Distributed electricity load forecasting model mining based on hybrid gene expression programming and cloud computing

Short-Term Building Electrical Energy Consumption Forecasting by Employing Gene Expression Programming and GMDH Networks

Over the past decade, energy forecasting applications not only on the grid side of electric power systems but also on the customer side for load and demand prediction purposes have become ubiquitous after the advancements in the smart grid technologies. Within this context, short-term electrical energy consumption forecasting is a requisite for energy management and planning of all buildings from households and residences in the small-scale to huge building complexes in the large-scale. Today’s popular machine learning algorithms in the literature are commonly used to forecast short-term building electrical energy consumption by generating an abstruse analytical expression between explanatory variables and response variables. In this study, gene expression programming (GEP) and group method of data handling (GMDH) networks are meticulously employed for creating genuine and easily understandable mathematical models among predictor variables and target variables and forecasting short-term electrical energy consumption, belonging to a large hospital complex situated in the Eastern Mediterranean. Consequently, acquired results yielded mean absolute percentage errors of 0.620% for GMDH networks and 0.641% for GEP models, which reveal that the forecasting process can be accomplished and formulated simultaneously via proposed algorithms without the need of applying feature selection methods.

Operation Health Assessment of Power Market Based on Improved Matter-Element Extension Cloud Model

The complex power system and trading environment in China has led to higher requirements for the efficient and stable operation of the electricity market. With the continuous advancement of power system reforms, regular evaluation of the operation of the market can help us grasp its status and trends, which is of great significance for ensuring its sustainable development. In order to effectively evaluate the current operational status of the electricity market, the concept of operation health degree of power market (OHDPM) is proposed to measure whether the operation is safe, efficient, and sustainable. This paper establishes an improved model framework based on the matter-element extension theory for evaluation. In order to effectively avoid information distortion and loss in the evaluation process, this paper combines the cloud model, matter element extension theory, ideal point method (IPM), and cloud entropy optimization algorithm to deal with this problem. The matter-element extension cloud model (MEECM) can clearly represent the characteristics of the object to be evaluated. IPM is used to determine the weight of the index. For the improved matter-element extension model, the traditional rules of “3En” and “50% relevance” are taken into account, and the method of solving the entropy is optimized. Then, for the correlation degree between the object to be evaluated and the graded normal cloud, the weight vector solved by the IPM is used to weigh the cloud correlation degree, which can give a reliable evaluation result. The health evaluation index system of power market operation includes 16 sub-indicators in five categories: supply side, demand side, coordinated operation, market security, and sustainable development. In the empirical analysis, the OHDPM situation in Y Province was evaluated in May 2019. The results prove that the OHDPM level is medium, and the importance and health level of each index are given. The reliability of the power system, transaction price stability, Lerner index, residual proportion of producers, and user satisfaction have a greater impact on the health status. Finally, in order to verify the validity and stability of the model, different methods are used to evaluate the evaluation objects, and the advantages of OHDPM evaluation based on the model framework proposed in this paper are proven.