An open solution to provide personalized feedback for building energy management

Andrea Monacchi, Fabio Versolatto, Manuel Herold, Dominik Egarter, Andrea M. Tonello, Wilfried Elmenreich

Abstract

The integration of renewable energy sources increases the complexity of power grid maintenance. The dynamic nature of generation and consumption necessitates demand-response mechanisms to optimize energy resource utilization. This paper presents Mjölnir, an open-source energy management framework that provides personalized, appliance-level feedback to residential users. By analyzing high-resolution data from the GREEND dataset, we identify significant energy-saving opportunities through automated policies. Our findings suggest that tailored feedback and strategic appliance management can lead to energy savings of up to 34% for specific household devices.

Introduction

Traditional energy billing provides aggregated, delayed information that fails to empower consumers to make informed decisions about their energy usage. As the grid transitions toward decentralized renewable sources, the need for "demand-side management" becomes critical. Research indicates that the granularity and timing of feedback significantly impact consumer behavior.

Energy savings potential by feedback type

As shown in Figure 1, indirect feedback (like enhanced billing) offers modest savings, while direct, real-time, and tailored appliance-level feedback can drive savings exceeding 12%. This paper introduces Mjölnir, a system designed to bridge this information gap by translating raw data into actionable advice.

The Mjölnir Framework

Mjölnir is a web-based energy management system (EMS) designed to ingest data from both aggregate smart meters and individual appliance smart plugs. The framework consists of hardware measurement units and management software released under an open-source license.

A key component of Mjölnir is the Smart Advisor Widget. To mitigate "alert fatigue," the system employs an information filtering mechanism. It acts as a recommendation engine, learning user preferences. If a user dismisses a suggestion, the system adapts, focusing on high-impact, high-acceptance tips to ensure long-term engagement.

Consumption Analysis

The development of Mjölnir was informed by a year-long measurement campaign across eight households in Italy and Austria, resulting in the GREEND dataset. This high-resolution (1 Hz) data revealed distinct consumption patterns across different sites.

Appliance-level power consumption across four test sites

Figure 2 illustrates the monthly energy consumption for various appliances at four test sites (S0-S3). Several key insights emerged from this data:

  • The "Always-On" Drain: Standby power consumption is a significant source of waste. For instance, ADSL modems left active 24/7 can waste up to 37% of their total energy relative to actual usage hours.
  • Appliance Misplacement: In many homes, older, less efficient devices like Plasma TVs were found in high-traffic areas (living rooms), while more efficient LCD TVs were relegated to bedrooms. This leads to disproportionately high energy use due to the Plasma TV's higher power draw and longer operating hours.
  • Economic Incentives: In regions like Italy, time-of-use tariffs offer lower rates at night. However, the analysis showed that the current financial incentive is often too small (e.g., €0.12/month for shifting a washing machine) to motivate significant behavior change without automation.

Results and Discussion

Based on the data analysis, four core energy efficiency policies were formulated: lighting upgrades, device diagnostics, shedding standby losses, and device shifting.

Appliance Replacement and Diagnostics

The Mjölnir system's diagnostic logic can identify aging, inefficient appliances. In one test case, replacing two old fridge/freezers with modern A+++ models was estimated to save 34 kWh per month, representing an 11% reduction in the total household energy footprint.

Strategic Device Swapping

By identifying "energy hogs" through appliance-level monitoring, users can be advised to swap device locations. Swapping a living room Plasma TV with a bedroom LCD TV was calculated to reduce television-related energy consumption by 23% to 34%.

Conclusion

The Mjölnir framework provides a scalable, open-source solution for residential energy management. By moving beyond aggregate data to personalized, appliance-level feedback, the system empowers users to identify and eliminate waste. Future work will focus on integrating Non-Intrusive Load Monitoring (NILM) to reduce hardware costs and implementing automated control of smart loads to further optimize energy usage without requiring constant user intervention.

Summary updated

Abstract

The integration of renewable energy sources increases the complexity in maintaining the power grid. In particular, the highly dynamic nature of generation and consumption demands for a better utilization of energy resources, which seen the cost of storage infrastructure, can only be achieved through demand-response. Accordingly, the availability of energy and potential overload situations can be reflected using a price signal. The effectiveness of this mechanism arises from the flexibility of device operation, which is nevertheless heavily reliant on the exchange of information between the grid and its consumers. In this paper, we investigate the capability of an interactive energy management system to timely inform users on energy usage, in order to promote an optimal use of local resources. In particular, we analyze data being collected in several households in Italy and Austria to gain insights into usage behavior and drive the design of more effective systems. The outcome is the formulation of energy efficiency policies for residential buildings, as well as the design of an energy management system, consisting of hardware measurement units and a management software. The Mjölnir framework, which we release for open use, provides a platform where various feedback concepts can be implemented and assessed. This includes widgets displaying disaggregated and aggregated consumption information, as well as daily production and tailored advices. The formulated policies were implemented as an advisor widget able to autonomously analyze usage and provide tailored energy feedback. The advisor is estimated leading to a potential of 34% of savings using measurement data from the GREEND dataset.
BibTeX
@article{monacchi2017open,
  author = {Andrea Monacchi and Fabio Versolatto and Manuel Herold and Dominik Egarter and Andrea M. Tonello and Wilfried Elmenreich},
  title = {{An open solution to provide personalized feedback for building energy management}},
  journal = {J. Ambient Intell. Smart Environ.},
  year = {2017},
  url = {https://openreview.net/forum?id=7g9O4yNHnbN},
}
Figure