Intelligent Solar Energy Devices Cybersecurity System

Deployment of the smart grid that relies on new intelligent technologies using two-way communications and Internet connectivity increases vulnerability of the grid to potential cyberattacks. Although many cybersecurity (detection or prevention) software tools have been developed, all of them have limitations and, thus, cannot deliver protection against cyberattacks in the smart grid. An advanced cybersecurity tool must be developed to provide more intelligent shields to fend off known and new-generation cyberattacks to secure the electronic devices associated with the generation of solar energy (for example, inverters, DC-DC optimizers, and smart meters) that are used in the smart grid. Such a tool will help to ensure access-control, authorization, authentication, confidentiality, integrity, availability, and non-repudiation for the future smart grid and will support the SunShot initiative. The proposed risk-based cybersecurity software tool is based on intelligent decision-making algorithms that employ (1) machine learning and two branches of advanced statistical analysis and (2) correlation between control commands and states of electronic devices. These provide the artificial intelligence needed to detect and mitigate both known and new threats in the future smart grid, allowing more accurate attack detections and quicker responses compared to other methods, thus, improving the cybersecurity of electronic devices associated with the generation of solar energy. The new tool continuously monitors activities and states of devices in the grid, updates behavior models, and accurately detects, classifies, and intelligently responds to malicious activities and device failures in real time. A large-scale intelligent intrusion/failure detection software tool will be developed to evaluate system performance. Feasibility of the approach will be demonstrated by assembling and testing a technology readiness level 4 prototype. The prototype will demonstrate the capability to detect attack patterns and device failure and predict attacks in real time. The metrics that determine the prototype’s efficacy and performance will be identified.