A measurement error prediction framework for smart meters in typical regions

•With the field data collected from the high altitude region, the new framework we proposed has been proven to be excellent by comparing with several common machine learning methods, and it has universal applicability and can be applied to other typical regions except for high altitude regions.•We propose a new method based on the HBO-BiLSTM model to predict SMs’ ME. In comparison to models of BiLSTM, PSO-BiLSTM, GA-BiLSTM, and GWO-BiLSTM, the HBO-BiLSTM model exhibits better advantages in predicting the SMs’ ME.•The redundancy problem among multiple environments is solved, the impact of outliers on the ME prediction framework is reduced, and the prediction accuracy of the framework is enhanced by eliminating the environment stresses that have little effect on ME and cleaning the data with IFLOF outlier detection algorithm. The measurement error (ME) of smart meters (SMs) is a key index for assessing their performance, so accurate prediction of SMs’ ME is essential. However, SMs operate in all parts of the world, and the factors that impact the SMs’ ME differ across regions. Therefore, we propose a novel and general framework to predict the SMs’ ME. Firstly, we study the influence of environment stress on SMs’ ME by the Pearson correlation coefficient (PCC) and Least squares method (LSM), select the environment stresses that have a greater impact on SMs’ ME, and clean those environment data and SMs’ ME data by the Isolated Forest and Local Outlier Factor algorithm (IFLOF). Subsequently, a new method based on the Heap-Based Optimizer of Bi-directional Long Short-Term Memory network (HBO-BiLSTM) is proposed to predict the SMs’ ME. To illustrate the framework we proposed, the framework is compared with some well-known machine learning methods with field data collected from the high altitude regions, the results indicated that the framework has excellent prediction ability, which can provide technical support for health management of SMs in typical regions.