Visible to the public Load Forecasting of Privacy-Aware Consumers

TitleLoad Forecasting of Privacy-Aware Consumers
Publication TypeConference Paper
Year of Publication2019
AuthorsChin, J., Zufferey, T., Shyti, E., Hug, G.
Conference Name2019 IEEE Milan PowerTech
Date PublishedJune 2019
ISBN Number978-1-5386-4722-6
KeywordsCollaboration, composability, consumer aggregation levels, consumer privacy, consumer privacy risks, data privacy, data-driven grid management, electric grid, energy consumption, forecast accuracy, Forecasting, grid visible consumer load profile, high spatial resolutions, higher aggregation levels, Human Behavior, load forecasting, Load modeling, load profiles, load-forecasting, load-levelling scheme, Metrics, model-distribution predictive control, Mutual information, planning techniques, policy-based governance, polling frequency constraints, power engineering computing, predictive control, Predictive models, privacy, privacy protection schemes, privacy-aware consumers, pubcrawl, regression analysis, report consumption data, resilience, Resiliency, Scalability, short-term load forecasts, SM data, smaller consumer aggregations, smart grid consumer privacy, smart meter, smart meters, STLF accuracy, Support vector machines, support vector regression, temporal resolutions

The roll-out of smart meters (SMs) in the electric grid has enabled data-driven grid management and planning techniques. SM data can be used together with short-term load forecasts (STLFs) to overcome polling frequency constraints for better grid management. However, the use of SMs that report consumption data at high spatial and temporal resolutions entails consumer privacy risks, motivating work in protecting consumer privacy. The impact of privacy protection schemes on STLF accuracy is not well studied, especially for smaller aggregations of consumers, whose load profiles are subject to more volatility and are, thus, harder to predict. In this paper, we analyse the impact of two user demand shaping privacy protection schemes, model-distribution predictive control (MDPC) and load-levelling, on STLF accuracy. Support vector regression is used to predict the load profiles at different consumer aggregation levels. Results indicate that, while the MDPC algorithm marginally affects forecast accuracy for smaller consumer aggregations, this diminishes at higher aggregation levels. More importantly, the load-levelling scheme significantly improves STLF accuracy as it smoothens out the grid visible consumer load profile.

Citation Keychin_load_2019