Data Mining - Concepts and Techniques.

Introduction to stochastic programming

A systematic literature review of blockchain-based applications: Current status, classification and open issues

Trends in extreme learning machines

Differential Evolution (DE) is arguably one of the most powerful and versatile evolutionary optimizers for the continuous parameter spaces in recent times. Almost 5 years have passed since the first comprehensive survey article was published on DE by Das and Suganthan in 2011. Several developments have been reported on various aspects of the algorithm in these 5 years and the research on and with DE have now reached an impressive state. Considering the huge progress of research with DE and its applications in diverse domains of science and technology, we find that it is a high time to provide a critical review of the latest literatures published and also to point out some important future avenues of research. The purpose of this paper is to summarize and organize the information on these current developments on DE. Beginning with a comprehensive foundation of the basic DE family of algorithms, we proceed through the recent proposals on parameter adaptation of DE, DE-based single-objective global optimizers, DE adopted for various optimization scenarios including constrained, large-scale, multi-objective, multi-modal and dynamic optimization, hybridization of DE with other optimizers, and also the multi-faceted literature on applications of DE. The paper also presents a dozen of interesting open problems and future research issues on DE.

Recent advances in differential evolution – An updated survey

The invention relates to an imperialistic competitive algorithm-based carbon-energy combined flow solving method. Carbon-energy combined flow of a power system is optimized by adopting a multicultural transfer-based imperialistic competitive reinforcement learning algorithm; each empire adopts a value function matrix in the reinforcement learning algorithm as a cultural matrix of the empire; each optimization nation updates the cultural matrix through interaction with the environment and performs action selection according to the cultural matrix to improve the globality of a policy; and knowledge in the cultural matrix is stored in real time and multicultural transfer is performed to improve the optimization efficiency of subsequent new tasks. According to the adopted method, the cultural transfer-based imperialistic competitive reinforcement learning algorithm is a relatively new intelligent algorithm and has the advantages of high convergence speed, better global convergence, higher stability and the like, so that quick carbon-energy combined flow optimization of the large-scale power system is realized.

Imperialistic competitive algorithm-based carbon-energy combined flow solving method

In deregulated electricity markets, market players have an important task of implementing optimal offers, also called bids, for each trading intervals to achieve the goal of profit-maximizing. This paper applies Generalized autoregressive conditional heteroskedastic (GARCH) methodology to predict electricity prices and then proposes a novel approach of designing the optimal bidding strategies based on generator's degree of risk taking. Case studies using a coal generator located in Australian national electricity market are conducted. The proposed method is compared with a traditional bidding method to further verify its effectiveness. (8 pages)

Optimal GENCO's bidding strategies under price uncertainty in poolco electricity market

Carbon/TiO2 composites were prepared via the reaction under Autogenic Pressure at Elevated Temperature (RAPET) using alkoxides as precursor, and then porous TiO2 hollow spheres were derived after removing the carbon ingredient by calcination at 600°C. The influence of surfactant additives, including the addition ratio and the nature of the surfactants, on the morphology and the structures of the Carbon/TiO2 composites and the derived TiO2 were also studied with scanning electron microscopy (SEM), X-ray diffraction (XRD), UV-Vis diffuse reflectance spectrophotoscopy (DRS) and nitrogen adsorption-desorption measurements. The results revealed that the morphology of the products turned to spherical and then fusiform and the structures turned from hollow to solid with the increasing of surfactant additive. The BET surface area of the hollow TiO2 was modified from 12m2/g to 57m2/g after calcinations. The XRD investigation indicates that the phases of the TiO2 in both the carbon/TiO2 composites and the derived TiO2 hollow spheres are anatase.

TiO2 Hollow Spheres Obtained under Autogenic Pressure at Elevated Temperature

/pdf/intelligent-grid-research-cluster-project-2-55why4run9.pdf

Intelligent grid research cluster - project 2

Non-intrusive load monitoring (NILM) is essential for understanding customer's power consumption patterns and may find wide applications like carbon emission reduction and energy conservation. The training of NILM models requires massive load data containing different types of appliances. However, inadequate load data and the risk of power consumer privacy breaches may be encountered by local data owners during the NILM model training. To prevent such potential risks, a novel NILM method named Fed-NILM which is based on Federated Learning (FL) is proposed in this paper. In Fed-NILM, local model parameters instead of local load data are shared among multiple data owners. The global model is obtained by weighted averaging the parameters. Experiments based on two measured load datasets are conducted to explore the generalization ability of Fed-NILM. Besides, a comparison of Fed-NILM with locally-trained NILMs and the centrally-trained NILM is conducted. The experimental results show that Fed-NILM has superior performance in scalability and convergence. Fed-NILM outperforms locally-trained NILMs operated by local data owners and approximates the centrally-trained NILM which is trained on the entire load dataset without privacy protection. The proposed Fed-NILM significantly improves the co-modeling capabilities of local data owners while protecting power consumers' privacy.

Junhua Zhao

Papers

Imperialistic competitive algorithm-based carbon-energy combined flow solving method

Optimal GENCO's bidding strategies under price uncertainty in poolco electricity market

TiO2 Hollow Spheres Obtained under Autogenic Pressure at Elevated Temperature

Intelligent grid research cluster - project 2

Fed-NILM: A Federated Learning-based Non-Intrusive Load Monitoring Method for Privacy-Protection.