Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Privacy-Preserving Framework for Cloud-Based HVAC Control

Zhenan Feng, Ehsan Nekouei

TL;DR

The paper tackles privacy risks in cloud-based HVAC control by embedding fully homomorphic encryption (CKKS) into an MPC framework that regulates temperature and CO2. It introduces an encrypted fast gradient method for solving two MPCs on ciphertext and couples this with an optimal event-triggering unit to drastically cut encrypted communications, while two randomized triggering strategies mitigate leakage from timing information. The approach is validated with TRNSYS simulations, showing more than a 60% reduction in communication and computation costs with negligible impact on control performance. Overall, the work delivers a practical, privacy-preserving, and scalable solution for cloud-based building automation with significant potential for deployment across portfolios of buildings.

Abstract

The objective of this work is (i) to develop an encrypted cloud-based HVAC control framework to ensure the privacy of occupancy information, (ii) to reduce the communication and computation costs of encrypted HVAC control,(iii) to reduce the leakage of private information via the triggering time instances. Occupancy of a building is sensitive and private information that can be accurately inferred by cloud-based HVAC controllers. To ensure the privacy of the privacy information, in our framework, the measurements of an HVAC system are encrypted by a fully homomorphic encryption prior to communication with the cloud controller. We first develop an encrypted algorithm that allows the cloud controller to regulate the indoor temperature and CO_2 of a building. We next develop an event-triggered control policy to reduce the communication and computation costs of the encrypted HVAC control. We cast the optimal design of the event-triggered policy as an optimal control problem. Using Bellman's optimality principle, we study the structural properties of the optimal event-triggered policy and show the necessary information for optimal triggering policy. We also show that the optimal design of the event-triggered policy can be transformed into a Markov decision process by introducing new states. As the triggering time instances are not encrypted, there is a risk that the cloud may use them to deduce sensitive information. To mitigate this risk, we introduce two randomized triggering strategies. We finally study the performance of the developed encrypted HVAC control framework using the TRNSYS simulator. Our numerical results show that the proposed framework not only ensures efficient control of the indoor temperature and CO$_2$ but also reduces the computation and communication costs of encrypted HVAC control by at least 60%.

A Privacy-Preserving Framework for Cloud-Based HVAC Control

TL;DR

The paper tackles privacy risks in cloud-based HVAC control by embedding fully homomorphic encryption (CKKS) into an MPC framework that regulates temperature and CO2. It introduces an encrypted fast gradient method for solving two MPCs on ciphertext and couples this with an optimal event-triggering unit to drastically cut encrypted communications, while two randomized triggering strategies mitigate leakage from timing information. The approach is validated with TRNSYS simulations, showing more than a 60% reduction in communication and computation costs with negligible impact on control performance. Overall, the work delivers a practical, privacy-preserving, and scalable solution for cloud-based building automation with significant potential for deployment across portfolios of buildings.

Abstract

The objective of this work is (i) to develop an encrypted cloud-based HVAC control framework to ensure the privacy of occupancy information, (ii) to reduce the communication and computation costs of encrypted HVAC control,(iii) to reduce the leakage of private information via the triggering time instances. Occupancy of a building is sensitive and private information that can be accurately inferred by cloud-based HVAC controllers. To ensure the privacy of the privacy information, in our framework, the measurements of an HVAC system are encrypted by a fully homomorphic encryption prior to communication with the cloud controller. We first develop an encrypted algorithm that allows the cloud controller to regulate the indoor temperature and CO_2 of a building. We next develop an event-triggered control policy to reduce the communication and computation costs of the encrypted HVAC control. We cast the optimal design of the event-triggered policy as an optimal control problem. Using Bellman's optimality principle, we study the structural properties of the optimal event-triggered policy and show the necessary information for optimal triggering policy. We also show that the optimal design of the event-triggered policy can be transformed into a Markov decision process by introducing new states. As the triggering time instances are not encrypted, there is a risk that the cloud may use them to deduce sensitive information. To mitigate this risk, we introduce two randomized triggering strategies. We finally study the performance of the developed encrypted HVAC control framework using the TRNSYS simulator. Our numerical results show that the proposed framework not only ensures efficient control of the indoor temperature and CO but also reduces the computation and communication costs of encrypted HVAC control by at least 60%.
Paper Structure (32 sections, 3 theorems, 47 equations, 15 figures, 2 algorithms)

This paper contains 32 sections, 3 theorems, 47 equations, 15 figures, 2 algorithms.

Table of Contents

  1. Introduction
  2. Motivation
  3. Contributions
  4. Related Work
  5. Organization
  6. Encrypted Model Predictive HVAC Control
  7. Building Model
  8. Thermal Model
  9. CO$_2$ Model
  10. Encrypted HVAC control
  11. Encrypted temperature regulation
  12. Encrypted CO$_2$ regulation
  13. Optimal Design of Event-triggering Unit
  14. The Sufficient Information for Decision-making
  15. Dynamic Programming Decomposition
  16. ...and 17 more sections

Key Result

Theorem 1

Let $a_t^\star$ denote the optimal event-triggering policy at time $t$. Then, $a_t^\star$ depends on $\bm{x}_t,\bm{x}_{s_t^\star}, L_t$ where $\bm{x}_t$ is the current state, $\bm{x}_{s_t^\star}$ is the last communicated state with the controller, $L_t$ is the time since last communication between t

Figures (15)

  • Figure 1: The comparison of true occupancy and predicted building occupancy over time.
  • Figure 2: The proposed encrypted cloud-based HVAC control scheme.
  • Figure 3: The time evolution of $L_t$.
  • Figure 4: The building shape used in the TRNSYS for simulation.
  • Figure 5: The performance of the HVAC system in regulating the temperature and CO$_2$ under the optimal and threshold-based event-triggering policies.
  • ...and 10 more figures

Theorems & Definitions (4)

  • Remark 1
  • Theorem 1
  • Theorem 2
  • Theorem 3