtain a large amount of grid data from edge terminal devices. On the other hand, edge computing also brings some security threats. Therefore, edge data security faces major challenges. Objective: In order to ensure the security of data in the edge computing environment of the smart grid, we propose an edge data storage scheme (BlockSE) for the smart grid edge computing environment. Method: BlockSE combines permissioned blockchain and smart contract technology to achieve secure storage of data on edge. We adapted ring signature technology to achieve privacy preserving of participating nodes. To allocate the storage resources of edge servers fairly and transparently, we designed a storage resource allocation algorithm based on the smart contract, whereby edge devices can obtain storage resources fairly according to demand. Results: Simulation experiments were performed; the results show the effectiveness of the proposed BlockSE scheme. Conclusion: This paper focused on data security in the smart grid's edge computing environment and proposed a secure storage scheme for edge data based on permissioned blockchain. The evaluation shows the safety, effectiveness, and practicability of the proposed BlockSE scheme.

The existing static ABAC(Attribute-Based Access Control) model cannot fully meet the increasingly complex, dynamic and scalable demands of the power grid. At the same time, its versatility and flexibility bring high costs. Additionally, the increasing complexity of organizational systems and the need for federated access to their resources make implementing and managing access control more challenging. This paper proposes a fine-grained dynamic access control method based on Kformer to automate authorization management tasks. We use Kformer, which filters and integrates external knowledge through feed-forward layers in Transformer. Then, we use BERT(Bidirectional Encoder Representations from Transformer) to perform feature extraction on the input fused text, extract the implied attribute-authority relationship from the log records and external documents, and finally, perform sequence modeling on the extracted attribute features and input the obtained results. The final authorization result is obtained by classification through the softmax function in the final fully connected layer. The authorization management of the user’s request to the object is dynamically completed. Finally, using the access data of the grid information system to evaluate the method proposed by us, the experimental results show that the model can continuously monitor the access behavior of users inside the grid information system, change the access rights of entities and adjust the policy in real-time, and carry out dynamic access authorization. At the same time, the accuracy of the generated access control policy can reach 87.73%.

Suppl. Table 2. CSF and Matching Tissues Available for the Study Suppl. Table 3. Metabolite concentrations in the three cohorts (t-test Statistics) Suppl. Table 4. Site-specific thresholds for D-/L-2HG Suppl. Table 5. Information about site-specific accuracy for D-2HG Suppl. Table 6. Tumor tissue sample demographics tested in parallel by MS and NMR

Suppl. Table 1. Histology, age, gender, diagnosis, site of CSF draws, longitudinal # and IDH1/2 mutation status of 84 tumor samples analyzed. Highlighted in 'yellow' are CSF samples that tested positive for IDH1 mutant staining, while their DNA indicated WT IDH.

Purpose: Elevation in D-2-Hydroxyglutarate (D-2HG) has recently emerged as a mandatory byproduct of mutated Isocitrate Dehydrogenase (IDH) genes 1 and 2 in glioma patients. The goal of the present study was to demonstrate the feasibility of detection of elevated levels of D-2HG in the cerebrospinal fluid (CSF) of glioma patients that carry point substitutions in the IDH gene.Experimental Design: We developed a mass spectrometry (MS)–based platform to detect and quantify the D- and L-forms of 2HG in the CSF of glioma patients. Three independent cohorts of patients were analyzed, comprising a total of 176 samples derived from 84 patients. The levels of D- and L-2HG were used to stratify patients into IDH wild-type or IDH-mutated groups using an empirically obtained threshold of 0.69 μmol/L.Results: Using this platform, a greater than 17-fold mean increase in D-2HG was observed in the CSF of patients with IDH mutant versus wild-type gliomas. The means for the D-2HG levels in CSF were 0.427 μmol/L in wild-type and 7.439 μmol/L in mutant groups. The C statistic for the receiver operator curve was 0.938, with 84% sensitivity, 90% specificity, and 89% accuracy to detect D-2HG. The levels of D- and L-2HG in CSF from wild-type patients varied by location of CSF draw (cisternal > ventricular > lumbar).Conclusions: Our findings demonstrate that the CSF of patients harboring IDH mutant gliomas contain increased levels of D-2HG, which can be reliably detected with a MS-based platform. Clin Cancer Res; 22(24); 6256–65. ©2016 AACR.

In this manuscript, we propose a two-step lighting DNA tetrahedral nanoprobe for precise imaging-guided photodynamic therapy of tumors.

The deployment and operation of load frequency control (LFC) systems rely on the latest network and communication technologies. This exposes it to network attacks, such as DoS attacks, which affect the running of the system. In order to offset the impact of DoS attacks, this article proposes a data prediction-based defense method. First, the cyber–physical model of LFC is constructed to derive the frequency. Based on the model, a prediction model organically combined with the hierarchical attention network is applied to restore missing measurements. Then the proposed method can detect and eliminate the impact of DoS attacks by comparing and replacing the measurements, rather than adopting flexible LFC strategies. Finally, simulation experiments are carried out on three different power generation systems. The results prove that the suggested method can effectively resist DoS attacks.